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 frankxai/claude-skills-library --skill security-reviewgit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/frankxai/claude-skills-library/security-review)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/security-review"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/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/frankxai/claude-skills-library/security-review"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/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 | $0.00043 | $0.00417 |
| Opus 5.5 | $0.00017 | $0.00167 |
| Sonnet 5.5 | $0.00009 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
security-review scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- A curl command piped into a shell. What it actually says
Security review for a port
Read the diff. Then scan the new files for these patterns:
- Instructions to ignore previous directions.
- A private-key block.
sk-anttokens and other live credentials.- A curl command piped into a shell.
enableAllProjectMcpServers.- Hidden bidi or zero-width characters.
A line that tells the reader to reject one of those patterns is not an attack. Read the line. The 2026-10-10 port kept two such files after that read: a regex example, and a prohibition.
Deny list for this machine
Deny reads and writes under ~/.ssh and ~/.aws. Deny ssh, scp, and curl piped to a shell.
Do not blanket-deny .env. Agents here read local env files. Do not commit them.
Do not write an untrusted session into starlight-memory. Keep agent GitHub tokens separate from a personal token. Log the tool, the files, and the approval. Stop a session-owned process group. Do not kill Defender, indexers, or another task's MCP children.
Hooks
A config warning may fire. It must not block settings.json. A markdown warning must exit 0. Ops handovers are markdown on purpose.
AgentShield was not part of this port. Say that in the receipt. Do not claim a scanner you did not run.
Where this came from
The pre-copy scan follows affaan-m/ECC skills/security-review at 4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2 (MIT). The deny exceptions and the fail-open hook rule are estate law.
Built on SIP.
What ships with it
1 file 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.
- 9d ago First seen · 39 lines · 43 tokens per session scan A ada395f16f39
security-review is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 417 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
Other skills, from other repositories
triage
A process for reviewing issues and outside pull requests through category and status labels. An issue is a recorded problem or request, while a pull request is a proposed code change for review.
pr
A writing guide for creating pull request descriptions, which explain a proposed code change to reviewers. It uses sections for the summary, evidence, merge risk, and the likely area affected by the change.
code-review
A code-review skill that compares changes from a chosen commit, branch, tag, or merge-base against the repository’s coding standards and the related issue or specification.
improve-codebase-architecture
A skill that scans a codebase for places where restructuring could make future changes and testing easier, then produces an HTML report for selected improvements.
andrej-karpathy
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
code-reviewer
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.