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-devnpx skills add AKSoftCode/aicrew --skill aicrew-devgit 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 | $0.00037 | $0.00655 |
| Opus 5 | $0.00018 | $0.00328 |
| Sonnet 5 | $0.00007 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
aicrew-dev 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 yesterday.
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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aicrew /dev (Codex)
Codex does not support slash commands. Use this skill when the user asks for "/dev" or a full SDLC pipeline.
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 /dev, Scout opens Phase 1 Research before any Glob/Grep/Read; re-scout between phases if context grew.
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/dev.md- Project overrides in
.ai/skills/and repoAGENTS.md(if present)
Token foundation (mandatory — all phases):
- Graph-first research: codebase-memory-mcp (search_graph → trace_path → get_code_snippet) before any Grep/Read
- Speculative context: Scout pass (cheap model) at start of Phase 1; emit SCOUT: schema; verify before main trace
- Layered guardrails: security-guard.py (input) → scope lock (Phase 0) → karpathy-guardrails (Phase 4) → security-reviewer (Phase 6)
- Context economy: always on; /compact between phases; /lean amplifies
- Two-model routing: Scout on haiku/mini; Research+Implement on sonnet/opus
- See: ~/Agents/docs/token-foundation.md
Workflow summary:
- Intake: clarify bug/feature/refactor, acceptance criteria, scope, risks, test plan.
- Research: Scout pass (graph-first) → verify SCOUT schema → confirm root cause or key code paths.
- Brainstorm: 3 alternatives with trade-offs (features/refactors).
- Design: interface spec, contract checks, over/under-engineering flags.
- Implement: load karpathy-guardrails; TDD first (RED -> GREEN -> REFACTOR per acceptance criterion).
- Tests: targeted automated tests + smoke path.
- Security: changed files only, no false positives.
- Audit: if project defines domain audit checks.
- Conclude: summary, tests run, risks, commit message.
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.
- yesterday First seen · 42 lines · 37 tokens per session scan A a33c3207b276
aicrew-dev is a skill published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 655 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.
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.
institutional-memory-distill
Distill decisions, reasoning, and rejected alternatives from PRs, design docs, and postmortems into the project's decisionledger, so ult-context-generate's trip-wire can surface institutional memory before new work quietly repeats settled ground. Do NOT use to query the ledger against new work or decide…
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.…