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 skills add escoffier-labs/skillet --skill security-sweepgit clone --depth 1 https://github.com/escoffier-labs/skilletWrote 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/skills/escoffier-labs/skillet/security-sweep)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/security-sweep"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/security-sweep/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/skills/escoffier-labs/skillet/security-sweep"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/security-sweep.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 | $0.00051 | $0.00970 |
| Opus 5 | $0.00026 | $0.00485 |
| Sonnet 5 | $0.00010 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
security-sweep 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 10d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
security-sweep
A defensive security audit of a repository: find what an attacker could use, report how to fix it. Every finding ships with its remediation; nothing in the report teaches exploitation beyond what is needed to verify the fix.
Read-only, with one exception: never copy, log, or echo discovered secret values anywhere, including the report. Reference secrets by file:line and type only.
Lenses
| Lens | Hunting for |
|---|---|
| Secrets | Credentials, tokens, API keys, private keys in the working tree AND full git history (git log --all -p with pattern grep); high-entropy strings in config |
| Dependencies | Known CVEs (npm audit, pip-audit, govulncheck, cargo audit as applicable), abandoned packages, pinning hygiene, lockfile present |
| Input handling | Injection surfaces (SQL, shell, path traversal, template), missing validation at trust boundaries, unsafe deserialization |
| AuthN/AuthZ | Unprotected routes and endpoints, missing authorization checks distinct from authentication, weak hashing, session handling |
| Exposure | Destructive endpoints reachable without auth (a DELETE route an agent or crawler can hit), debug modes, verbose errors leaking internals, internal hostnames/private IPs/PII in code and docs |
Lens guidance:
- Secrets in history are findings even when the tree is clean; remediation is rotation first, history rewrite second (the publish-readiness skill has the full rewrite recipe).
- For exposure, think about non-human callers too: anything with an OpenAPI spec and an unprotected destructive route will eventually be called by an automated agent.
Verification
Confirm before reporting: trace the path from untrusted input to the sink, or confirm the dependency version is actually in the resolved lockfile, or confirm the route really lacks the auth middleware (read the router, not just the handler). Findings that depend on configuration you cannot see get (unverified) and one severity lower. Do not write exploit payloads to prove findings; a traced code path is the proof.
What ships with it
2 files 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.
- 10d ago First seen · 77 lines · 51 tokens per session scan A 9a465063d3cb
security-sweep is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 970 once invoked, about $0.0003 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
assess-interview-candidate
A structured hiring-assessment workflow that turns a candidate's résumé and a job description into reviewable evidence, interview questions, and an offline HTML report for interviewers.
task-clarifier
Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task…
user-profile-keeper
Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes $user-profile-keeper to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. It can extract durable collaboration…
run-history-skill-builder
Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons…
run-history-skill-upgrader
Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed…
session-handoff-prompt
Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries…