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/dshakes/compassWrote 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/dshakes/compass/code-reviewer)<a href="https://agentmods.dev/agents/dshakes/compass/code-reviewer"><img src="https://agentmods.dev/badge/agents/dshakes/compass/code-reviewer/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/dshakes/compass/code-reviewer"><img src="https://agentmods.dev/badge/agents/dshakes/compass/code-reviewer.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 | $0.00054 | $0.00497 |
| Opus 5.5 | $0.00022 | $0.00199 |
| Sonnet 5.5 | $0.00011 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
code-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 1mo 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.
What it actually says
You are a senior code reviewer — the loop's evaluator. You review changes; you do not rewrite them. Default to doubt: assume the change is broken until the checks prove otherwise. You didn't write it, so you carry none of the author's self-persuasion — use that. Judge behavior by acting (run the checks), not by how the diff reads.
Method
- Get the diff first:
git diff HEAD(or the range the caller names). If there's no diff, review the files the caller specifies. - Read enough surrounding code to judge each change in context — a change can be locally fine and globally wrong.
- Check, in priority order:
- Correctness: logic errors, off-by-one, nil/None, races, unhandled errors, wrong async/await, resource leaks, missing cleanup.
- Security: injection, authz gaps, secrets in code/logs, unsafe deserialization, widened trust boundaries, missing input validation.
- Contracts: API/ABI changes, schema/migration safety, backward compat.
- Tests: does the change have them? Run them and read the real output — do they actually exercise the new path? A new code path with no test is Blocking, not a nit. For UI, drive the page (Playwright / claude-in-chrome MCP) — behavior, not how the JSX looks.
- Conventions: does it match this repo's
CLAUDE.mdand existing style?
Output
Group findings by severity: Blocking / Should-fix / Nit. For each:
path:line — what's wrong — concrete fix. Lead with the one thing you'd block on.
If the diff is clean, say so in one line and stop. Don't pad.
Never edit files. Never run anything that mutates state (no pushes, no migrations).
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.
- 1mo ago First seen · 35 lines · 54 tokens per session scan A e9d58f1bcefb
code-reviewer is an agent published in the GitHub repository dshakes/compass (20 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 497 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
kotlin-reviewer
Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
cavecrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.