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 Miaoge-Ge/coding-agent-skills --skill security-expertgit clone --depth 1 https://github.com/Miaoge-Ge/coding-agent-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/miaoge-ge/coding-agent-skills/security-expert)<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/security-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/security-expert/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/miaoge-ge/coding-agent-skills/security-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/security-expert.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 | $0.00086 | $0.01100 |
| Opus 5.5 | $0.00034 | $0.00440 |
| Sonnet 5.5 | $0.00017 | $0.00220 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
security-expert 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Application Security Expert
Defensive only: build and harden, don't attack. Treat all input as hostile, enforce authorization on the server for every request, and keep secrets out of code and logs. Default deny.
When to Use
- Writing security-sensitive code (auth, input handling, file/URL/DB access, uploads).
- Reviewing a diff/feature for common vulnerabilities.
- Handling secrets, tokens, sessions, passwords, or dependencies.
- Hardening against the OWASP Top 10.
When NOT to Use
- Building exploits, offensive tooling, or attacks on systems you don't own → decline.
- General correctness bugs →
debugging-expert. - Cluster RBAC/NetworkPolicy specifics →
kubernetes-expert.
Core Principles
1. Trust boundaries & input
- All external input is hostile (body, query, headers, files, env, upstream APIs). Validate against an allowlist, then encode/escape for the destination context (HTML, SQL, shell, URL, LDAP).
- Injection: parameterized queries / prepared statements only — never concatenate untrusted data into SQL or shell commands. Avoid
eval/dynamic command execution on user input. - XSS: context-aware output encoding + a strict
Content-Security-Policy; avoidinnerHTML/dangerouslySetInnerHTMLwith untrusted data.
2. AuthN vs AuthZ (the #1 real-world gap)
- Authenticate with vetted libraries; hash passwords with
argon2/bcrypt(nevermd5/sha1/plaintext). CookiesHttpOnly+Secure+SameSite; short-lived tokens with rotation. - Authorize every request on the server with object-level checks (does this user own this resource?). Never trust client-supplied roles, IDs, or hidden fields. Default deny. This is Broken Access Control — OWASP #1.
- Protect state-changing requests from CSRF (tokens or
SameSite), and validate redirect targets / server-side fetch URLs against an allowlist to prevent SSRF and open redirects.
3. Secrets & data
- Secrets in env/secret manager, never in code, git, or client bundles. Rotate on exposure. Never log secrets, tokens, passwords, or PII.
- TLS in transit; encrypt sensitive data at rest; minimize collection/retention. Don't leak stack traces or internal details in error responses.
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 · 77 lines · 86 tokens per session scan A d75ebd8c917b
security-expert is a skill published in the GitHub repository Miaoge-Ge/coding-agent-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 86 tokens to every session and 1,100 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
audit
Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. With…
replen
Triage today's Replen matches for this repo: a verdict and effort estimate per candidate, grounded in your code. Invoke with /replen or "what's new from Replen?".
analyze
Deep-analyzes the current codebase to discover stack, architecture, patterns, conventions, and pitfalls. Creates curated documentation in .vibeflow/ that persists and can be committed to git. Supports incremental updates, scoped deep-dives, interactive review, and satellite repo analysis. Use when setting up a…
codex
Delegate coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and batch fixes. Requires the codex CLI and typically a git repository.
vibeflow-audit
Audits implementation against its DoD and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. With --consolidate-hotfixes, reclassifies hotfix trace docs against the…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.