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 ASMN-96/ai-agents-skills-toolkit --skill security-reviewgit clone --depth 1 https://github.com/ASMN-96/ai-agents-skills-toolkitWrote 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/asmn-96/ai-agents-skills-toolkit/security-review)<a href="https://agentmods.dev/skills/asmn-96/ai-agents-skills-toolkit/security-review"><img src="https://agentmods.dev/badge/skills/asmn-96/ai-agents-skills-toolkit/security-review/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/asmn-96/ai-agents-skills-toolkit/security-review"><img src="https://agentmods.dev/badge/skills/asmn-96/ai-agents-skills-toolkit/security-review.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 | $0.00389 |
| Opus 5 | $0.00028 | $0.00195 |
| Sonnet 5 | $0.00011 | $0.00078 |
| Haiku 4.5 | $0.00006 | $0.00039 |
Grade A, and why
security-review 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 12d 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.
What it actually says
Security Review
Use this as the canonical final security review skill for application and toolkit work.
This skill is a review and routing layer. It does not authorize production scans, secret access, policy weakening, external installs, CI edits, MCP setup, global config changes, or tool activation.
Review Focus
- Trust boundaries, auth, authorization, public/private payloads, and tenant data are explicit.
- Secrets, tokens, credentials, cookies, and private environment values are not exposed.
- External sources and tools remain untrusted until reviewed.
- Tenant isolation, RLS, API payloads, source safety, and supply-chain metadata are checked when in scope.
- Metadata-only tool records, skipped scans, dry-runs, unavailable scanners, and partial reviews are labeled honestly.
- Route application security readiness through
.ai-toolkit/methods/security/application-security-readiness.md. Canonical toolkit source:methods/security/application-security-readiness.md.
Tool Boundaries
Use scanner metadata only as routing intelligence unless the target project already owns the scanner command or the owner separately approves a scoped scan. Do not use Socket, ZAP, Harden-Runner, deep secret scanners, CI permission changes, or production-impacting scans without explicit approval.
Route WebView, native bridge, token/cookie, deep-link, local-file, and embedded-content risks through .ai-toolkit/methods/security/webview-boundary-review.md. Canonical toolkit source: methods/security/webview-boundary-review.md.
Completion Evidence
Report findings by severity, coverage, commands run, skipped checks, WARN output, and residual security risk.
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.
- 12d ago First seen · 30 lines · 57 tokens per session scan A 6bf802ca7848
security-review is a skill published in the GitHub repository ASMN-96/ai-agents-skills-toolkit (5 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 389 once invoked, about $0.0003 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
vc-agent-teams
Coordinate durable or cross-process work with local JSON mailboxes and vc teams commands. Use when messages must persist beyond one Codex session; prefer built-in Codex subagents for normal in-session delegation.
vc-phase-loop
Run a bounded evidence-first plan, execute, and verify workflow for multi-step implementation or repair tasks. Use when the user wants end-to-end completion; do not use for a simple answer or when a required decision needs user authority.
vc-router
Select the smallest suitable Vibe Codex workflow for a request. Use when the user wants help choosing between direct execution, the phase loop, or durable mailbox coordination.
replace-me
State the specific task this skill handles, when it should trigger, and when it should not.
vcf
Explicit short alias for vc-phase-loop. Use only when the user invokes $vcf for bounded end-to-end execution with verification.
vcg
Explicit short alias for vc-router. Use only when the user invokes $vcg and wants the smallest suitable Vibe Codex workflow selected.