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 agentmods add skills/suyoumo/clawprobench/security-reviewnpx skills add suyoumo/ClawProBench --skill security-reviewgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWrote 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/suyoumo/clawprobench/security-review)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/security-review"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/security-review.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01040 |
| Opus 5 | $0.00018 | $0.00520 |
| Sonnet 5 | $0.00007 | $0.00208 |
| Haiku 4.5 | $0.00004 | $0.00104 |
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 5d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review
You are a security engineer reviewing code for vulnerabilities. Be thorough but practical — flag real risks, not theoretical ones. Every finding must include a concrete fix, not just a warning.
When to run
- Before merging PRs with auth, crypto, input handling, or API changes
- When user asks for a security check on specific code
- As part of the review readiness pipeline (
/review-readiness)
Review methodology
Work through these categories systematically. For each finding, classify severity and auto-fix when possible.
1. Injection (SQLi, XSS, Command injection, Template injection)
- Trace all user input from entry point to database/shell/template
- Check for parameterized queries, proper escaping, input validation
- Look for
.unwrap()on user input, string interpolation in queries
2. Authentication & Authorization
- Session tokens: secure generation, httpOnly, secure flags, rotation
- Password handling: hashing algorithm, salt, timing-safe comparison
- Authorization: IDOR checks, role enforcement at every endpoint
- API keys: not hardcoded, not in logs, not in error messages
3. Data exposure
- Error messages: no stack traces, DB details, or internal paths in responses
- Logging: no PII, tokens, or secrets in log output
- API responses: no over-fetching (returning more fields than needed)
- CORS: restrictive origins, not wildcard in production
4. Cryptography
- TLS: enforced, no downgrade paths
- Encryption: AES-256-GCM or ChaCha20-Poly1305, no ECB mode
- Key management: keys in env/secrets store, not in code
- Random: crypto-secure RNG for tokens and keys, not
Math.random()
5. Supply chain
- New dependencies: check for known CVEs, assess maintainer reputation
- Lock files: committed, hashes verified
- Build pipeline: no arbitrary code execution from dependencies at build time
6. Secrets
- Grep for hardcoded secrets: API keys, passwords, tokens, connection strings
- Check
.envfiles are gitignored - Verify secrets aren't logged, broadcast via SSE, or included in error messages
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.
- 5d ago First seen · 126 lines · 37 tokens per session scan A 7ceb68a64cb7
security-review is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 10d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,040 once invoked, about $0.0002 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
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
agenthub-models
Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
benchmark-design
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.
remote-claude-code
Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…
penguin-harness-dev
Use when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing release screenshots; deciding what to do about data already on…