Aicrew fix
TDD-first AI dev pipeline for Claude Code, Cursor, Codex, Gemini CLI & Antigravity. /dev /fix /quick + token-saving hooks. npx aicrew install
npx -y skills add AKSoftCode/aicrew --skill aicrew-fixAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Run the aicrew /fix fast bug fix flow in Codex (triage -> root cause -> TDD -> verify).
SKILL.md
2.1 KB, as published. Nobody here has run it
aicrew /fix (Codex)
Use for fast bug fixes. This mirrors the /fix command but runs inline in Codex.
Token foundation (mandatory)
/dev, /fix, and /quick all share the same 11-capability token-saving stack — only pipeline depth differs. Full reference: ~/Agents/docs/token-foundation.md. Stack: graph-first (codebase-memory-mcp), speculative Scout → verify (SCOUT schema, two-model routing), Karpathy guardrails, layered guardrails (guardrails-taxonomy.md), context-economy read policy, security-guard.py hooks, .ai/state checkpoints, /compact between phases, /handoff on tool switch, optional context-mode + token-optimizer-mcp, caveman default output. For /fix, Scout opens Phase 1 Bug Analysis before the bug-analyst deep dive.
Default output
Caveman/lean style by default. See ~/Agents/agents/caveman.md and ~/Agents/agents/context-economy.md. /normal or /lean off restores verbose.
Source of truth:
~/Agents/commands/fix.md- Project overrides in
.ai/skills/and repoAGENTS.md(if present)
Token foundation (mandatory — all phases):
- Graph-first: codebase-memory-mcp (search_graph → trace_path → get_code_snippet) before any file read
- Speculative context: Scout pass at start of Phase 1 Bug Analysis; emit SCOUT: schema; verify before bug-analyst deep dive
- Layered guardrails: security-guard.py (input) → karpathy-guardrails (Phase 2 implement) → security-reviewer (Phase 4)
- Context economy: always on; slice reads only during Scout
- Two-model routing: Scout on haiku/mini; fix on sonnet
- See: ~/Agents/docs/token-foundation.md
Workflow summary:
- Ask the 3 clarifying questions (symptom, expected behavior, repro).
- Scout pass (graph-first) → emit SCOUT: schema → verify → bug-analyst deep trace → confirm root cause.
- Load karpathy-guardrails; write the smallest failing test or reproducible check.
- Implement the minimal fix to make it pass.
- Run targeted tests + smoke path.
- Security review on changed files.
- Conclude with summary, tests run, and any risks.