feat: add Promo_Champions_V2.1 ECC bundle

[ecc-tools]

Summary

Auto-generated ECC bundle from repository analysis.

What This Does

Merging this PR adds repo-local ECC artifacts for both Claude Code and Codex. The generated bundle captures repository patterns, Codex baseline config, and reusable workflow scaffolds derived from git history analysis.

Analysis Scope

• Commit history patterns and conventions
• Code architecture and structure
• Testing patterns and coverage
• Recurring workflows

Files

Path	Description
.claude/ecc-tools.json	ECC install manifest used for upgrades, repair, and uninstall.
.claude/skills/Promo_Champions_V2.1/SKILL.md	Repository-specific Claude Code skill generated from git history.
.agents/skills/Promo_Champions_V2.1/SKILL.md	Codex-facing copy of the generated repository skill.
.agents/skills/Promo_Champions_V2.1/agents/openai.yaml	Codex skill metadata so the repo skill appears cleanly in the skill interface.
.claude/identity.json	Suggested identity.json baseline derived from repository conventions.
.codex/config.toml	Repo-local Codex MCP and multi-agent baseline aligned with ECC defaults.
.codex/AGENTS.md	Codex usage guide that points at the generated repo skill and workflow bundle.
.codex/agents/explorer.toml	Read-only explorer role config for Codex multi-agent work.
.codex/agents/reviewer.toml	Read-only reviewer role config focused on correctness and security.
.codex/agents/docs-researcher.toml	Read-only docs researcher role config for API verification.
.claude/homunculus/instincts/inherited/Promo_Champions_V2.1-instincts.yaml	Continuous-learning instincts derived from repository patterns.

Optional: Continuous Learning (6 instincts)

This PR also includes instincts for the continuous-learning-v2 skill. These are optional and only useful if you use that skill.

Import after merging:

/instinct-import .claude/homunculus/instincts/inherited/Promo_Champions_V2.1-instincts.yaml

Review Checklist

• Verify detected patterns are accurate
• Confirm generated config, commands, and skill metadata match the repo’s real workflow
• Check best practices align with team standards before merging

---

_{ECC Tools | Everything Claude Code}

---

Summary by cubic

Adds repo-local ECC config for Claude Code and Codex, auto-generated from analysis of this repository's history and structure. The bundle adds repo skills, Codex multi-agent roles, an MCP baseline, and an install manifest; no existing files are modified.

What's included

• Repo skill in .claude/skills/ and .agents/skills/ encodes detected conventions for commits, naming, imports/exports, and tests.
• .codex/config.toml enables MCP servers and read-only explorer, reviewer, and docs-researcher roles.
• .claude/ecc-tools.json is the install manifest tracking all managed files for upgrades, repair, and uninstall.
• .claude/homunculus/instincts/inherited/ adds optional continuous-learning instincts; import with /instinct-import if you use the continuous-learning-v2 skill.
• .claude/identity.json sets a suggested baseline (technical, detailed, TypeScript-focused).

Review focus

• Detected conventions come from a single analyzed commit, so commit-style and naming patterns may be under-sampled.
• Confirm the generated skill, MCP baseline, and agent role configs match the repo's real workflow before merging.

^{Written for commit 700df2c. Summary will update on new commits.}

Greptile Summary

The PR adds an auto-generated ECC bundle for Claude Code and Codex, including repository skills, agent roles, MCP configuration, identity metadata, and continuous-learning instincts.

• Adds matching Claude and Codex repository-convention skills.
• Adds a repo-local Codex baseline with six MCP integrations and three read-only specialist roles.
• Adds ECC ownership metadata, identity preferences, and inherited convention instincts.

Confidence Score: 4/5

The PR appears safe to merge after considering two non-blocking improvements: correcting inaccurate repository guidance and pinning executable MCP dependencies.

The bundle files and manifest are structurally present, but the generated naming convention conflicts with the existing codebase and the MCP baseline executes mutable npm package resolutions.

Files Needing Attention: .agents/skills/Promo_Champions_V2.1/SKILL.md, .claude/skills/Promo_Champions_V2.1/SKILL.md, .codex/config.toml

Security Review

The npm-backed MCP definitions resolve mutable package releases at invocation time. Pinning immutable reviewed versions would make execution reproducible and reduce supply-chain exposure in workspace-write sessions.

Important Files Changed

Filename	Overview
.agents/skills/Promo_Champions_V2.1/SKILL.md	Adds implicitly invocable repository guidance, but its snake_case naming instruction contradicts established PascalCase and camelCase filenames.
.claude/skills/Promo_Champions_V2.1/SKILL.md	Adds the Claude-facing copy of the same generated conventions and carries the same inaccurate naming guidance.
.codex/config.toml	Adds Codex agents and MCP servers, with non-reproducible npm package resolution that warrants supply-chain hardening.
.claude/ecc-tools.json	Records the generated bundle inventory and adapter paths consistently with the files present in the PR head.
.claude/homunculus/instincts/inherited/Promo_Champions_V2.1-instincts.yaml	Adds optional learned conventions, including the same inaccurate snake_case naming instruction.

Prompt To Fix All With AI

### Issue 1
.agents/skills/Promo_Champions_V2.1/SKILL.md:65-71
**Inaccurate file-naming convention**

This implicitly invocable skill instructs agents to use snake_case filenames, while the repository predominantly uses PascalCase for React components and camelCase for helpers. Following this guidance will introduce files inconsistent with the surrounding codebase and create avoidable naming churn.

### Issue 2
.codex/config.toml:10-27
**Mutable MCP package execution**

The npm-backed MCP definitions use `npx -y` with unversioned packages or mutable `latest` tags, so identical repository revisions can execute different third-party code over time in a workspace-write session. Pin reviewed immutable versions to make execution reproducible and reduce supply-chain exposure.

**How this was verified:** The configuration combines `sandbox_mode = "workspace-write"` with mutable npm package resolution for the configured MCP processes.

---

For each issue above, determine whether it is valid and should be fixed. If so, fix it directly.

_{Reviews (1): Last reviewed commit: "feat: add Promo_Champions_V2.1 ECC bundl..." | Re-trigger Greptile}

Greptile also left 2 inline comments on this PR.

[greptile-apps]

Inaccurate file-naming convention

This implicitly invocable skill instructs agents to use snake_case filenames, while the repository predominantly uses PascalCase for React components and camelCase for helpers. Following this guidance will introduce files inconsistent with the surrounding codebase and create avoidable naming churn.

Prompt To Fix With AI

This is a comment left during a code review.
Path: .agents/skills/Promo_Champions_V2.1/SKILL.md
Line: 65-71

Comment:
**Inaccurate file-naming convention**

This implicitly invocable skill instructs agents to use snake_case filenames, while the repository predominantly uses PascalCase for React components and camelCase for helpers. Following this guidance will introduce files inconsistent with the surrounding codebase and create avoidable naming churn.

---

For each issue above, determine whether it is valid and should be fixed. If so, fix it directly.

Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!

[greptile-apps]

Mutable MCP package execution

The npm-backed MCP definitions use npx -y with unversioned packages or mutable latest tags, so identical repository revisions can execute different third-party code over time in a workspace-write session. Pin reviewed immutable versions to make execution reproducible and reduce supply-chain exposure.

How this was verified: The configuration combines sandbox_mode = "workspace-write" with mutable npm package resolution for the configured MCP processes.

Prompt To Fix With AI

This is a comment left during a code review.
Path: .codex/config.toml
Line: 10-27

Comment:
**Mutable MCP package execution**

The npm-backed MCP definitions use `npx -y` with unversioned packages or mutable `latest` tags, so identical repository revisions can execute different third-party code over time in a workspace-write session. Pin reviewed immutable versions to make execution reproducible and reduce supply-chain exposure.

**How this was verified:** The configuration combines `sandbox_mode = "workspace-write"` with mutable npm package resolution for the configured MCP processes.

---

For each issue above, determine whether it is valid and should be fixed. If so, fix it directly.