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 atretyak1985/swarmery --skill security-auditgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/security-audit)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/security-audit"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/security-audit/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/atretyak1985/swarmery/security-audit"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/security-audit.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 | $0.00043 | $0.00852 |
| Opus 5.5 | $0.00017 | $0.00341 |
| Sonnet 5.5 | $0.00009 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
security-audit 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 1mo 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Perform a static security audit of the project's application code, configuration, and infrastructure manifests, producing a structured report where every finding carries a file:line citation, OWASP category, severity, and concrete remediation. Covers injection, auth bypass, secrets leakage, insecure configuration, and dependency CVEs; pipeline hardening, image scanning, and SBOMs belong to supply-chain-security.
Rules (never violate)
- Read-only: never modify source files, install packages, or fix findings during an audit.
- Redact any discovered secret with
***in the report — never print credentials in plain text. - Every finding needs a file:line citation, a severity (Critical/High/Medium/Low), and an OWASP category.
- Flag Critical findings (auth bypass, RCE, secrets in git) immediately, before the full report.
- Mark inferred or uncertain findings
[LOW-CONFIDENCE]; do not report guesses as facts. - Use
npm audit --json(never without--json— it may writepackage-lock.json).
Resources
- Read
resources/owasp-checklist.mdat the start of every audit — the authoritative OWASP Top 10 per-category checklist (map items onto the project's actual stack,project.json → stack). - Read
resources/audit-procedure.mdwhen running the audit: the 7-step procedure (secrets, injection, auth, device/realtime transport, dependencies, infrastructure), report template and length budgets, self-check, escalation, examples, failure modes.
How to use
What it does
Runs a read-only static security audit over application code, configuration, and deployment manifests: it walks the OWASP Top 10, hunts hardcoded secrets, injection paths, weak auth, vulnerable dependencies, and unsafe infrastructure settings, then hands you a structured report with a prioritized action plan and a scope-coverage list.
When to use it
- Someone asks to audit, scan, or review code for security vulnerabilities.
- A new feature or module needs a security review before merge.
- A quick secrets pass on the current branch; a suspected auth bypass or injection risk; an OWASP compliance picture for a repo.
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.
- 1mo ago First seen · 67 lines · 43 tokens per session scan A a5371a835590
security-audit is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 852 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
commit-message
Use ANY time the user signals they want to commit staged changes — including bare "commit", "/commit", "commit this", "commit these changes", "let's commit", "make a commit", "git commit", "write a commit message", "make a conventional commit", "use conventional commits", or any equivalent phrasing in context (e.g.…
dependency-versions
MUST consult this skill before answering whenever the user's task involves external versioned dependencies — even if you think you can handle it directly. This applies to: checking if packages/tools are up to date, upgrading npm/pip/cargo/go dependencies, planning or writing CI/CD workflows (GitHub Actions, CircleCI…
finish
Ship phase — merge, PR, keep, or discard with pre-merge verification.
gws-quick-ref
Quick reference for gws CLI syntax — core patterns, key flags, pagination, field masks, and output formats.
excalidraw
Create or extend editable Excalidraw diagrams from descriptions or repository evidence using a local skeleton-to-scene converter.
gws-events-subscribe
Google Workspace Events: Subscribe to Workspace events and stream them as NDJSON.