メニュー
Use when scanning new commits in the external affaan-m/everything-claude-code repo for ideas worth adopting. Triggers on "catchup ecc", "check ecc", "what is new in ecc", "check affaan".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | catchup-ecc |
| description | Use when scanning new commits in the external affaan-m/everything-claude-code repo for ideas worth adopting. Triggers on "catchup ecc", "check ecc", "what is new in ecc", "check affaan". |
Review new commits in affaan-m/everything-claude-code since last check and surface changes worth adopting.
Read ~/.claude/dev/local/ecc-cursor. Format:
<last_commit_sha>
If no cursor file exists (first run), fetch the latest commit SHA from the repo, write it to the cursor file, report "Cursor initialized at <sha>, nothing to compare yet" and stop.
Use the GitHub API to list commits since the cursor SHA:
gh api repos/affaan-m/everything-claude-code/commits --paginate -q '.[].sha'
Save the command's output to dev/local/tmp/ecc-commits.txt with the Write
tool (shell redirects into dev/local/ are blocked by the aegis hook).
Find commits newer than the cursor SHA. If the cursor SHA is not found in the list (history rewrite or too old), fetch the last 30 commits and note this in the report.
If no new commits, report "No new changes since last check" and stop.
For each new commit (oldest first):
gh api repos/affaan-m/everything-claude-code/commits/<sha>~/.claude setup:
Focus on:
Show a table:
SHA (short) | message | classification | what's relevant
For each interesting or check item, include a brief note on what the user might want to adopt and how it differs from their current setup.
Wait for user input before making any changes.
After review is complete (regardless of what the user adopts), write the new HEAD SHA to ~/.claude/dev/local/ecc-cursor.
| Situation | Action |
|---|---|
| Cursor file missing | Initialize and stop (first run) |
| Cursor SHA not in history | Fetch last 30 commits, note gap |
gh not authenticated | Ask user to run ! gh auth login |
| Rate limit hit | Report and suggest trying later |
| Repo renamed/deleted | Report error and stop |
Use when designing a goal-oriented agent loop or reviewing one for runaway risk - build gate, machine-decidable goal, anti-Goodhart boundaries, five failure modes. Triggers on "design a loop", "review this loop", "will this loop run away".
Use when running OpenAI Codex via the codex CLI (copilot CLI fallback) for code analysis, refactoring, or editing. Triggers on "run codex", "codex analyze", "ask codex", "copilot with codex".
Use when running Google Gemini via the native Gemini CLI for code analysis, refactoring, or editing. Triggers on "run gemini", "gemini analyze", "ask gemini".
Use when running a local Qwen model (via llama.cpp and the pi agent) for code analysis, refactoring, or editing - local inference, no API cost. Triggers on "run qwen", "qwen analyze", "ask qwen", "local model task".
Use when running Anthropic Claude Sonnet via the native claude CLI (headless) for code analysis, refactoring, or editing. Triggers on "run sonnet", "sonnet analyze", "ask sonnet".
Use when converting a plan, design doc, brainstorming output, or discovery doc into a structured PRD saved to the backlog. Triggers on "create PRD", "create PRD from plan", "make PRD", "convert to PRD", "save plan as PRD".