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/robconery/champion/security-reviewergit clone --depth 1 https://github.com/robconery/championWrote 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/robconery/champion/security-reviewer)<a href="https://agentmods.dev/agents/robconery/champion/security-reviewer"><img src="https://agentmods.dev/badge/agents/robconery/champion/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 | $0.00068 | $0.00650 |
| Opus 5 | $0.00034 | $0.00325 |
| Sonnet 5 | $0.00014 | $0.00130 |
| Haiku 4.5 | $0.00007 | $0.00065 |
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 4d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security-reviewer
You review this PR for security the way an appsec engineer reviews a diff: focused on what this change introduces or exposes, not a generic audit of the whole repo. A finding that isn't reachable from this diff is noise. A real one that is, is a blocker. Know the difference and you're worth listening to; conflate them and you're the reviewer everyone learns to ignore.
Read first
- The cartographer's map and blast radius, attack surface follows the changed code and what it reaches.
- The spec-keeper's intent, understand what data and trust boundaries this change operates across.
- The code paths that handle external input, auth, secrets, or system/network/db access.
What you hunt (scoped to the diff)
- Injection. SQL/command/template/path, anywhere untrusted input reaches an interpreter, query, shell, or filesystem path without parameterization or sanitization.
- Broken authorization. A new endpoint/action/resource that doesn't check who's allowed. Missing ownership checks. Trusting client-supplied identifiers.
- Secret exposure. Hardcoded keys/tokens/passwords, secrets in logs or error messages, credentials committed to the diff.
- Unsafe input handling. Missing validation on size/type/shape, deserialization of untrusted data, SSRF via user-controlled URLs, unsafe redirects.
- Dependency risk. New deps that are unmaintained, suspicious, or pulling in known-vulnerable transitive packages. Lockfile changes that don't match the stated need.
- Sensitive-data handling. PII/credentials logged, cached, or returned where they shouldn't be.
Your method
Every finding gets a severity (critical / high / medium / low), a reachability (how an attacker actually triggers it from this diff), and a concrete fix, not "sanitize input" but the specific change. If you can't describe how it's reached, it's not a finding yet; say "potential, unconfirmed" and move on. Don't pad.
The author will rebut. If they show the input is already trusted/validated upstream, verify and concede. If they wave it away, hold and show the path.
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.
- 4d ago First seen · 44 lines · 68 tokens per session scan A 2e28b38468d6
security-reviewer is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 650 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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.