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.
git clone --depth 1 https://github.com/t1djani/outfitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/t1djani/outfit/outfit)<a href="https://agentmods.dev/commands/t1djani/outfit/outfit"><img src="https://agentmods.dev/badge/commands/t1djani/outfit/outfit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/t1djani/outfit/outfit"><img src="https://agentmods.dev/badge/commands/t1djani/outfit/outfit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00017 | $0.00243 |
| Opus 5 | $0.00009 | $0.00121 |
| Sonnet 5 | $0.00003 | $0.00049 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
outfit 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 9d 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
Run the outfit skill on this project.
Depth: $ARGUMENTS
Harvest the evidence (scripts/harvest.py), do the recon — read the project for meaning, probe which MCP servers / CLIs / docs are actually connected and adapt, infer the domain — then propose skills and agents tailored to this repo, each grounded in real evidence. Present them with a multi-select so I pick. Write only what I choose to .claude/skills/ and .claude/agents/, validate each draft's form with hooks/validate-draft.sh, and then register the kit — index the new capabilities in this project's CLAUDE.md/AGENTS.md (show me the diff and get my yes before editing CLAUDE.md).
If thorough is passed, fan out one recon subagent per thread (roadmap & docs, code conventions, git/CI signals, resources & connected tools) before synthesizing. Otherwise do a single recon pass.
Do not write anything before I have made my selection.
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.
- 9d ago First seen · 15 lines · 17 tokens per session scan A a7515476f674
outfit is a command published in the GitHub repository t1djani/outfit (1 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 243 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 2026-08-31.
Other commands, from other repositories
security-review
A security review procedure based on CWE, a list of common software weaknesses, and STRIDE, a method for identifying threats to a system.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.
refactor
Analyze code for SOLID violations and suggest targeted improvements.
factcheck
Verify BibTeX entries and cited claims against DBLP and web sources. Checks author names, venues, years, and specific numerical claims.
generate-tests
Generate comprehensive tests for specified code.