Director prompt hygiene: fix impossible tool refs, dedupe report contract, drop dead no-ship branch, structured evidence gate

- Removed hand-written "Report: Summary, Findings, Blockers, Paths" duplicates
  from worker system prompts (build, bruckheimer, explore, gaasbot, plan,
  neckbeard, greybeard, intern, shakespeare, tester, testsmith, critique,
  emil) — the shared sub-agent report contract and each package's
  report.requiredSections already state it.
- Removed "Do not spawn agents"/"Never spawn" duplicates from prompts whose
  packages already declare spawn.maySpawn: false (build, neckbeard,
  brand-reviewer, draper) — spawn is enforced structurally by not mounting
  the task tool.
- Removed impossible tool references: tester/testsmith telling the model not
  to use write_file/edit_file or write notes under tmp/ when those tools are
  never mounted (READ_TOOLS); critique's "if shell is allowed" hedge when
  run_shell is always in its tool set; emil's and draper's write-tool denial
  explanations; gaasbot's write-tool disclaimer; plan's ask_operator mention
  (never mounted on workers).
- Removed the dead no-ship branch: evaluateSubAgentStop never returned
  "no-ship" (only evaluateThrashStop and the never-edited/never-acted paths
  fire), so the nudge director's stop === "no-ship" branch was unreachable.
  Dropped it from SubAgentStopReason and the nudge director's switch.
  ForcedStopReason (a separate type used by forcedStopReport/brief-dispatch
  salvage classification) is untouched.
- Replaced persona-string coupling: shouldRequireEvidence keyed off
  systemPromptRole.includes("CritiqueDirector"); now keys off a structured
  directorId threaded from task-tool's already-resolved director id.
- Added a registry test that cross-checks every director's prompt text
  against its mounted tool set for the known tool names, so a future prompt
  can't reference a tool it cannot call.

Author: TheGreatAxios

src/agent/directors/brand-reviewer/package.ts

@@ -65,5 +65,5 @@ Missing brand sources, ambiguous scope, product-code asks.
 ## Paths
 DESIGN.md path and UI files reviewed.
 
-Never spawn. Never commit. Stay on the DESIGN.md lane.`,
+Never commit. Stay on the DESIGN.md lane.`,
 };

src/agent/directors/bruckheimer/package.ts

@@ -30,5 +30,5 @@ Read the product as a person using it: can a new user get through the first nine
 
 OUT OF LANE: implementing features, architecture sign-off, code review severity theater, fleet orchestration. Route those via Blockers to build, greybeard, critique, or skywalker.
 
-Report: Summary, Findings (product shape + discovery), Blockers, Paths.`,
+Findings: product shape and discovery, not implementation notes.`,
 };

src/agent/directors/build/package.ts

@@ -25,7 +25,6 @@ You are not a reviewer, not an orchestrator, not a doc-only planner.
 
 Before substantial repo work: follow style and philosophy conventions (baked; use_skill is not mounted on workers).
 Follow AGENTS.md and /docs. Touch only what the brief requires.
-Do not spawn sub-agents.
 
 DONE GATE: Stop when every success_criteria item from the brief is met OR explicitly blocked under Blockers. Do not invent architecture or expand the brief after criteria are satisfied.
 
@@ -35,7 +34,5 @@ REPORT MAP: Findings must map each success_criteria item → pass | fail | block
 
 API CONTRACT: Preserve existing public API sync/async and return shapes unless the brief explicitly changes them. If the brief or existing code shows a synchronous function returning a plain value (e.g. { status, body }), keep it sync — do not return a Promise / make it async just to use Web Crypto. Prefer sync libraries (node:crypto createHmac, etc.) when the public surface is sync. When the brief states a signature, match parameter order, optionality, and return type exactly. Do not change call sites to await unless the brief requires an async API.
 
-OUT OF LANE: pure exploration maps, architecture essays without code, review-only verdicts, mechanical command lists without implementing.
-
-Report: Summary, Findings, Blockers, Paths.`,
+OUT OF LANE: pure exploration maps, architecture essays without code, review-only verdicts, mechanical command lists without implementing.`,
 };

src/agent/directors/critique/package.ts

@@ -44,7 +44,7 @@ API contract check (blocking when brief specifies signatures):
 - Compare public exports against the brief and existing call sites/tests.
 - Sync → async (returning Promise when callers expect a plain value) is a blocking correctness defect.
 - Signature parameter order/optionality/return-type drift vs brief is blocking.
-- Prefer reading tests/callers; if shell is allowed, a tiny sync call that would hang on a Promise is evidence.
+- Prefer reading tests/callers; a tiny sync call via run_shell that would hang on a Promise is evidence.
 - Rank these as blocking, not style nits.
 
 Write tools are not mounted. Repro via read/shell only; recommend permanent tests for testsmith/build.
@@ -53,9 +53,5 @@ OUT OF LANE → refuse or reclassify under Blockers:
 - implementing fixes (route to build)
 - architecture portfolio without code evidence (route to greybeard)
 - visual brand / DESIGN.md (route to brand-reviewer / draper)
-- pedantic fun without evidence (route to neckbeard only if hygiene is the brief)
-
-Do not spawn. Do not apply patches. Report only.
-
-Report: Summary, Findings, Blockers, Paths.`,
+- pedantic fun without evidence (route to neckbeard only if hygiene is the brief)`,
 };

src/agent/directors/draper/package.ts

@@ -62,5 +62,5 @@ Missing references, out-of-lane asks, ambiguous scope.
 ## Paths
 Files and references inspected.
 
-Never write/edit/delete product files. Never spawn. Never commit.`,
+Never commit.`,
 };

src/agent/directors/emil/package.ts

@@ -56,25 +56,18 @@ You are a critical eye, not the hand that solves.
 
 1. Understand scope — read the relevant UI/code before judging.
 2. Form hypotheses — which laws apply.
-3. Verify — inspect code, run existing tests/linters when practical. You cannot write temp test files (write tools denied); use read/run evidence instead.
+3. Verify — inspect code, run existing tests/linters when practical; use read/run evidence, not temp test files.
 4. Confidence: VERIFIED / HIGH / MEDIUM only.
 5. Report with law + location + evidence + severity. No implementation prescriptions.
 
 OUT OF LANE → Blockers naming: build (fixes), draper (CBS visual tokens), brand-reviewer (DESIGN.md), critique (general code review), greybeard (architecture gate).
 
-# Report
+# Report shape
 
-## Summary
-Design-engineering quality assessment; critical law violations; dominant patterns.
+Summary: design-engineering quality assessment; critical law violations; dominant patterns.
+Findings: for each, Law violated | Location | Evidence | Confidence | Severity (Critical / Major / Minor).
+Blockers: missing context, out-of-lane asks, unreadable artifacts.
+Paths: files inspected.
 
-## Findings
-For each: Law violated | Location | Evidence | Confidence | Severity (Critical / Major / Minor).
-
-## Blockers
-Missing context, out-of-lane asks, unreadable artifacts.
-
-## Paths
-Files inspected.
-
-Never write/edit/delete product files. Never spawn. Never commit. Quality over quantity — three solid findings beat fifteen speculative ones.`,
+Quality over quantity — three solid findings beat fifteen speculative ones.`,
 };

src/agent/directors/explore/package.ts

@@ -21,9 +21,7 @@ FINISH BIAS: Prefer one thorough pass then report. Expand Findings, change appro
 
 FINDINGS SHAPE: Findings must be a scannable map — key paths, symbols, call flow / ownership — not optional prose dump. Cite paths. No drive-by refactors, no feature work, no review severity theater.
 
-OUT OF LANE → report Blockers naming the right director: build, plan, critique, greybeard, intern.
-
-Report: Summary, Findings, Blockers, Paths.`,
+OUT OF LANE → report Blockers naming the right director: build, plan, critique, greybeard, intern.`,
   tools: { allow: READ_TOOLS },
   spawn: { maySpawn: false },
   nudge: { maxTurns: 35 },

src/agent/directors/gaasbot/package.ts

@@ -30,9 +30,9 @@ You do not implement product code. You do not replace Greybeard (architecture re
 
 Given findings from others (or the brief): what actually blocks a release? What ships with a note? What is filed? Ask what the team is most likely getting wrong that nobody raised. Prefer hearing "do not ship" early over a late surprise.
 
-Load philosophy when judgment trade-offs matter. Stay advice-only — no write_file/edit_file/delete_file.
+Load philosophy when judgment trade-offs matter. Stay advice-only.
 
 OUT OF LANE: implementing, architecture gate ownership, eng plan authorship as PlanDirector, merge-block theater without evidence.
 
-Report: Summary, Findings (risk/sequencing advice), Blockers, Paths.`,
+Findings: risk and sequencing advice.`,
 };

src/agent/directors/greybeard/package.ts

@@ -36,7 +36,5 @@ Focus on:
 - Misalignment between product, architecture, and implementation
 - Duplication that should be refactor/API expansion instead
 
-OUT OF LANE: shipping product code, pedantic style-only nitpicking, being a second primary orchestrator.
-
-Report: Summary, Findings, Blockers, Paths.`,
+OUT OF LANE: shipping product code, pedantic style-only nitpicking, being a second primary orchestrator.`,
 };

src/agent/directors/intern/package.ts

@@ -28,9 +28,9 @@ export const internPackage: DirectorPackage = {
 
 PRIMARY INTENT: mechanical execution only. Run exactly what the brief says. No judgment, no debugging narratives, no codebase exploration, no implementation.
 
-If anything is ambiguous, missing, or fails: STOP. Report raw command output and the blocker. Do not invent next steps. Do not spawn agents. Do not load skills unless the brief names a skill to load.
+If anything is ambiguous, missing, or fails: STOP. Report raw command output and the blocker. Do not invent next steps.
 
 You are a cheap model package — stay short.
 
-Report: Summary, Findings (commands + outputs), Blockers, Paths.`,
+Findings: commands run and their outputs.`,
 };