Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add thermiteau/maverick/plugin install 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-remote-code-review)<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-bp-remote-code-review"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-bp-remote-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-remote-code-review"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-bp-remote-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 | $0.00083 | $0.01251 |
| Opus 5 | $0.00042 | $0.00626 |
| Sonnet 5 | $0.00017 | $0.00250 |
| Haiku 4.5 | $0.00008 | $0.00125 |
Grade A, and why
mav-bp-remote-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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remote Code Review (Optional CI Gate)
Maverick runs PR code review locally by default — agent-code-reviewer is dispatched as a subagent during do-issue-solo Phase 9 (and equivalent in do-issue-guided / do-epic) and produces the binary PASS/FAIL verdict that the auto-merge path trusts. The local agent's verdict is the gate.
This skill describes an optional GitHub Actions workflow that re-runs the same agent in CI. Adding it to a project gives you an independent CI-side check on every PR, at the cost of paid Anthropic API tokens for each run and a bit of setup. It is not required, and do-init does not scaffold it — projects that want it adopt it deliberately.
When to Add the Remote Gate
The remote workflow is worth the setup and the per-PR API spend when one or more of these apply:
- Multi-machine / fleet operation. When
do-epicdispatches a wave of stories across worktrees in parallel, a single worktree's local review can fail to fire (process crash, network blip, agent skipped). A CI gate guarantees the merge cannot complete without a review having run somewhere, regardless of what happened on any one worker. - Untrusted dev environments. If contributors run their own local sessions in environments you don't control (shared infra, varied tooling, contractors), a CI-side review is the only review you can rely on.
- Audit / regulatory needs. Some teams need a verifiable status check on every PR — a record outside any one developer's session that an AI reviewer was invoked and what verdict it returned. The workflow's
Code Reviewcheck on the PR is that record.
For solo / single-machine use, the local agent runs in the same session that opens the PR. Skipping it requires deliberately ignoring its output. A CI re-run mostly duplicates work the local agent already did — and bills against ANTHROPIC_API_KEY for the privilege.
The Contract (When You Adopt It)
A repository that opts in is compliant iff it ships a GitHub Actions workflow that:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 67 lines · 83 tokens per session scan A 629f7d9606ad
mav-bp-remote-code-review is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,251 once invoked, about $0.0004 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
gemini-review
Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration.
squid-implement-night
Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan.
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.
pr-babysitter
Monitors or repairs an open GitHub PR: CI failures, conflicts, review threads, and merge readiness, reporting state changes. Use when asked to "watch this PR", "fix CI", "resolve conflicts", or "address review comments". For PR metadata use pr-creator; for npm release PRs use autoship.
aster-review-ci
Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.
argot-setup-ci
Wire argot into a repository's GitHub Actions as a non-blocking configured check on every pull request — a job summary plus code-scanning annotations. Use when the user wants argot "in CI", "on PRs", "as a GitHub Action", or asks to "set up argot CI". Distinct from argot-setup (local checking) and argot-review-pr…