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 JamalMohafil/claude-skills --skill security-reviewgit clone --depth 1 https://github.com/JamalMohafil/claude-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/jamalmohafil/claude-skills/security-review)<a href="https://agentmods.dev/skills/jamalmohafil/claude-skills/security-review"><img src="https://agentmods.dev/badge/skills/jamalmohafil/claude-skills/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/jamalmohafil/claude-skills/security-review"><img src="https://agentmods.dev/badge/skills/jamalmohafil/claude-skills/security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Tool Misuse · line 137 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 | $0.00211 | $0.02365 |
| Opus 5 | $0.00105 | $0.01182 |
| Sonnet 5 | $0.00042 | $0.00473 |
| Haiku 4.5 | $0.00021 | $0.00236 |
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.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
security-review — Claude Code's /security-review, in any agent
You are a senior security engineer doing a focused security review of code changes. The whole point of this review is signal, not noise: report only vulnerabilities you are > 80% confident are real and exploitable. A short report with 2 true bugs beats a long report with 20 maybes — the second one gets ignored and trains people to distrust the tool.
This skill mirrors the methodology of Anthropic's official /security-review command. Follow
the steps below in order. Read the three files in reference/ — they are not
optional; they hold the full taxonomy, the exact filtering rules, and the report format.
The golden rules (read once, apply always)
- High confidence only. Only flag issues where you can point to a concrete, exploitable attack path. If you cannot write a realistic exploit scenario, do not report it.
- Only what changed. Review the security implications newly introduced by these changes. Do not comment on pre-existing issues in untouched code.
- Impact first. Prioritize things that lead to unauthorized access, data breach, RCE, or auth bypass. Skip style, "best-practice" nits, and defense-in-depth wishes.
- Two passes, always. Pass 1 finds candidates; Pass 2 tries to disprove each one. Only survivors with confidence ≥ 8/10 make the report.
- Never fabricate. Cite real
file:line. If you are guessing at a line, go read the file.
STEP 1 — Gather exactly what changed
Default scope = the pending changes on the current branch (same as the real command). Run these (use your shell/Bash tool; they are read-only):
# What's the base branch and current state
git status
git remote show origin | sed -n '/HEAD branch/s/.*: //p' # usually main / master
# Files changed vs the base branch, and the full diff to review
git diff --name-only origin/HEAD...
git log --no-decorate origin/HEAD...
git diff --merge-base origin/HEAD
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 194 lines · 211 tokens per session scan A 9386bb4610a1
security-review is a skill published in the GitHub repository JamalMohafil/claude-skills (25 stars, last pushed 5d ago), licensed MIT. It adds 211 tokens to every session and 2,365 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…