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 MichaelYcJo/SpecSeal --skill security-auditgit clone --depth 1 https://github.com/MichaelYcJo/SpecSealWrote 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/michaelycjo/specseal/security-audit)<a href="https://agentmods.dev/skills/michaelycjo/specseal/security-audit"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/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/michaelycjo/specseal/security-audit"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/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 | $0.00057 | $0.00660 |
| Opus 5.5 | $0.00023 | $0.00264 |
| Sonnet 5.5 | $0.00011 | $0.00132 |
| Haiku 4.5 | $0.00006 | $0.00066 |
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 7d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/specseal:security-audit, a checklist walked the same way every time
A scan finds what it was built to look for. The value of a written checklist
is the opposite property: it covers the same ground on a bad day as on a good
one. Walk every heading and say none found explicitly, because a silently
skipped section reads exactly like a clean one.
What this checklist assumes. It describes a service that takes untrusted input over a network: injection through request data, sessions and authorization, data at rest and in transit, deployment configuration. That is the shape of most OWASP material and it is the shape of this file.
Other projects have real threats this will not name. A mobile or desktop client worries about local storage, keychain use, certificate pinning, and what a rooted device can read. An embedded target worries about firmware signing and physical access. A library worries about what it does with attacker-controlled input on behalf of its callers, and about its own supply chain. A data pipeline worries about what leaks into logs and derived datasets.
Say which of those the project is before walking the list. If the answer is "none of the above", a clean report here means the checklist did not apply; say that instead of reporting a pass.
OWASP Top 10 Check
Injection
- SQL: parameterized queries used?
- XSS: output encoding applied?
- Command: user input in shell commands?
- Path traversal: file paths validated?
Authentication and Authorization
- Passwords properly hashed (bcrypt or argon2)?
- Session management secure?
- Auth checks on every endpoint?
- RBAC or ABAC properly implemented?
Data Protection
- Sensitive data encrypted at rest?
- TLS for data in transit?
- PII handling compliant?
- No secrets in code, logs or errors?
Configuration
- Debug mode off in production?
- CORS properly configured?
- Security headers present?
- Dependencies up to date?
Input Validation
- All user input validated at boundary
- Whitelist over blacklist
- File upload restrictions
- Rate limiting on sensitive endpoints
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.
- 7d ago Changed add17fe34b4c
- 2mo ago First seen · 86 lines · 57 tokens per session scan A e0538336f8d3
security-audit is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 660 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 2026-08-31.
Other skills, from other repositories
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.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
pr-review
Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…
pr-review
Use when the user wants to deeply review a pull/merge request or a local diff — "review this PR", "grill the MR", "stress-test this diff", "deep-dive code review", "code review before merge", or when they name a PR/MR URL, number, branch, commit range (A..B/A...B), tag or SHA. Works on GitHub (gh), GitLab (glab), or a…
genshijin-review
A compact pull-request review format that writes one actionable finding per line in Japanese or English.
skill-distiller
Fetches top-rated skills from skills.sh, analyzes them, and synthesizes one token-efficient skill combining the best elements. Use when the user asks to "distill skills for X", "find and combine skills for X", "synthesize skills", "merge skills", "make a skill for X from skills.sh", "update distilled skill", or…