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 lgbarn/shipyard --skill security-auditgit clone --depth 1 https://github.com/lgbarn/shipyardWrote 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/lgbarn/shipyard/security-audit)<a href="https://agentmods.dev/skills/lgbarn/shipyard/security-audit"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/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/lgbarn/shipyard/security-audit"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 6 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00097 | $0.01461 |
| Opus 5.5 | $0.00039 | $0.00584 |
| Sonnet 5.5 | $0.00019 | $0.00292 |
| Haiku 4.5 | $0.00010 | $0.00146 |
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 6d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit
When to Use
- Working with any code that handles user input, authentication, or authorization
- Adding or updating dependencies
- Reviewing infrastructure-as-code (Terraform, Ansible, Docker, CloudFormation)
- Before claiming security posture is adequate
- When conversation mentions: security, vulnerability, CVE, OWASP, secrets, hardening
Natural Language Triggers
- "security check", "is this secure", "vulnerability scan", "audit security", "check for secrets"
Core principle: Assume every change introduces risk until proven otherwise.
OWASP Top 10 Quick Checks
For every code change, verify:
- Injection: All user input parameterized/escaped -- no string concatenation in queries or commands
- Broken Auth: Passwords hashed properly (bcrypt/argon2), session tokens random, rate limiting on auth endpoints
- Data Exposure: Encryption at rest and transit, no sensitive data in logs/errors, proper key management
- XXE: XML parsers disable external entities
- Access Control: Authorization on every request (not just UI), default deny, restrictive CORS
- Misconfiguration: Debug mode off in production, default credentials changed, security headers set
- XSS: Output encoding on all user data, CSP headers, no
dangerouslySetInnerHTMLwithout sanitization - Deserialization: No deserializing untrusted data without allowlists
- Vulnerable Components: Dependencies pinned, no known CVEs, lock files committed
- Insufficient Logging: Auth events logged, failures logged, logs don't contain secrets
Secrets Detection
Flag these patterns in ANY file (code, config, IaC, docs, tests):
| Pattern | What It Is |
|---|---|
AKIA[0-9A-Z]{16} |
AWS Access Key |
ghp_[0-9a-zA-Z]{36} |
GitHub Token |
sk-[0-9a-zA-Z]{48} |
OpenAI/Stripe Secret Key |
(postgres|mysql|mongodb)://[^:]+:[^@]+@ |
DB credentials in URI |
-----BEGIN.*PRIVATE KEY----- |
Private key |
(password|secret|token|api_key)\s*[:=]\s*['"][^'"]{8,} |
Generic secret |
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.
- 6d ago Changed · -1 tokens per session ad8ebc0cff3a
- 1mo ago First seen · 146 lines · 98 tokens per session scan A b9d8d3153c51
security-audit is a skill published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 6d ago), licensed MIT. It adds 97 tokens to every session and 1,461 once invoked, about $0.0004 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
gate-wiring
Detects unused exports, orphaned files, architecture layer violations, and circular dependencies across changed files. Delegates to architect agent for structural analysis. Internal gate — invoked by verify.
sw-design
Autonomous solution architecture. Researches the codebase, designs a solution, challenges it adversarially, and produces design artifacts.
sw-review
Fetches and displays PR review comments from GitHub, grouped by priority, and allows the user to reply to or resolve individual threads.
gate-semantic
Tiered semantic analysis of changed code (rg → ast-grep → OpenGrep). Detects error-path bugs structural gates miss. Findings default to WARN. Internal — invoked by verify.
sw-audit
Periodic codebase health check. Analyzes architecture, complexity, consistency, and debt across the full codebase. Produces persistent findings in AUDIT.md.
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.