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 commands/d3x293/code-crew/crew-litegit clone --depth 1 https://github.com/d3x293/code-crewWhat 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 | $0.00026 | $0.00204 |
| Opus 5 | $0.00013 | $0.00102 |
| Sonnet 5 | $0.00005 | $0.00041 |
| Haiku 4.5 | $0.00003 | $0.00020 |
Grade A, and why
crew-lite 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.
What it actually says
Parse the user's message after /crew lite as the task description.
This command always runs in Lite Mode — no --lite flag needed.
Invoke the codecrew:lite-router skill with the task description.
What the lite-router will do:
- Read the project profile and team config
- Classify the task (type + complexity)
- Select agents using only Sonnet + Haiku tiers (no Opus CEO)
- vp-engineering (Sonnet) handles planning that CEO would normally do
- Choose parallel vs sequential execution
- Auto-inject relevant skills from the catalog
- Execute via the agent team
- Auto-update the codebase index for modified files
- Report results with agents, skills, and files modified
Pass the task description to the lite-router skill.
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 · 23 lines · 26 tokens per session scan A 937613af890a
crew-lite is a command published in the GitHub repository d3x293/code-crew (13 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 204 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
update-docs
Update all the documentation related files.
plugin-audit
Run the full 8-phase plugin audit pipeline on a skill directory.
seo-auditor
Scan and optimize docs for SEO — meta tags, readability, keywords, broken links, sitemap.
clean
Clean up merged branches locally and on remote, keeping only main, dev, and gh-pages.
review
Run the local review gate before pushing.