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.
git clone --depth 1 https://github.com/CrashBytes/claude-role-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/commands/crashbytes/claude-role-skills/security-review)<a href="https://agentmods.dev/commands/crashbytes/claude-role-skills/security-review"><img src="https://agentmods.dev/badge/commands/crashbytes/claude-role-skills/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 5.1 | $0.00008 | $0.00529 |
| Opus 5 | $0.00004 | $0.00264 |
| Sonnet 5 | $0.00002 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
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 8d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review
Perform a security-focused code review on a file or set of changes.
Arguments
Target to review: $ARGUMENTS
Context
Recent changes: !git diff --stat HEAD~1 2>/dev/null || echo "No git context"
Workflow
-
Identify review scope
- If a file path is provided, read it
- If a git ref is provided, get the diff
- If no argument, review staged or recent changes
-
Check OWASP Top 10
- Injection: SQL, NoSQL, OS command, LDAP injection via unsanitized inputs
- Broken Auth: Hardcoded credentials, weak session management, missing MFA hooks
- Sensitive Data: Secrets in code, unencrypted PII, excessive logging of sensitive data
- XXE / Deserialization: Unsafe XML parsing, insecure deserialization
- Broken Access Control: Missing authorization checks, IDOR vulnerabilities, path traversal
- Misconfig: Debug mode enabled, default credentials, verbose error messages in production
- XSS: Unescaped user input in HTML output, innerHTML usage, dangerouslySetInnerHTML
- Insecure Dependencies: Known CVEs in dependencies (check package.json/requirements.txt)
- Insufficient Logging: Missing audit trails for auth events and data access
- SSRF: Unvalidated URLs in server-side requests
-
Check secure coding patterns
- Input validation at trust boundaries
- Output encoding for the correct context (HTML, URL, JS, CSS)
- Parameterized queries (no string concatenation in SQL)
- Proper error handling (no stack traces to users)
- Secure defaults (deny by default, least privilege)
- Secrets management (env vars or vault, not hardcoded)
-
Check dependency security
- If package.json exists:
npm auditfindings - If requirements.txt exists: known vulnerabilities
- Flag any pinned versions with known CVEs
- If package.json exists:
-
Output
- Issues grouped by severity: Critical / High / Medium / Low / Info
- Each issue: file, line, vulnerability type, code snippet, fix recommendation
- Summary: total issues by severity, overall risk assessment
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.
- 8d ago First seen · 55 lines · 8 tokens per session scan A 3ce16620def6
security-review is a command published in the GitHub repository CrashBytes/claude-role-skills (6 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 8 tokens to every session and 529 once invoked, about $0.0000 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 commands, from other repositories
review-pr
Review a pull request against an authorized reviewer's brief — answer their questions, examine their angles, run their validations, and converse until they say done. Change NO code.
review
/review [optional: specific files or PR number].
pr-description
Write a pull request description that helps reviewers: what changed, why, and how to verify, from a diff.
refactor-code
Suggest refactorings that improve readability and structure without changing behavior, ranked by payoff.
review-code
Agent review pass plus manual checklist for correctness, security, performance, and accessibility.
clean-check
Analyze code for cleanliness issues (unused code, comment quality, formatting, naming, complexity). Delegates to the code-cleanliness agent.