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 ckorhonen/swe-skills --skill security-auditgit clone --depth 1 https://github.com/ckorhonen/swe-skillsWrote 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/ckorhonen/swe-skills/security-audit)<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/security-audit"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/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/ckorhonen/swe-skills/security-audit"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/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 | $0.00108 | $0.01610 |
| Opus 5 | $0.00054 | $0.00805 |
| Sonnet 5 | $0.00022 | $0.00322 |
| Haiku 4.5 | $0.00011 | $0.00161 |
Grade A, and why
swe: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 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.
How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Security Audit
What This Skill Does
Use this skill to run a dependency- and package-surface-focused security audit across a repository, workspace, or monorepo.
The primary job is to find evidence-backed issues in:
- Vulnerabilities
- Outdated dependencies with real security relevance
- License issues
- Dependency hygiene gaps that materially weaken auditability
When To Use
Use this skill when the user wants to:
- Audit a repo or monorepo for vulnerable packages
- Check dependency freshness and license risk
- Review package surfaces service by service
- Produce one consolidated dependency-security report
Do Not Use
Do not use this skill for:
- A broad application code review
- Threat modeling
- Hand-auditing runtime bugs unrelated to dependencies or manifests
- Guessing about security posture without manifests, lockfiles, or scanners
Inputs To Confirm
Confirm or infer:
- Repo or package scope
- Whether the audit should include all services or only selected units
- Which package managers and ecosystems are present
- What scanners or audit tools are available locally
Parallelization Rule
Create one session per service or package when the environment supports parallel agent work.
- Run up to 10 sessions at a time
- Give each session a disjoint surface area
- Have each session return raw evidence, not just conclusions
- Compile the final report centrally after the sessions finish
If parallel sessions are unavailable, process the units in local batches and keep the same report shape.
Instructions
Step 1: Identify Audit Units
Inspect the repository and group the codebase into the smallest practical independent audit surfaces, such as:
- Services
- Apps
- Packages
- Libraries
- Deployable components
Step 2: Detect Each Unit's Ecosystem
For every unit, determine the ecosystem and package manager in use so the correct scanner or audit command can be chosen.
Step 3: Run The Strongest Available Checks
Run the most appropriate security, dependency, and license checks for each surface. Prefer the package manager and scanners already used by the repo.
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 · 271 lines · 108 tokens per session scan A 6292b5e60db4
swe:security-audit is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,610 once invoked, about $0.0005 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.