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 skills add thermiteau/maverick --skill mav-bp-code-reviewgit clone --depth 1 https://github.com/thermiteau/maverickWrote 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/skills/thermiteau/maverick/mav-bp-code-review)<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-bp-code-review"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-bp-code-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/skills/thermiteau/maverick/mav-bp-code-review"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-bp-code-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 | $0.00043 | $0.00777 |
| Opus 5 | $0.00022 | $0.00388 |
| Sonnet 5 | $0.00009 | $0.00155 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
mav-bp-code-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 10d 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.
Code Review Standards
Ensure all code changes are reviewed before merging; in Maverick the reviewer is agent-code-reviewer running in-session, backed by branch-protection gates.
Maverick's Rules
- No unreviewed merges: at least one approval on protected branches; no self-approval; stale approvals are dismissed when new commits are pushed; all CI checks must pass. Never disable or skip a check to merge faster — fix the check or the code.
- Security is out of scope for PR review — it runs as a separate pre-push gate via
do-cybersecurity-review(update mode against the diff and impact set) before the PR is opened. By review time, security findings are already surfaced and folded into the PR body. - Review scope: correctness, maintainability, test coverage, documentation. Style and formatting are the linter's job — do not comment on them. Do not review generated code (codegen, lockfiles) line by line, and do not request changes to correct-but-different approaches on personal preference.
- Verdict discipline: distinguish blocking findings from non-blocking (prefix "nit:" or "optional:"); demonstrate understanding of the change rather than rubber-stamping; approve once the code is correct, tested, and maintainable — do not hold changes hostage for perfection. AI review findings require judgement — dismiss false positives with reasoning, never silently.
- Automated checks pass before review begins — do not review code that fails lint, type checks, or tests.
PR Size
| Size | Lines changed | Review quality | Recommendation |
|---|---|---|---|
| Small | < 100 | Excellent | Ideal. Aim for this size. |
| Medium | 100 - 400 | Good | Acceptable for most feature work. |
| Large | 400 - 800 | Declining | Split if possible. Flag to reviewers. |
| Too large | > 800 | Poor | Must split. Reviewers cannot effectively review this. |
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.
- 10d ago First seen · 44 lines · 43 tokens per session scan A 06b1c6ba0ffe
mav-bp-code-review is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 777 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…