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/commands/leanandmean/scramjet/mach12-pr-review)<a href="https://agentmods.dev/commands/leanandmean/scramjet/mach12-pr-review"><img src="https://agentmods.dev/badge/commands/leanandmean/scramjet/mach12-pr-review/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/commands/leanandmean/scramjet/mach12-pr-review"><img src="https://agentmods.dev/badge/commands/leanandmean/scramjet/mach12-pr-review.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 | $0.00016 | $0.02429 |
| Opus 5 | $0.00008 | $0.01215 |
| Sonnet 5 | $0.00003 | $0.00486 |
| Haiku 4.5 | $0.00002 | $0.00243 |
Grade A, and why
mach12:pr-review 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review PR
Goals
- Produce a comprehensive, evidence-grounded review of every relevant command and runtime surface without modifying the pull request.
- Publish one verified structured review whose actionable findings, strengths, scope, and stable identifiers are consumable by independent assessment.
- Hand the exact review artifact to the forced assessment step so no finding is treated as fix authority before independent classification.
Step 1: Parse input
The user's input typically contains:
- A PR number (required)
- Optional review aspects:
comments,tests,errors,types,code,simplify,completeness, orall - Additional context, focus areas, or constraints (optional)
Example inputs:
108108 error handling and test coverage108 focus on the new API endpoints108 tests errors108 all
Extract the PR number. If recognized review aspects were provided, note them as review focus in Step 3. Treat any remaining text as user context. If the input is ambiguous, ask the user to clarify.
Step 2: Check out PR branch
Ensure you are on the correct branch:
gh pr checkout <pr-number>
git pull
Step 3: Run the review
Determine the changed files and PR context before launching reviewers:
git diff --name-only origin/main...HEAD
gh pr view <pr-number> --json title,body,createdAt,updatedAt,comments,files
Collect current CI/check evidence. Identify project-provided tools relevant to the changed artifacts from repository guidance, manifests, adjacent scripts, CI configuration, and established usage; establish each tool's authority; classify its relevance as required verification, advisory analysis, or irrelevant, and its execution effect as non-mutating or mutating generation/formatting. When current CI evidence is unavailable or insufficient, safely run applicable non-mutating checks. Inspect unfamiliar scripts before use; do not install missing tools or run mutating modes without authorization. Record exact commands, outputs, and limitations. Treat failures as evidence rather than automatic root causes, warnings as bounded diagnostics rather than expanded review scope, and clean output as insufficient behavioral proof.
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 Changed · +1 lines · -1 tokens per session 0fe07b0c23a6
- 9d ago First seen · 128 lines · 17 tokens per session scan A ebec7c4a03bc
mach12:pr-review is a command published in the GitHub repository LeanAndMean/scramjet (6 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 2,429 once invoked, about $0.0001 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 commands, from other repositories
afrv
Revise the current feature worktree after code review — decide accept/revert/modify (shortcut for feature-code-revise).
aigon-feature-code-revise
A reviewing agent has just committed fixes (or notes) on this feature branch. Your job — as the implementing agent — is to read what the reviewer did, then decide how to respond: accept, revert, or modify.
feature-code-review
Review feature - code review with fixes by a different agent.
aigon-feature-code-review
Perform a code review on another agent's implementation, making targeted fixes where needed. Use a different model than the implementer for best results.
feature-code-revise
Revise the current feature worktree after code review — decide accept/revert/modify.
done
Finish a task - document, create PR or merge, close.