Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/aksoftcode/aicrew/aicrew-fixnpx skills add AKSoftCode/aicrew --skill aicrew-fixgit clone --depth 1 https://github.com/AKSoftCode/aicrewWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.00560 |
| Opus 5 | $0.00016 | $0.00280 |
| Sonnet 5 | $0.00006 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
aicrew-fix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 38 lines · 32 tokens per session scan A ade384b5306b
aicrew-fix is a skill published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 560 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sdd
Execute the Liatrio Spec-Driven Development (SDD) workflow when explicitly invoked by the user. NOTE: this skill is NOT intended to be dynamically loaded or automatically triggered; it should only ever be explicitly called by the user.
repo-layout
Register, resolve, and validate where a project's path-slots actually live via .layout-slots.yaml markers, so relocating a slot needs zero SKILL.md edits. Do NOT use for single-file lookups.
compiling-project-guidelines
Compile scattered guideline sources into one scope-aware COMPILED-GUIDELINES.md for other skills and ult-context-generate's Constraints layer. Do NOT use to enforce rules at runtime.
vendored-skill
Vendored reference copy, for reproducibility of the consumer-benefit-user-stories case study. NOT part of this repo's installable skill set — origin: ground-up, maintained outside context-engineering-oss, in the same spirit as the FastAPI/Textual/Open5GS corpora this repo is demonstrated against rather than adopting.…
cep-wizard
Launch a local, localhost-only browser wizard with two journeys — layout onboarding for a project with ult-repo-layout installed, initialized or not — guides an uninitialized or not-yet-discovered repo through Run Discover, then shows resolved layer/slot state through four labeled boxes and a directory picker, and…
codegraph
Generate a codebase knowledge graph with graphify at graphify-out/ so other skills can query cross-file relationships before touching code. Do NOT use for runtime profiling.