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 luisalima/agent-policy-kit --skill security-reviewgit clone --depth 1 https://github.com/luisalima/agent-policy-kitWrote 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/luisalima/agent-policy-kit/security-review)<a href="https://agentmods.dev/skills/luisalima/agent-policy-kit/security-review"><img src="https://agentmods.dev/badge/skills/luisalima/agent-policy-kit/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/luisalima/agent-policy-kit/security-review"><img src="https://agentmods.dev/badge/skills/luisalima/agent-policy-kit/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 | $0.00021 | $0.00804 |
| Opus 5.5 | $0.00008 | $0.00322 |
| Sonnet 5.5 | $0.00004 | $0.00161 |
| Haiku 4.5 | $0.00002 | $0.00080 |
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 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review
Use this skill after implementation, before closing a large or security-relevant task, when the completed diff plausibly changes security posture.
Good triggers include changes to auth, authorization, parsers, serializers, template rendering, subprocess execution, filesystem paths, network requests, secrets handling, logging of sensitive data, dependency loading, CI/CD, release automation, privileged automation, or user-controlled inputs.
Do not make this a ritual for every task. State why the review is relevant, and let the user decline unless the repo policy makes it a gate.
Goal
Identify high-confidence vulnerabilities newly introduced by the branch or task. This is not a general code review.
Workflow
- Establish the review base with
git status, the current branch, the merge base, changed files, commits, and diff. - Research repository context before judging findings: security model, frameworks, auth patterns, validation helpers, serializers, parsers, shell execution, secrets handling, and deployment assumptions.
- Review only security implications introduced or changed by the diff.
- Trace user-controlled or untrusted input to sensitive sinks such as database queries, template rendering, subprocesses, file paths, deserialization, network requests, authz decisions, and secret/logging paths.
- Report only concrete findings with a clear attack path and at least 8/10 confidence. Prefer missing a theoretical issue over flooding the user with noise.
High-Signal Categories
- Injection: SQL, command, template, XML/XXE, NoSQL, unsafe deserialization, YAML/pickle/eval, XSS through unsafe rendering APIs.
- Authn/authz: bypasses, privilege escalation, session flaws, token validation bugs, cross-tenant access.
- Data exposure: PII or secret disclosure, sensitive endpoint leakage, debug output exposure.
- Crypto and secrets: weak crypto, bad randomness, certificate validation bypass, improper key handling.
- Path and file safety: path traversal or unsafe file operations with untrusted input.
- Supply chain and CI/CD: concrete workflow or dependency-loading paths where an attacker can control code execution or release artifacts.
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 · 94 lines · 21 tokens per session scan A e3934e38434e
security-review is a skill published in the GitHub repository luisalima/agent-policy-kit (3 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 804 once invoked, about $0.0001 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…