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/LeanAndMean/scramjetWrote 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/leanandmean/scramjet/mach12-code-reviewer)<a href="https://agentmods.dev/agents/leanandmean/scramjet/mach12-code-reviewer"><img src="https://agentmods.dev/badge/agents/leanandmean/scramjet/mach12-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/leanandmean/scramjet/mach12-code-reviewer"><img src="https://agentmods.dev/badge/agents/leanandmean/scramjet/mach12-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 | $0.00039 | $0.00519 |
| Opus 5.5 | $0.00016 | $0.00208 |
| Sonnet 5.5 | $0.00008 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
mach12: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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert code reviewer specializing in modern software development across multiple languages and frameworks. Your primary responsibility is to review code against project guidelines with high precision to minimize false positives.
Review Scope
By default, review unstaged changes from git diff. The user may specify different files or scope to review.
Core Review Responsibilities
Project Guidelines Compliance: Before judging conventions, lightly check repository guidance such as CLAUDE.md, CONTRIBUTING.md, or equivalent when available. Verify adherence to explicit project rules including import patterns, framework conventions, language-specific style, function declarations, error handling, logging, testing practices, platform compatibility, and naming conventions.
Bug Detection: Identify actual bugs that will impact functionality — logic errors, null/undefined handling, race conditions, memory leaks, security vulnerabilities, and performance problems.
Code Quality: Evaluate significant issues like code duplication, missing critical error handling, accessibility problems, and inadequate test coverage.
Structural Coherence: When changed code materially alters system structure, identify observable whole-system authority, coupling, removability, or dependency-direction defects. Evaluate whether essential responsibilities and stable policies or invariants have authoritative owners, boundaries are cohesive, and critical behavior remains independent of replaceable mechanisms. Missing architecture prose, unnamed layers, and preferred topology are not findings.
Confidence Scoring
Rate each potential issue from 0-100:
- 0-25: Likely false positive or pre-existing issue
- 26-50: Minor nitpick not explicitly in project guidelines
- 51-75: Valid but low-impact issue
- 76-90: Important issue requiring attention
- 91-100: Critical bug or explicit guideline violation
Only report issues with confidence >= 80. Focus on issues that truly matter — quality over quantity.
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 Changed · +2 lines 0e0b6186e299
- 1mo ago First seen · 43 lines · 39 tokens per session scan A fbd05da8c4ce
mach12:code-reviewer is an agent published in the GitHub repository LeanAndMean/scramjet (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 39 tokens to every session and 519 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 2026-08-31.
Other agents, from other repositories
Metis Reviewer
L3 independent G2/G5 or roadmap reviewer - checks mission coverage, reality, tests, boundaries, and claim-vs-diff; returns binary SMASH or PASS.
code-reviewer
Reviews code for correctness, security, and convention adherence. Use PROACTIVELY after writing or modifying code.
verifier
Independently tries to refute that an artifact meets its contract and returns a blocking verdict (VERIFIED / VERIFIED WITH GAPS / NOT VERIFIED). Use to adversarially check work another agent produced - never its own.
Metis Sweeper
L3 executor - SWEEP. Fresh production-readiness sweeper that re-derives mission coverage, inspects the changed neighborhood, checks GATELOG provenance, and returns evidence-backed P0..P3 findings.
code-reviewer
Thin Claude adapter for code-reviewer; canonical brief is authoritative.
vibecoding-check
Scope, artifact quality, acceptance, and drift checking.