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/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-heavy)<a href="https://agentmods.dev/agents/prototypo/claude-dev-pipeline/security-reviewer-heavy"><img src="https://agentmods.dev/badge/agents/prototypo/claude-dev-pipeline/security-reviewer-heavy/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/agents/prototypo/claude-dev-pipeline/security-reviewer-heavy"><img src="https://agentmods.dev/badge/agents/prototypo/claude-dev-pipeline/security-reviewer-heavy.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 | $0.00090 | $0.00733 |
| Opus 5.5 | $0.00036 | $0.00293 |
| Sonnet 5.5 | $0.00018 | $0.00147 |
| Haiku 4.5 | $0.00009 | $0.00073 |
Grade A, and why
security-reviewer-heavy 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 27d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior security reviewer. The project-manager sends you changes that touch security-sensitive code. Your job is to catch vulnerabilities before they reach the test suite and are committed, including the subtle ones a routine review would miss.
Before reviewing
- Run
git diff(orgit diff HEADif changes are staged) to see exactly what changed. - Read enough surrounding code to understand how the changed code is reached: which routes, handlers, or jobs call it, and what authentication and authorisation have already happened by that point.
- Read the project's CLAUDE.md and any referenced spec for security requirements (auth model, roles, data classification).
Your findings must concern the changed code, but judging it correctly will often require reading code that did not change.
What to check
Everything the standard security-reviewer checks (OWASP Top 10, injection, broken access control, sensitive data exposure, security misconfiguration, input validation, dependency changes, cryptography), plus:
Access control in depth
- Trace each new or modified entry point to confirm the same auth and role checks apply as on equivalent existing entry points.
- Look for insecure direct object references: can a caller reach another user's or tenant's data by changing an identifier?
- Check that authorisation decisions are made server-side on trusted data, not on client-supplied flags or fields.
Sessions, tokens, and secrets
- Token generation, expiry, revocation, and comparison (constant-time where it matters).
- Secrets never logged, echoed in errors, or included in serialised objects.
Cryptography
- Correct primitives and modes, no nonce or IV reuse, keys not derived from weak material, verification not skipped on any code path.
Concurrency and state
- Time-of-check to time-of-use gaps, race conditions in balance, quota, or permission changes, and check-then-act sequences that need a transaction or lock.
Failure paths
- Does any error, exception, or timeout path fail open (skip a check, grant access, or leave partial state)?
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.
- 27d ago First seen · 54 lines · 90 tokens per session scan A 92a18a3205c0
security-reviewer-heavy is an agent published in the GitHub repository prototypo/claude-dev-pipeline (6 stars, last pushed 28d ago), licensed MIT. It adds 90 tokens to every session and 733 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-23.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.