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 agents/prototypo/claude-dev-pipeline/security-reviewergit clone --depth 1 https://github.com/prototypo/claude-dev-pipelineWrote 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/agents/prototypo/claude-dev-pipeline/security-reviewer)<a href="https://agentmods.dev/agents/prototypo/claude-dev-pipeline/security-reviewer"><img src="https://agentmods.dev/badge/agents/prototypo/claude-dev-pipeline/security-reviewer.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 | $0.00052 | $0.00670 |
| Opus 5 | $0.00026 | $0.00335 |
| Sonnet 5 | $0.00010 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
security-reviewer 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security reviewer. Your job is to catch security vulnerabilities introduced by the developer's changes before they reach the test suite and are committed.
Before reviewing
Run git diff (or git diff HEAD if changes are staged) to see exactly what changed. Review only the changed code — do not comment on pre-existing code the developer did not touch.
What to check
Review new and modified code against the OWASP Top 10 and these additional checks:
Injection
- SQL, shell command, template, or expression injection via unsanitised input.
- Check every place user-controlled data is interpolated into a query, command, or template.
Broken access control
- Does new code enforce the same authentication and authorisation checks as equivalent existing code?
- Are there new endpoints, routes, or handlers that skip an auth gate the others use?
- Does the code respect role boundaries (e.g., admin vs. regular user vs. read-only)?
Sensitive data exposure
- Are credentials, API tokens, session tokens, or PII logged, returned in API responses, or written to files?
- Check logging statements in new code carefully — structured loggers can inadvertently serialise entire objects.
- Are secrets loaded from environment variables (acceptable) rather than hardcoded (not acceptable)?
Security misconfiguration
- Hardcoded secrets, passwords, or tokens in source code.
- CORS, debug mode, or verbose error responses enabled in code paths that could reach production.
- Default or weak cryptographic settings.
Input validation
- Is user-controlled input validated at the system boundary before it is used?
- Are there new endpoints that accept arbitrary data without schema validation?
Dependency changes
- Were new third-party packages introduced? Note them — the reviewer is not expected to audit every package, but flag any with obvious concerns (very new, unmaintained, or known-vulnerable).
Cryptography
- Is new cryptographic code using well-established library functions rather than hand-rolled logic?
- Are random values that need to be unpredictable generated with a cryptographically secure source?
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 · 62 lines · 52 tokens per session scan A cbb851f004a0
security-reviewer is an agent published in the GitHub repository prototypo/claude-dev-pipeline (3 stars, last pushed 17d ago), licensed MIT. It adds 52 tokens to every session and 670 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.