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 agentmods add skills/shandar/pwp-plugin/pwp-security-auditnpx skills add shandar/pwp-plugin --skill pwp-security-auditgit clone --depth 1 https://github.com/shandar/pwp-pluginWrote 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/shandar/pwp-plugin/pwp-security-audit)<a href="https://agentmods.dev/skills/shandar/pwp-plugin/pwp-security-audit"><img src="https://agentmods.dev/badge/skills/shandar/pwp-plugin/pwp-security-audit.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.01186 |
| Opus 5 | $0.00053 | $0.00593 |
| Sonnet 5 | $0.00021 | $0.00237 |
| Haiku 4.5 | $0.00011 | $0.00119 |
Grade A, and why
pwp-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 4d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit Skill
This skill defines how to perform a security-focused code review. Security changes have high blast radius — always flag findings and get explicit approval before making fixes.
Security Mindset
- Assume all input is hostile. User input, API responses, URL parameters, cookies, headers — all untrusted until validated.
- Defense in depth. Never rely on a single layer of protection. Validate on client AND server.
- Least privilege. Give code, users, and services only the permissions they need. Nothing more.
- Flag, don't fix (without approval). Security changes can break auth flows, lock users out, or introduce regressions. Always get approval first.
Security Review Checklist
1. Secrets & Credentials
- No API keys, tokens, or passwords in source code
- No secrets in client-side bundles
- .env files are in .gitignore
- .env.example exists with placeholder values (no real secrets)
- No secrets in commit history
- Server-side environment variables used for sensitive config
2. Input Validation & Sanitization
- All user input validated on the server (not just client-side)
- HTML output sanitized to prevent XSS (no dangerouslySetInnerHTML with user data)
- SQL queries use parameterized statements (no string concatenation)
- File uploads validated (type, size, content — not just extension)
- URL parameters and query strings validated before use
- JSON payloads validated against expected schema
3. Authentication
- Passwords hashed with bcrypt/argon2 (never MD5/SHA1, never plaintext)
- Session tokens are cryptographically random and sufficiently long
- JWT tokens have expiration and are validated on every request
- Password reset tokens are single-use and time-limited
- Rate limiting on login endpoints (prevent brute force)
- Failed login attempts logged (for detection)
4. Authorization
- Every API endpoint checks user permissions (server-side)
- UI hiding is NOT the only access control
- Resource access checks ownership (user can only access their own data)
- Admin routes require admin role verification on every request
- CORS configured to allow only trusted origins
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.
- 4d ago First seen · 105 lines · 105 tokens per session scan A 04a60db18d9d
pwp-security-audit is a skill published in the GitHub repository shandar/pwp-plugin (1 stars, last pushed 6mo ago), licensed MIT. It adds 105 tokens to every session and 1,186 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
glossary-init
USE WHEN setting up a repo for AI-first work, when an agent hallucinates domain term meaning, or when user asks to bootstrap / extend the repo's domain glossary. Surfaces candidate terms by identifier frequency, asks the user for 1-sentence definitions, writes GLOSSARY.md at repo root. Idempotent — re-running adds new…
status
Set a status message on your DevGlobe profile.
codex-pair-resume
Resume codex-pair for this project after a previous pause. Removes .codex-pair/state/paused and clears failure state. Review resumes on the next supported file edit; missing state is a no-op.
conventions-init
USE WHEN setting up a repo for AI-first work (after /init-repo), or when the context-surface hook should start feeding repo conventions to agents before edits. Drafts conventions.yml at repo root: per-kind casing (inferred from the code), a vague-name denylist seed, directory roles, and a hand-filled house-rules…
opik
This skill should be used when the user needs to add Opik tracing or integrations to their code, instrument an LLM application, or needs reference for Opik SDK usage (Python, TypeScript, REST API). Use for tasks like "add tracing", "instrument my code", "use trackopenai", "add OpikTracer", "what span types are…
codex-review
Get a second opinion from OpenAI Codex on your current code changes. Analyzes staged/unstaged diffs and returns prioritized findings. Use when user asks to "review with Codex", "Codex code review", or "ask Codex to check my code".