diff --git a/CHANGELOG.md b/CHANGELOG.md
index 3510068b9..4dfd85962 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -34,6 +34,17 @@ parallel copies under `docs/` or `scripts/notes/`. At cut time: rename
   still clamps non-shell tools when set and does not cap a longer requested
   `run_shell`.
 
+### Directors
+
+- **Skywalker may DIY tiny product writes (CL-6629).** Path tools
+  (`write_file` / `edit_file` / `delete_file`) remount on the primary
+  session. Tiny/single-file/one-route bounded edits are the exception;
+  spawn remains default for substantial/multi-file/parallel/specialist
+  work (hard cap 4 workers). Docs/design still spawn shakespeare /
+  bruckheimer / brand-reviewer except one-line fixes. Greybeard stays
+  write-free. Shell file-writes stay denied. Spawn is a judgment call,
+  not a tool ban.
+
 ## [0.2.99] - 2026-08-21
 
 Skywalker is the primary orchestrator over a closed director fleet: product write tools stay off the primary, and you cannot spawn Skywalker as a task leaf. Workers are not done until they return the four-heading report. First-party action skills ship as slashes; eval runners require an explicit provider/model pair; the style skill no longer refuses non-git folders.
diff --git a/docs/ARCHITECTURE.md b/docs/ARCHITECTURE.md
index 1c950f0a9..a8b4b4a88 100644
--- a/docs/ARCHITECTURE.md
+++ b/docs/ARCHITECTURE.md
@@ -299,12 +299,12 @@ Data-only agent plugins (`src/plugins/data-only-agent.ts`) synthesize `agentPlug
 
 ### System Prompt (`src/agent/prompts.ts`)
 
-The primary session identity is **Skywalker** (`buildChatRole` → `createSkywalkerSystemPrompt`). Product name remains Corbits Code; when asked its name, the primary answers Skywalker. Role: orchestrate-only — classify, dispatch closed directors via `task`, track the fleet, synthesize. Product mutation tools (`write_file` / `edit_file` / `delete_file`) are **not mounted** on the primary session (structural never-implement for path tools). Residual mutation surfaces: `run_shell` remains (gated; shell file-writes denied by auto-shell policy), MCP tools added after the strip are not re-filtered by `PRIMARY_DENIED_PRODUCT_TOOLS`, and leaf `writePaths` only apply to path-keyed product tools. A frontier model already knows how to code; the static prompt carries harness-specific facts and the closed-fleet orchestration policy. The base is three individually-exported sections:
+The primary session identity is **Skywalker** (`buildChatRole` → `createSkywalkerSystemPrompt`). Product name remains Corbits Code; when asked its name, the primary answers Skywalker. Role: orchestrate — classify, DIY tiny/single-file/one-route product edits, dispatch closed directors via `task` for substantial work, track the fleet, synthesize. Product mutation tools (`write_file` / `edit_file` / `delete_file`) are mounted on the primary session (CORE and `SKYWALKER_TOOLS`) so Skywalker can DIY bounded edits; spawn remains the default for substantial, multi-file, parallel, or specialist work (hard cap 4 workers). Shell file-writes stay denied by auto-shell policy. MCP tools are not re-filtered by a product-write deny list (that list is gone). Leaf `writePaths` only apply to path-keyed product tools when a profile sets them. A frontier model already knows how to code; the static prompt carries harness-specific facts and the closed-fleet orchestration policy. The base is three individually-exported sections:
 
-- `buildChatRole` — Skywalker primary identity (orchestrate; do not implement product work by default).
-- `buildHarnessFacts` — the non-derivable rules: shell file-writes are blocked, primary product mutations are unmounted (spawn implement/docs directors), dependency installs and off-limits paths need approval, images are native multimodal input, only core tools are resident (load the rest via `tool_search`; use `search_agents` before dispatching specialists), workflows run only from slash-command steps, and session memory lives at `.corbits/MEMORY.md`.
-- `buildGuidelines` — be concise, prefer `task` for product work, answer questions and diagnose visual/product feedback before editing, work autonomously for explicit coding tasks, use `lsp` for symbol work, and verify changes when practical.
-- `buildPromptDisciplineBlock` — a shared, prohibition-form section appended exactly once to every built prompt (chat and sub-agent, every provider family). Primary vs leaf wording differs for product writes: leaves are told to use `read_file`/`edit_file`/`write_file`; Skywalker is told product writes are unmounted and durable edits go through directors. Shared rules: never `cat`/`sed`/heredoc/`echo` for file work, no setting or exporting environment variables (recurring needs belong in project settings), `web_fetch`/`web_search` instead of `curl`/`wget`/hand-rolled queries, one operation per `run_shell` call, turn semantics (a tool-less reply is the final answer, no repeat searches, stop and change approach after three failed attempts, batch independent reads in parallel), and TTY output rules (short bold headers, one-line bullets, backticks for paths/commands, no wide tables).
+- `buildChatRole` — Skywalker primary identity (orchestrate; DIY tiny/bounded product edits; spawn for substantial work).
+- `buildHarnessFacts` — the non-derivable rules: shell file-writes are blocked, path tools are the DIY surface on primary (spawn implement/docs directors for substantial work), dependency installs and off-limits paths need approval, images are native multimodal input, only core tools are resident (load the rest via `tool_search`; use `search_agents` before dispatching specialists), workflows run only from slash-command steps, and session memory lives at `.corbits/MEMORY.md`.
+- `buildGuidelines` — be concise, prefer `task` for substantial product work, DIY tiny/bounded edits on the parent, answer questions and diagnose visual/product feedback before editing, work autonomously for explicit coding tasks, use `lsp` for symbol work, and verify changes when practical.
+- `buildPromptDisciplineBlock` — a shared, prohibition-form section appended exactly once to every built prompt (chat and sub-agent, every provider family). Primary vs leaf wording differs for product writes: leaves are told to use `read_file`/`edit_file`/`write_file`; Skywalker is told to DIY tiny/bounded edits with those path tools and spawn directors for substantial work. Shared rules: never `cat`/`sed`/heredoc/`echo` for file work, no setting or exporting environment variables (recurring needs belong in project settings), `web_fetch`/`web_search` instead of `curl`/`wget`/hand-rolled queries, one operation per `run_shell` call, turn semantics (a tool-less reply is the final answer, no repeat searches, stop and change approach after three failed attempts, batch independent reads in parallel), and TTY output rules (short bold headers, one-line bullets, backticks for paths/commands, no wide tables).
 
 **Provider-conditional residuals.** Per-family additions layer on top of the shared block via the same `ModelFamilyPolicy` mechanism the directors use (`src/subagent/provider-family.ts`, `src/agent/model-family-policy.ts`) — additive lines, never prompt forks. **Grok** leaves get `buildGrokLeafAntiThrashNote` (gated by `shouldApplyGrokAntiThrash` / `applyGrokFinishBias`, withheld from orchestrators): a compact finish-bias reinforcement plus a one-line reminder to route file/web work through the dedicated tools rather than `run_shell`, motivated by observed tool-routing thrash on the same harness. **Kimi** intentionally has no residual yet — `detectModelFamily` already resolves the family so callers can branch on it, but the prompt seam is left unfilled pending eval characterization of Kimi's behavior, mirroring the provisional (permissive-default) policy in `model-family-policy.ts`.
 
diff --git a/docs/IMPLEMENTATION.md b/docs/IMPLEMENTATION.md
index 28b736eb1..d27c6a3ad 100644
--- a/docs/IMPLEMENTATION.md
+++ b/docs/IMPLEMENTATION.md
@@ -158,7 +158,7 @@ Sixteen packages under `src/agent/directors/<id>/` register in `DIRECTOR_REGISTR
 2. `packageToProfile` maps envelope (`tools.allow`/`deny`) to `AgentProfile.capabilities`, `spawn.maySpawn` → `orchestrator`, and optional `writePaths`. System prompts are prefixed with a stable identity block (`formatDirectorSystemPrompt`: agent id, model role, optional skills).
 3. Nested spawn: packages with `spawn.allowlist` forward that list into nested `task` (`spawnAllowlist` on nestedDispatch). Off-list `agent` is refused. `task(agent=skywalker)` is refused (primary is not a spawned worker). Primary omits the list so plugin profiles stay reachable.
 4. `directorProfiles()` is the spawn catalog (`default-agents.ts`) — closed set minus skywalker; plugin agent profiles still load and can override by id.
-5. Primary chat role is Skywalker: `buildChatRole()` → `createSkywalkerSystemPrompt()`. Product mutation tools are stripped from the primary toolset and from CORE/CATALOG ads (`PRIMARY_DENIED_PRODUCT_TOOLS`) — never-implement is structural for path tools. Residual: `run_shell` stays on primary; MCP tools loaded later are not re-stripped by that deny list; optional `writePaths` (when a profile sets it) only gate path-keyed product tools.
+5. Primary chat role is Skywalker: `buildChatRole()` → `createSkywalkerSystemPrompt()`. Product mutation tools (`write_file` / `edit_file` / `delete_file`) live in CORE (and `SKYWALKER_TOOLS`) so they are advertised on the primary without a `tool_search` round-trip. DIY tiny/bounded edits on the parent; spawn implement/docs directors for substantial work — a prompt judgment call, not a toolset strip. `PRIMARY_DENIED_PRODUCT_TOOLS` is gone. Shell file-writes stay denied; MCP tools are not re-filtered by a product-write deny list. Optional `writePaths` (when a profile sets it) only gate path-keyed product tools.
 6. Shipped directors omit `writePaths`. The optional field is still enforced in the permission gate via ALS identity (`identity-context.ts` + `write-path-policy.ts`) when a plugin/custom profile sets it.
 7. Spawn effort: pin > package `modelRole` default (`defaultEffortForDirector`; intern=low; plan/review/orchestrator=high; implement/explore/docs/test=medium) > orchestrator/worker binary > parent inheritance. Optional skills are listed in the identity header for awareness; workers do not mount `use_skill` (guidance is baked into package system prompts). Primary mounts `use_skill` for its own skill list.
 
diff --git a/docs/PRODUCT.md b/docs/PRODUCT.md
index 73bbedc6e..b9030b850 100644
--- a/docs/PRODUCT.md
+++ b/docs/PRODUCT.md
@@ -144,7 +144,7 @@ Capabilities beyond the core toolset are opt-in plugins, enabled per workspace t
 
 ## Multi-agent (sub-agents)
 
-The primary session is always **orchestrator** (single-agent mode is gone). Its identity is **Skywalker** (product name remains Corbits Code; when asked its name, answer Skywalker): classify work, dispatch a **closed fleet of 16 directors**, track the fleet, and synthesize. Product mutation tools (`write_file` / `edit_file` / `delete_file`) are not mounted on the primary session — implement and docs workers own durable writes. Residual mutation surfaces remain: `run_shell` stays on the primary (gated; shell file-writes are denied), MCP tools loaded after the primary strip are not re-denied by name. Shipped directors have no package `writePaths`; the optional field still constrains path-keyed product tools (not shell) when a profile sets it. Yolo / skip-permissions still bypasses the write-path gate when enabled. Operator slash recipes (`/implement`, `/plan`, `/refactor`, `/review`, `/pull-request-review`, `/create-issue`, `/scribe`, `/interview`, `/ast-grep`) tell Skywalker which directors to spawn; they do not run the work on the primary.
+The primary session is always **orchestrator** (single-agent mode is gone). Its identity is **Skywalker** (product name remains Corbits Code; when asked its name, answer Skywalker): classify work, DIY tiny/single-file/one-route product edits, dispatch a **closed fleet of 16 directors** for substantial work, track the fleet, and synthesize. Product mutation tools (`write_file` / `edit_file` / `delete_file`) are mounted on the primary (CORE / `SKYWALKER_TOOLS`) — path tools are the DIY surface; spawn remains the default for substantial, multi-file, parallel, or specialist work (hard cap 4). Shell file-writes stay denied. MCP tools are not re-filtered by a product-write deny list (that list is gone). Shipped directors have no package `writePaths`; the optional field still constrains path-keyed product tools (not shell) when a profile sets it. Yolo / skip-permissions still bypasses the write-path gate when enabled. Operator slash recipes (`/implement`, `/plan`, `/refactor`, `/review`, `/pull-request-review`, `/create-issue`, `/scribe`, `/interview`, `/ast-grep`) tell Skywalker which directors to spawn for substantial work; tiny/bounded edits may run on the primary.
 
 | Lane | Directors |
 |---|---|
diff --git a/plugins/corbits-skills/skills/create-issue/SKILL.md b/plugins/corbits-skills/skills/create-issue/SKILL.md
index 7e213e106..889065ef1 100644
--- a/plugins/corbits-skills/skills/create-issue/SKILL.md
+++ b/plugins/corbits-skills/skills/create-issue/SKILL.md
@@ -21,7 +21,7 @@ Pick the tracker before drafting. Do not skip this.
    - GitLab
    - Linear (enable MCP)
    - Other
-   Then persist the choice: spawn `task(agent="implement")` with a tiny brief that appends `Preferred issue tracker: <name>` to `.corbits/MEMORY.md` only. Primary cannot write product files; shell writes are blocked. Do not ask implement to touch anything else.
+   Then persist the choice: DIY with write_file/edit_file — append `Preferred issue tracker: <name>` to `.corbits/MEMORY.md` only. Path tools are the DIY surface; shell writes stay denied. Do not touch anything else.
 4. **GitHub** → create with `gh issue create` (title + body) via `run_shell`. If `gh` is missing, tell the operator to install GitHub CLI (`gh`) and stop. Do not invent an HTTP client.
 5. **GitLab** → create with `glab issue create` (title + body) via `run_shell` similarly. If `glab` is missing, tell the operator and stop.
 6. **Linear without MCP** → stop and tell the operator to enable Linear MCP. Do not invent a Linear REST client.
diff --git a/plugins/corbits-skills/skills/dispatch/SKILL.md b/plugins/corbits-skills/skills/dispatch/SKILL.md
index 0fb9683e3..c3127f5b1 100644
--- a/plugins/corbits-skills/skills/dispatch/SKILL.md
+++ b/plugins/corbits-skills/skills/dispatch/SKILL.md
@@ -2,12 +2,12 @@
 name: dispatch
 user-invocable: false
 argument-hint: "[<name> | dispatch/<name>/ | dispatch/<name>/dispatch.yaml | <spec-file> ]"
-description: Multi-lane DAG orchestration. Skywalker recipe — use_skill("dispatch"). Spawns explore, intern, implement, plan, and critique. Never implements product code.
+description: Multi-lane DAG orchestration. Skywalker recipe — use_skill("dispatch"). Spawns explore, intern, implement, plan, and critique. DAG product tasks go through implement; Skywalker may DIY tiny edits outside the DAG.
 ---
 
 # Dispatch
 
-You are Skywalker. This skill is loadable with `use_skill("dispatch")`. Follow this recipe; do not implement product code; do not write `dispatch.yaml` or `plan.md` yourself.
+You are Skywalker. This skill is loadable with `use_skill("dispatch")`. Follow this recipe. DAG product tasks go through implement workers. Do not write `dispatch.yaml` or `plan.md` yourself (intern cannot write; implement writes manifests). Tiny / single-file / one-route product edits outside this DAG may be DIY with write_file/edit_file/delete_file.
 
 Orchestrate parallel director runs across a dependency graph. Fan out work, fan in reports, critique, verify, re-dispatch fixes, and synthesize until done.
 
@@ -39,7 +39,7 @@ If the spec is vague, incomplete, or contradictory: stop and report Blockers. Do
 | Architecture judgment before a large DAG | `task(agent="greybeard")` |
 | Independent suite / repro evidence | `task(agent="tester")` |
 
-Skywalker classifies, spawns, tracks, and synthesizes. Product mutation tools are not mounted on this session. Durable files go through implement: orchestration artifacts (`dispatch.yaml`, `plan.md`, status) and product code. Implement is used for those artifacts because it has write tools; intern does not (`INTERN_TOOLS` = run_shell, read_file, list_dir). Do not spawn a blob agent to author the manifest.
+Skywalker classifies, spawns, tracks, and synthesizes. Path tools (`write_file` / `edit_file` / `delete_file`) are mounted for DIY tiny/bounded product edits; spawn remains the default for DAG product work. Durable orchestration artifacts (`dispatch.yaml`, `plan.md`, status) still go through implement — intern does not have write tools (`INTERN_TOOLS` = run_shell, read_file, list_dir). Do not spawn a blob agent to author the manifest. Do not write those manifests on Skywalker.
 
 Prefer typed briefs: `intent`, `success_criteria`, `do_not`, `report_focus`, and `agent`.
 
diff --git a/plugins/corbits-skills/skills/implement/SKILL.md b/plugins/corbits-skills/skills/implement/SKILL.md
index 266e3a730..e9deef6ce 100644
--- a/plugins/corbits-skills/skills/implement/SKILL.md
+++ b/plugins/corbits-skills/skills/implement/SKILL.md
@@ -5,9 +5,11 @@ description: Disciplined per-commit workflow — Skywalker spawns greybeard, imp
 
 # Implement
 
-You are Skywalker. This skill is a per-commit spawn recipe. You orchestrate specialists; you do not implement.
+You are Skywalker. This skill is a per-commit spawn recipe for substantial landings.
 
-Primary never writes product files. Spawn workers. Wait for reports. Decide the next spawn from those reports.
+DIY is the exception: tiny / single-file / one-route / clear bounded product edits → use write_file/edit_file/delete_file on this session. Do not load this loop for that work.
+
+Spawn remains the default for substantial, multi-file, parallel, or specialist work (hard cap 4 workers). When this recipe runs, spawn workers. Wait for reports. Decide the next spawn from those reports.
 
 ## Prerequisites
 
@@ -24,7 +26,7 @@ Track commit-sized units with `manage_tasks`. One item per unit that will become
 
 ## Per-commit spawn loop
 
-For each unit, run these steps in order. Do not skip. Do not write, edit, or delete product files yourself.
+For each unit, run these steps in order. Do not skip. When this loop is running, do not DIY the unit — spawn implement.
 
 ### 1. Review — greybeard
 
@@ -72,8 +74,7 @@ When critique is clean (or remaining findings are acknowledged judgment calls),
 
 ## Hard rules
 
-- Skywalker MUST NOT write/edit/delete product files.
-- Do not do the coding yourself.
+- Tiny / single-file / one-route / clear bounded edits: DIY with write_file/edit_file/delete_file. This recipe is for substantial units — when running it, spawn, do not DIY the coding.
 - Spawn with `task(agent="greybeard")`, `task(agent="implement")`, `task(agent="intern")` or `task(agent="tester")`, and `task(agent="critique")`.
 - Track only with `manage_tasks`.
 - Do not shortcut the loop. Skipping greybeard “because this is simple” or skipping critique “because the build passed” defeats the recipe.
diff --git a/plugins/corbits-skills/skills/linear-issue-workflow/SKILL.md b/plugins/corbits-skills/skills/linear-issue-workflow/SKILL.md
index 6a2469cf9..a5277e9ff 100644
--- a/plugins/corbits-skills/skills/linear-issue-workflow/SKILL.md
+++ b/plugins/corbits-skills/skills/linear-issue-workflow/SKILL.md
@@ -1,13 +1,13 @@
 ---
 name: linear-issue-workflow
 user-invocable: false
-description: Skywalker implements a Linear issue by fetching it via MCP then running the /implement spawn loop. Does not write product code.
+description: Skywalker implements a Linear issue by fetching it via MCP then running the /implement spawn loop. DIY tiny/bounded issue edits; spawn implement for substantial landings.
 argument-hint: "<issue-id> [--reviewer <reviewer>]"
 ---
 
 # Linear Issue Workflow
 
-You are Skywalker. Host is Corbits Code. This skill is a spawn recipe. You do not write product code. You orchestrate: Linear MCP on the primary, then the `/implement` spawn loop.
+You are Skywalker. Host is Corbits Code. This skill is a spawn recipe for substantial issue work. Tiny / single-file / one-route / clear bounded product edits: DIY with write_file/edit_file/delete_file. Substantial landings: Linear MCP on the primary, then the `/implement` spawn loop.
 
 If Linear MCP (`mcp__linear__*`) is missing, stop and tell the operator. Do not invent Claude-only tools.
 
@@ -154,7 +154,7 @@ If the worktree directory was already deleted: `git worktree prune`.
 
 ## Hard rules
 
-- Skywalker MUST NOT write/edit/delete product files.
+- Tiny / single-file / one-route / clear bounded edits: DIY with write_file/edit_file/delete_file. Substantial issue landings: spawn implement (this recipe).
 - Spawn with `task(agent="greybeard")`, `task(agent="implement")`, `task(agent="intern")` or `task(agent="tester")`, and `task(agent="critique")`.
 - Clarifying questions use `ask_operator`.
 - Shell is `run_shell`, not a Bash tool.
diff --git a/plugins/corbits-skills/skills/opsh/SKILL.md b/plugins/corbits-skills/skills/opsh/SKILL.md
index 57943bde6..8ef14edc6 100644
--- a/plugins/corbits-skills/skills/opsh/SKILL.md
+++ b/plugins/corbits-skills/skills/opsh/SKILL.md
@@ -1,14 +1,14 @@
 ---
 name: opsh
 user-invocable: false
-description: Write scripts using opsh and its built-in libraries. Skywalker copies these rules into an implement brief; does not write the script. Load when writing, reviewing, or debugging opsh scripts.
+description: Write scripts using opsh and its built-in libraries. Tiny scripts: DIY with these rules. Substantial script work: copy the rules into an implement brief. Load when writing, reviewing, or debugging opsh scripts.
 ---
 
 # opsh Scripting
 
-You are Skywalker. Host is Corbits Code. This is a convention skill. You do not write the script.
+You are Skywalker. Host is Corbits Code. This is a convention skill. Tiny / single-file scripts: DIY with write_file/edit_file using these rules. Substantial script work: spawn implement with this skill's rules copied into the brief (workers do not mount `use_skill`).
 
-If the operator wants a script written, spawn `task(agent="implement")` with this skill's rules copied into the brief (workers do not mount `use_skill`). If the operator wants a review, spawn `task(agent="critique")` (or `task(agent="neckbeard")` for hygiene-only) with the same rules copied in.
+If the operator wants a substantial script written, spawn `task(agent="implement")` with this skill's rules copied into the brief. If the operator wants a review, spawn `task(agent="critique")` (or `task(agent="neckbeard")` for hygiene-only) with the same rules copied in.
 
 Shell for agent commands is `run_shell` (there is no Bash tool). Bash-the-language in the examples below stays — opsh scripts are bash.
 
diff --git a/plugins/corbits-skills/skills/pull-request-review/SKILL.md b/plugins/corbits-skills/skills/pull-request-review/SKILL.md
index ea7cc6eaa..eb320ab0b 100644
--- a/plugins/corbits-skills/skills/pull-request-review/SKILL.md
+++ b/plugins/corbits-skills/skills/pull-request-review/SKILL.md
@@ -5,7 +5,7 @@ description: Review a pull request by branch name or URL. Intern checks out a wo
 
 # Pull Request Review
 
-You are Skywalker. Host is Corbits Code. This skill is a spawn recipe. Do not implement fixes. Do not write product patches. Do not impersonate GitHub-Claude (or any other vendor) review comments.
+You are Skywalker. Host is Corbits Code. This skill is a spawn recipe. Do not implement fixes as part of the review. Do not impersonate GitHub-Claude (or any other vendor) review comments.
 
 ## Input
 
@@ -101,7 +101,7 @@ Or leave it and tell the operator it remains for further investigation.
 
 ## Hard rules
 
-- Skywalker MUST NOT write/edit/delete product files.
+- This recipe reviews; it does not land product patches. If the operator then asks for a tiny/bounded fix, DIY with write_file/edit_file/delete_file; spawn implement for substantial fixes.
 - Skywalker MUST NOT run the worktree git; intern does, via `run_shell`.
-- Do not implement fixes.
+- Do not implement fixes as part of the review.
 - Do not impersonate GitHub-Claude review comments.
diff --git a/plugins/corbits-skills/skills/refactor/SKILL.md b/plugins/corbits-skills/skills/refactor/SKILL.md
index d4dc55719..393840733 100644
--- a/plugins/corbits-skills/skills/refactor/SKILL.md
+++ b/plugins/corbits-skills/skills/refactor/SKILL.md
@@ -1,12 +1,12 @@
 ---
 name: refactor
 argument-hint: <directory>
-description: Skywalker maps a directory then plans improvements. Explore, then plan. No product writes.
+description: Skywalker maps a directory then plans improvements. Explore, then plan. Does not ship product code.
 ---
 
 # Refactor
 
-You are Skywalker. This skill is a spawn recipe. You do not write a design document. You do not write product files. `$ARGUMENTS` is the directory to analyze.
+You are Skywalker. This skill is a spawn recipe. You do not write a design document. `$ARGUMENTS` is the directory to analyze. This recipe maps and plans; it does not ship. Tiny / single-file / one-route product edits outside this recipe may be DIY with write_file/edit_file/delete_file.
 
 ## Recipe
 
@@ -35,7 +35,7 @@ Do not write the plan to disk yourself. Plan's report is the artifact. A later `
 
 ## Hard rules
 
-- Skywalker MUST NOT write/edit/delete product files, including design documents.
+- Do not write the plan to disk or author design documents on this session — plan's report is the artifact. A later `/implement` or `use_skill("dispatch")` ships substantial work; DIY remains for tiny/bounded edits outside this recipe.
 - Do not skip explore "because you already know the directory."
 - Do not skip `ask_operator` when the operator has not chosen among alternatives.
 - Spawn with `task(agent="explore")` then `task(agent="plan")`.
diff --git a/plugins/corbits-skills/skills/scribe/SKILL.md b/plugins/corbits-skills/skills/scribe/SKILL.md
index 46668690a..53df56d22 100644
--- a/plugins/corbits-skills/skills/scribe/SKILL.md
+++ b/plugins/corbits-skills/skills/scribe/SKILL.md
@@ -5,10 +5,10 @@ description: Skywalker spawn recipe — shakespeare writes PRODUCT.md, ARCHITECT
 
 # Scribe
 
-You are Skywalker. This skill is a spawn recipe. You do not write the docs.
+You are Skywalker. This skill is a spawn recipe. Spawn `task(agent="shakespeare")` for PRODUCT.md, ARCHITECTURE.md, and IMPLEMENTATION.md unless the ask is a one-line fix (DIY with write_file/edit_file).
 
 Spawn `task(agent="shakespeare")` with the operator args / pasted material as the brief. Shakespeare owns PRODUCT.md, ARCHITECTURE.md, and IMPLEMENTATION.md.
 
 Use `ask_operator` if the doc target (P vs A vs I) is ambiguous.
 
-Do not edit those docs yourself. DESIGN.md is brand-reviewer, not this skill.
+Do not edit those docs yourself except a one-line fix. DESIGN.md is brand-reviewer, not this skill.
diff --git a/src/agent/directors/registry.test.ts b/src/agent/directors/registry.test.ts
index 0d6825968..47797cdb9 100644
--- a/src/agent/directors/registry.test.ts
+++ b/src/agent/directors/registry.test.ts
@@ -139,7 +139,6 @@ describe("director registry", () => {
       "testsmith",
       "tester",
       "gaasbot",
-      "skywalker",
     ] as const) {
       const allow = DIRECTOR_REGISTRY[id].tools?.allow ?? [];
       expect(allow).not.toContain("write_file");
@@ -169,13 +168,16 @@ describe("director registry", () => {
     }
   });
 
-  test("skywalker primary stance: never implement, no product write tools", () => {
+  test("skywalker primary stance: DIY tiny writes, spawn for substantial work", () => {
     const s = DIRECTOR_REGISTRY.skywalker;
-    expect(s.systemPrompt).toContain("NEVER implement");
+    expect(s.systemPrompt).toContain("write_file/edit_file/delete_file");
+    expect(s.systemPrompt).toContain("DIY tiny/single-file/one-route");
     expect(s.systemPrompt).toContain("You are Skywalker");
     expect(s.systemPrompt).toMatch(/No catch-all worker/i);
     expect(s.tools?.allow).toContain("task");
-    expect(s.tools?.allow).not.toContain("write_file");
+    expect(s.tools?.allow).toContain("write_file");
+    expect(s.tools?.allow).toContain("edit_file");
+    expect(s.tools?.allow).toContain("delete_file");
     expect(s.spawn.allowlist).toHaveLength(15);
   });
 
diff --git a/src/agent/directors/skywalker/package.test.ts b/src/agent/directors/skywalker/package.test.ts
index 4545ed319..f38a973d5 100644
--- a/src/agent/directors/skywalker/package.test.ts
+++ b/src/agent/directors/skywalker/package.test.ts
@@ -12,7 +12,8 @@ describe("skywalkerPackage", () => {
     expect(skywalkerPackage.systemPrompt).toContain("You are Skywalker");
     expect(skywalkerPackage.systemPrompt).toContain("When asked your name, answer: Skywalker");
     expect(skywalkerPackage.systemPrompt).toContain("PRIMARY INTENT");
-    expect(skywalkerPackage.systemPrompt).toContain("NEVER implement");
+    expect(skywalkerPackage.systemPrompt).toContain("write_file/edit_file/delete_file");
+    expect(skywalkerPackage.systemPrompt).toContain("DIY tiny/single-file/one-route");
   });
 
   test("createSkywalkerSystemPrompt returns package systemPrompt", () => {
@@ -41,13 +42,13 @@ describe("skywalkerPackage", () => {
     ]);
   });
 
-  test("tools.allow mounts orchestrator surface without product writes", () => {
+  test("tools.allow mounts orchestrator surface plus product writes for DIY", () => {
     const allow = skywalkerPackage.tools?.allow ?? [];
     expect(allow).toContain("task");
     expect(allow).toContain("search_agents");
-    expect(allow).not.toContain("write_file");
-    expect(allow).not.toContain("edit_file");
-    expect(allow).not.toContain("delete_file");
+    expect(allow).toContain("write_file");
+    expect(allow).toContain("edit_file");
+    expect(allow).toContain("delete_file");
   });
 
   test("report required sections", () => {
@@ -74,9 +75,9 @@ describe("skywalkerPackage", () => {
 
   test("primaryIntent and outOfLane", () => {
     expect(skywalkerPackage.primaryIntent).toBe(
-      "Orchestrate only — triage and dispatch; do not implement product code",
+      "Orchestrate; DIY tiny/bounded product edits; spawn for substantial work",
     );
-    expect(skywalkerPackage.outOfLane).toContain("product edits");
+    expect(skywalkerPackage.outOfLane).toContain("substantial multi-file product work without spawning");
     expect(skywalkerPackage.outOfLane).toContain("catch-all worker");
     expect(skywalkerPackage.outOfLane).toContain(
       "searching the repo yourself after a worker stops without finishing",
@@ -118,9 +119,9 @@ describe("skywalkerPackage", () => {
 
   test("systemPrompt simple path skips explore+critique for tiny work", () => {
     const p = skywalkerPackage.systemPrompt;
-    expect(p).toContain("one implement worker");
-    expect(p).toContain("skip explore and skip critique");
-    expect(p).toContain("tests green");
+    expect(p).toContain("DIY on the parent");
+    expect(p).toContain("skip spawn, skip explore, skip critique");
+    expect(p).toContain("write_file/edit_file");
     expect(p).toContain("Do not always explore→implement→critique");
   });
 
diff --git a/src/agent/directors/skywalker/package.ts b/src/agent/directors/skywalker/package.ts
index b6fd451cb..911c23248 100644
--- a/src/agent/directors/skywalker/package.ts
+++ b/src/agent/directors/skywalker/package.ts
@@ -1,25 +1,25 @@
 // Skywalker: primary orchestration director. Chains specialists into a workflow.
 
 import type { DirectorPackage } from "../types.js";
-import { ORCHESTRATOR_TOOLS } from "../tool-sets.js";
+import { SKYWALKER_TOOLS } from "../tool-sets.js";
 
 const SKYWALKER_SYSTEM_PROMPT = `You are Skywalker — the primary orchestrator for Corbits Code.
 
 When asked your name, answer: Skywalker.
 Agent id: skywalker (primary session; not a spawned worker). Start specialists with task(agent="…").
 
-PRIMARY INTENT: run the workflow. Classify every request. Delegate. Chain specialists into a sequence of actions. Track who is running. Synthesize for the operator. Do not become the implementer, reviewer, or explorer by default.
+PRIMARY INTENT: run the workflow. Classify every request. DIY tiny/single-file/one-route product edits. Delegate substantial work. Chain specialists into a sequence of actions. Track who is running. Synthesize for the operator. Do not become the reviewer or explorer by default.
 
-You do not do the specialists' jobs. You start them, wait for their reports, and decide the next action from those reports.
+You do not do the specialists' jobs by default. For tiny bounded product edits, use write_file/edit_file/delete_file yourself. For substantial work you start specialists, wait for their reports, and decide the next action from those reports.
 
 # Parent tools
 
-Do not run long-blocking jobs on the parent (evals, full test suites, long installs). Dispatch intern (mechanical shell) or tester (suite / repro).
+Do not run long-blocking jobs on the parent (evals, full test suites, long installs, long-running implementation). Dispatch intern (mechanical shell), tester (suite / repro), or implement (substantial code). Path tools (write_file/edit_file/delete_file) are the DIY surface; shell file-writes stay denied.
 
 task() still awaits the worker's full report. Enter mid-run delivers at the next parent tool.boundary — a long parent run_shell or awaiting task() holds those steers. Dispatching a worker does not make Enter a new turn until that parent tool returns.
 
 Example chains:
-- tiny fix: implement
+- tiny fix: DIY write_file/edit_file (do not spawn)
 - feature: explore → implement → critique
 - "why / how / is this stalled": answer yourself; at most one explore if a single unknown blocks you
 
@@ -51,14 +51,14 @@ Parallelize independent lanes. manage_tasks for your checklist. ask_operator whe
 
 When the operator (or brief) gives an http(s) URL to read:
 - Call **web_fetch** yourself on that URL — it is already mounted. Do not tool_search for it, do not shell curl/wget/fetch, do not thrash run_shell to download pages.
-- After you have the content, spawn implement only if a file must be written (e.g. write the extracted fact). For pure Q&A from a URL, answer directly.
+- After you have the content, DIY a tiny file write yourself; spawn implement only if the write is substantial. For pure Q&A from a URL, answer directly.
 - Cap retries: if web_fetch fails once with a clear error, report the blocker — do not burn a long tool-only streak on shell workarounds.
 
 # Effort scaling (IMPLEMENTATION / ORCHESTRATION)
 
 Scale fan-out to the ask — do not spawn 10+ workers for a simple request:
 - Simple (answer, one-path lookup, tiny fix): 0–1 worker, few tools; often answer without fleet
-- Tiny single-file / one-route asks: **one implement worker**; skip explore and skip critique when implement reports tests green and criteria mapped pass. Do not always explore→implement→critique for simple work — that burns wall clock.
+- Tiny single-file / one-route asks: **DIY on the parent** with write_file/edit_file; skip spawn, skip explore, skip critique. Do not always explore→implement→critique for simple work — that burns wall clock.
 - Medium: 2–4 workers with distinct path/package ownership
 - Complex: more workers only with named lanes and clear non-overlap
 Hard cap: **at most 4 workers at once** unless the operator explicitly asks for a wider fan-out. Prefer synthesizing early returns over launching a second wave.
@@ -94,7 +94,13 @@ Before responding, classify:
 2. ORCHESTRATION — plan, coordinate, or manage work in progress
 3. COMMUNICATION — answer a question, provide information, or clarify
 
-## If IMPLEMENTATION → dispatch; NEVER implement directly
+## If IMPLEMENTATION → DIY when tiny; spawn when substantial
+
+Tiny / single-file / one-route / clear bounded edit: write_file/edit_file/delete_file on this session. Do not spawn.
+
+Substantial / multi-file / parallel lanes / long-running: spawn implement (hard cap 4). Keep long-blocking jobs off the parent so Enter can steer.
+
+Docs/design (PRODUCT.md, ARCHITECTURE.md, docs/design/*, brand) still spawn shakespeare / bruckheimer / brand-reviewer unless the ask is a one-line fix.
 
 1. If requirements are fuzzy or complex, load interview and discover first.
 2. Use explore workers for scope when needed.
@@ -103,8 +109,6 @@ Before responding, classify:
 5. Present the plan when the change is large or ambiguous; then execute via task spawns.
 6. Track progress with manage_tasks; synthesize results for the operator.
 
-Forbidden: product Write/Edit, "just quickly" shipping code yourself, implementing to save time.
-
 ## If ORCHESTRATION → coordinate
 
 Track with manage_tasks. Parallelize independent lanes. Escalate blockers with ask_operator. This is your core role.
@@ -117,11 +121,10 @@ Do not reclassify COMMUNICATION as ORCHESTRATION just to justify parallel task s
 
 # Non-negotiables
 
-- NEVER implement product features yourself (zero product Write/Edit).
+- Tiny/single-file/one-route product edits: write_file/edit_file/delete_file yourself. Substantial, multi-file, parallel, or specialist work: spawn (implement for code; shakespeare / bruckheimer / brand-reviewer for docs/design unless a one-line fix).
 - Interview when requirements are fuzzy; consult greybeard on architecture/approach.
 - Use plan or dispatch skill for multi-lane eng plans; clarify before large dispatch.
-- Product file mutation tools (write_file, edit_file, delete_file) are not mounted on this session. Track work with manage_tasks; spawn implement (code), shakespeare (P/A/I docs), or brand-reviewer (DESIGN.md) for durable artifacts.
-- Before any product file op, self-check: "Am I implementing instead of orchestrating?" If yes, STOP and spawn implement.
+- Path tools are the DIY surface; shell file-writes stay denied. Track fleet work with manage_tasks.
 - Optional skills when needed on the primary session: dispatch, style, philosophy, interview (use_skill is primary-mounted).
 
 
@@ -154,9 +157,10 @@ export function createSkywalkerSystemPrompt(): string {
 
 export const skywalkerPackage: DirectorPackage = {
   id: "skywalker",
-  primaryIntent: "Orchestrate only — triage and dispatch; do not implement product code",
+  primaryIntent: "Orchestrate; DIY tiny/bounded product edits; spawn for substantial work",
   outOfLane: [
-    "product edits",
+    "substantial multi-file product work without spawning",
+    "docs/design authorship (PRODUCT.md, ARCHITECTURE.md, docs/design/*, brand) except one-line fixes",
     "deep multi-path repo walks when a single explore worker or mounted tools suffice",
     "being the reviewer/implementer by default",
     "catch-all worker",
@@ -166,7 +170,7 @@ export const skywalkerPackage: DirectorPackage = {
   description: "Primary orchestration director — chains specialists into a workflow",
   systemPrompt: SKYWALKER_SYSTEM_PROMPT,
   optionalSkills: ["dispatch", "style", "philosophy", "interview"],
-  tools: { allow: ORCHESTRATOR_TOOLS },
+  tools: { allow: SKYWALKER_TOOLS },
   spawn: {
     maySpawn: true,
     allowlist: [
diff --git a/src/agent/directors/tool-sets.test.ts b/src/agent/directors/tool-sets.test.ts
index 92b268ae6..c5baf5b6c 100644
--- a/src/agent/directors/tool-sets.test.ts
+++ b/src/agent/directors/tool-sets.test.ts
@@ -2,7 +2,9 @@ import { describe, expect, test } from "bun:test";
 import {
   DOCS_TOOLS,
   IMPLEMENT_TOOLS,
+  ORCHESTRATOR_TOOLS,
   READ_TOOLS,
+  SKYWALKER_TOOLS,
 } from "./tool-sets.js";
 
 describe("DOCS_TOOLS", () => {
@@ -34,3 +36,14 @@ describe("DOCS_TOOLS", () => {
     }
   });
 });
+
+describe("SKYWALKER_TOOLS / ORCHESTRATOR_TOOLS", () => {
+  test("Skywalker mounts product writes; greybeard orchestrator surface does not", () => {
+    for (const name of ["write_file", "edit_file", "delete_file"] as const) {
+      expect(SKYWALKER_TOOLS as readonly string[]).toContain(name);
+      expect(ORCHESTRATOR_TOOLS as readonly string[]).not.toContain(name);
+    }
+    expect(SKYWALKER_TOOLS).toContain("task");
+    expect(ORCHESTRATOR_TOOLS).toContain("task");
+  });
+});
diff --git a/src/agent/directors/tool-sets.ts b/src/agent/directors/tool-sets.ts
index e750cc33d..1c73604da 100644
--- a/src/agent/directors/tool-sets.ts
+++ b/src/agent/directors/tool-sets.ts
@@ -51,3 +51,11 @@ export const ORCHESTRATOR_TOOLS = [
   "search_agents",
   "task",
 ] as const;
+
+/** Skywalker primary: orchestrator surface plus product writes for DIY tiny work. */
+export const SKYWALKER_TOOLS = [
+  ...ORCHESTRATOR_TOOLS,
+  "write_file",
+  "edit_file",
+  "delete_file",
+] as const;
diff --git a/src/agent/prompt-contract.ts b/src/agent/prompt-contract.ts
index db259c99c..ca9d4f35b 100644
--- a/src/agent/prompt-contract.ts
+++ b/src/agent/prompt-contract.ts
@@ -9,7 +9,7 @@ export const CHAT_PROMPT_QUALITY_MARKERS = [
   "Tool choice:",
   "Ask vs proceed:",
   "Scope and conventions:",
-  "Product write tools are not mounted on Skywalker",
+  "DIY tiny/single-file/one-route",
   "ask_operator only when permission blocks you",
   "Touch only code required for the task",
   "load the style and philosophy skills",
diff --git a/src/agent/prompts.test.ts b/src/agent/prompts.test.ts
index d72f08db3..73207a3d1 100644
--- a/src/agent/prompts.test.ts
+++ b/src/agent/prompts.test.ts
@@ -13,10 +13,6 @@ import { CORE_TOOL_NAMES, CATALOG_TOOL_NAMES } from "./tool-search.js";
 const REGISTERED_TOOL_NAMES = new Set([
   ...CORE_TOOL_NAMES,
   ...CATALOG_TOOL_NAMES,
-  // Product mutation tools mount on workers, not primary CORE/CATALOG ads.
-  "write_file",
-  "edit_file",
-  "delete_file",
 ]);
 
 const REFERENCED_TOOL_NAMES = [
diff --git a/src/agent/prompts.ts b/src/agent/prompts.ts
index 4b17b3d47..d1a4b1020 100644
--- a/src/agent/prompts.ts
+++ b/src/agent/prompts.ts
@@ -64,8 +64,8 @@ export function buildHarnessFacts(
           "- Change files with write_file/edit_file and remove files with delete_file; shell file-writes and deletions are blocked.",
         ]
       : [
-          "- Product file mutations (write_file, edit_file, delete_file) are not mounted on the primary Skywalker session — spawn implement (code), shakespeare (P/A/I), brand-reviewer (DESIGN.md), or bruckheimer (PRODUCT.md) for durable edits.",
-          "- Shell file-writes and deletions are blocked; never use echo/heredoc/sed/rm as a substitute for product tools.",
+          "- Change files with write_file/edit_file and remove files with delete_file for tiny/single-file/one-route bounded edits. Spawn implement for substantial/multi-file/parallel/specialist work (hard cap 4 workers). Docs/design still spawn shakespeare/bruckheimer/brand-reviewer except one-line fixes.",
+          "- Shell file-writes and deletions are blocked; never use echo/heredoc/sed/rm as a substitute for product tools. Path tools are the DIY surface.",
         ]),
     "- Use the provided tools for file reads/searches instead of shelling out as a substitute.",
     "- read_file accepts a filesystem path or a tool-output:///{callId} URI from a prior tool result when the harness exposes one; prefer the URI over re-reading huge blobs.",
@@ -108,12 +108,12 @@ export function buildGuidelines(opts: { subAgent?: boolean; sessionMode?: Sessio
     ...(subAgent
       ? []
       : [
-          "- Prefer task(intent=…) / task(agent=…) for product implementation, exploration, review, and docs — that is the primary loop.",
+          "- Prefer task(intent=…) / task(agent=…) for substantial product implementation, exploration, review, and docs — spawn remains default for substantial work, not a tool ban.",
         ]),
     "- read_file for file contents; grep or search_files to locate code; lsp for symbols, types, references, or call flow before opening large files.",
     subAgent
       ? "- edit_file for targeted changes; write_file for new files or full rewrites; delete_file to remove files — never echo, heredoc, sed, or rm in the shell for those jobs."
-      : "- Product write tools are not mounted on Skywalker. Spawn implement (or a docs director) for durable file changes; never shell-write (echo/heredoc/sed/rm).",
+      : "- edit_file for targeted DIY tiny/single-file/one-route edits; write_file for new files or full rewrites; delete_file to remove files — never shell-write (echo/heredoc/sed/rm). Spawn implement (or a docs director) for substantial/multi-file/parallel/specialist work.",
     "- run_shell for builds, tests, git, and one-off commands — not for shell find, head-position rg, or recursive grep -r (OOM risk), cat, or messaging the user.",
     ...(subAgent
       ? []
@@ -162,7 +162,7 @@ export function buildPromptDisciplineBlock(opts: { subAgent?: boolean } = {}): s
   const subAgent = opts.subAgent ?? false;
   const toolsOverShell = subAgent
     ? "- Never use run_shell to read, edit, or write files — use read_file, edit_file, write_file; cat/head/tail, sed/awk/perl -i, and heredoc/echo redirection are prohibited substitutes."
-    : "- Never use run_shell to read, edit, or write files — use read_file for reads; durable product edits go through implement/docs directors (write tools are not mounted on Skywalker); cat/head/tail, sed/awk/perl -i, and heredoc/echo redirection are prohibited substitutes.";
+    : "- Never use run_shell to read, edit, or write files — use read_file, edit_file, write_file for tiny/bounded DIY; spawn implement/docs directors for substantial work; cat/head/tail, sed/awk/perl -i, and heredoc/echo redirection are prohibited substitutes.";
   return [
     "Prompt discipline:",
     "",
diff --git a/src/agent/tool-search.test.ts b/src/agent/tool-search.test.ts
index 53d492dc3..b516eb50c 100644
--- a/src/agent/tool-search.test.ts
+++ b/src/agent/tool-search.test.ts
@@ -9,7 +9,6 @@ import {
   coreToolNamesForSessionMode,
   CORE_TOOL_NAMES,
   CATALOG_TOOL_NAMES,
-  PRIMARY_DENIED_PRODUCT_TOOLS,
   type ToolAvailability,
 } from "./tool-search.js";
 
@@ -83,12 +82,11 @@ describe("createToolIndex", () => {
     expect(coreToolNamesForSessionMode("orchestrator", FULL_AVAILABILITY)).not.toContain("present");
   });
 
-  test("primary CORE and CATALOG omit product mutation tools", () => {
+  test("primary CORE includes product mutation tools; CATALOG does not duplicate them", () => {
     for (const name of ["write_file", "edit_file", "delete_file"] as const) {
-      expect(CORE_TOOL_NAMES).not.toContain(name);
+      expect(CORE_TOOL_NAMES).toContain(name);
       expect(CATALOG_TOOL_NAMES).not.toContain(name);
     }
-    expect(PRIMARY_DENIED_PRODUCT_TOOLS).toEqual(["write_file", "edit_file", "delete_file"]);
   });
 
   test("catalog advertises web_fetch and web_search so URL work needs no tool_search", () => {
@@ -193,8 +191,8 @@ describe("advertisedTools", () => {
     const names = advertisedTools(registry).map((d) => d.name);
     expect(names).toContain("read_file");
     expect(names).toContain("grep");
-    // write_file is not in primary CATALOG — product mutations are leaf-only.
-    expect(names).not.toContain("write_file");
+    // write_file is in CORE so the primary can DIY tiny/bounded edits.
+    expect(names).toContain("write_file");
     expect(names).not.toContain("mcp__linear__create_issue");
   });
 
diff --git a/src/agent/tool-search.ts b/src/agent/tool-search.ts
index b25486811..5229bcb67 100644
--- a/src/agent/tool-search.ts
+++ b/src/agent/tool-search.ts
@@ -16,11 +16,15 @@ import { sessionModeEnablesSubAgents } from "../config/session-mode.js";
 // dispatchable — the model finds it via tool_search when a session actually
 // needs it.
 //
-// Product mutation tools (write_file / edit_file / delete_file) are intentionally
-// absent from the primary Skywalker core/catalog sets — they mount only on leaf
-// directors that need them (implement, shakespeare, …). See PRIMARY_DENIED_PRODUCT_TOOLS.
+// Product mutation tools (write_file / edit_file / delete_file) sit in CORE so
+// the primary Skywalker session can DIY tiny/bounded edits without a
+// tool_search round-trip. Substantial work still spawns implement / docs
+// directors — that is a prompt judgment call, not a toolset strip.
 export const CORE_TOOL_NAMES: readonly string[] = [
   "read_file",
+  "write_file",
+  "edit_file",
+  "delete_file",
   "lsp",
   "run_shell",
   "ask_operator",
@@ -35,13 +39,6 @@ export const CORE_TOOL_NAMES: readonly string[] = [
   "task",
 ];
 
-/** Product mutation tools denied on the primary Skywalker session (structural). */
-export const PRIMARY_DENIED_PRODUCT_TOOLS: readonly string[] = [
-  "write_file",
-  "edit_file",
-  "delete_file",
-];
-
 const ORCHESTRATOR_ONLY_TOOL_NAMES: readonly string[] = ["search_agents", "task"];
 
 // Session-start facts that gate a core tool's advertisement. Each must be
@@ -77,8 +74,8 @@ export function advertisedToolNamesForSessionMode(
 // Built-in file/search/web tools advertised alongside the core set. They carry full
 // schemas on the wire so the model can call them directly; MCP tools are not
 // listed at all — they are discovered blind via tool_search.
-// write_file is intentionally omitted: primary Skywalker does not mutate product
-// files; implement/docs leaves mount write tools via their own toolsets.
+// write_file / edit_file / delete_file live in CORE (not here) so they are
+// advertised without a tool_search round-trip.
 // web_fetch / web_search are catalog (not deferred): URL reads and search are
 // first-class primary work; requiring tool_search before web_fetch caused
 // thrash on web-bait and contradicted the skywalker "already mounted" rule.
diff --git a/src/agent/tools.ts b/src/agent/tools.ts
index aa901b71c..4661e05c8 100644
--- a/src/agent/tools.ts
+++ b/src/agent/tools.ts
@@ -32,7 +32,7 @@ import {
 import type { ToolWatchdogConfig } from "../tui/tool-execution-watchdog.js";
 import type { SessionMode } from "../config/session-mode.js";
 import { sessionModeEnablesSubAgents } from "../config/session-mode.js";
-import { advertisedToolNamesForSessionMode, PRIMARY_DENIED_PRODUCT_TOOLS, type ToolAvailability } from "./tool-search.js";
+import { advertisedToolNamesForSessionMode, type ToolAvailability } from "./tool-search.js";
 import type { ProviderCatalogEntry } from "../config/index.js";
 import type { AgentProfile } from "./profiles.js";
 import {
@@ -341,13 +341,7 @@ export async function createAgentToolset(args: AgentToolsetArgs): Promise<AgentT
     }),
   );
 
-  // Primary Skywalker never mounts product mutation tools — never-implement is
-  // structural (toolset), not prompt-only. Leaves that need write/edit/delete
-  // mount them via createTaskTool / runSubAgent's own tool assembly.
-  const primaryDenied = new Set(PRIMARY_DENIED_PRODUCT_TOOLS);
-  const primaryTools = baseTools.filter((tool) => !primaryDenied.has(tool.definition.name));
-
-  const dynamicRunner = createDynamicToolRunner(primaryTools, toolWatchdog);
+  const dynamicRunner = createDynamicToolRunner(baseTools, toolWatchdog);
   runnerRef = dynamicRunner;
   const connectedClients: MCPClient[] = [];
 
diff --git a/src/prompts.test.ts b/src/prompts.test.ts
index 4864e0a8b..a58057349 100644
--- a/src/prompts.test.ts
+++ b/src/prompts.test.ts
@@ -47,8 +47,10 @@ test("agent identity is Skywalker orchestrator", () => {
 
 test("harness facts state only the non-derivable tool and safety rules", () => {
   const facts = buildHarnessFacts();
-  expect(facts).toContain("write_file, edit_file, delete_file");
-  expect(facts).toContain("not mounted on the primary Skywalker session");
+  expect(facts).toContain("write_file/edit_file");
+  expect(facts).toContain("tiny/single-file/one-route");
+  expect(facts).toContain("Spawn implement");
+  expect(facts).not.toContain("not mounted on the primary Skywalker session");
   expect(facts).toContain("blocked");
   expect(facts).toContain("15s timeout");
   expect(facts).toContain("find, rg, and grep -r");
@@ -92,6 +94,9 @@ test("guidelines cover response style, tool choice, ask vs proceed, and scope",
   expect(guidelines).toContain("grep or search_files");
   expect(guidelines).toContain("ask_operator only when permission blocks you");
   expect(guidelines).toContain("load the style and philosophy skills");
+  expect(guidelines).toContain("DIY tiny/single-file/one-route");
+  expect(guidelines).toContain("never shell-write (echo/heredoc/sed/rm)");
+  expect(guidelines).not.toContain("not mounted on Skywalker");
 });
 
 test("orchestrator guidelines teach the typed task spawn contract", () => {
diff --git a/tests/unit/tui/agent-tools.test.ts b/tests/unit/tui/agent-tools.test.ts
index 59d576a21..a8c94bde2 100644
--- a/tests/unit/tui/agent-tools.test.ts
+++ b/tests/unit/tui/agent-tools.test.ts
@@ -8,6 +8,8 @@ const mockPosixTools = {
   definitions: [
     { name: "read_file", description: "Read a file", inputSchema: { type: "object", properties: {}, required: [] } },
     { name: "write_file", description: "Write a file", inputSchema: { type: "object", properties: {}, required: [] } },
+    { name: "edit_file", description: "Edit a file", inputSchema: { type: "object", properties: {}, required: [] } },
+    { name: "delete_file", description: "Delete a file", inputSchema: { type: "object", properties: {}, required: [] } },
   ] as ToolDefinition[],
   run: mock(async (_call: ToolCall, _signal: AbortSignal) => ({
     callId: "test",
@@ -191,10 +193,10 @@ test("dynamicRunner contains posix tool names plus ask_operator", async () => {
   const names = toolset.dynamicRunner.currentDefinitions().map((d) => d.name);
   expect(names).toContain("read_file");
   expect(names).toContain("ask_operator");
-  // Primary Skywalker never mounts product mutation tools.
-  expect(names).not.toContain("write_file");
-  expect(names).not.toContain("edit_file");
-  expect(names).not.toContain("delete_file");
+  // Primary Skywalker mounts product mutation tools for DIY tiny/bounded edits.
+  expect(names).toContain("write_file");
+  expect(names).toContain("edit_file");
+  expect(names).toContain("delete_file");
 });
 
 test("onOperatorGate callback is invoked when the operator tool handler is called", async () => {