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 ddtcorex/maestro-skills --skill review-in-worktreegit clone --depth 1 https://github.com/ddtcorex/maestro-skillsWrote 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/ddtcorex/maestro-skills/review-in-worktree)<a href="https://agentmods.dev/skills/ddtcorex/maestro-skills/review-in-worktree"><img src="https://agentmods.dev/badge/skills/ddtcorex/maestro-skills/review-in-worktree/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/ddtcorex/maestro-skills/review-in-worktree"><img src="https://agentmods.dev/badge/skills/ddtcorex/maestro-skills/review-in-worktree.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 | $0.00065 | $0.00738 |
| Opus 5 | $0.00032 | $0.00369 |
| Sonnet 5 | $0.00013 | $0.00148 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
review-in-worktree 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 yesterday.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing in Detached Worktrees
Why Govard Commands Fail Here
govard tool … resolves the project from a .govard.yml found upward from
the current directory and dispatches into that project's running app
container. A bare review worktree (created with git worktree add for a
merge request) carries neither the config nor a running environment, so
project-routed Govard commands fail by design.
Option 1 — Point at the Owning Checkout (preferred, read-only intent)
If the branch under review belongs to a Govard project that is already up
(govard up ran in the real checkout), resolve the environment from there:
GOVARD_PROJECT_DIR=/path/to/real-checkout govard status
Verify with govard status before anything else. Treat this as read-only
context for your review; never run mutations (migrations, cache flushes,
indexers) against the owning project's database because a review asked for it.
Option 2 — Bootstrap a Throwaway Config
Only when the review must execute code and no owning environment exists:
govard init # detects the framework, writes .govard.yml in the worktree
govard up # brings up an isolated stack named after this directory
Clean up afterwards so review trees do not leak containers:
govard down && git worktree remove ../<worktree>
Option 3 — Static Analysis Only (most MR reviews)
Most automated reviews only need the diff, repository history, and the domain
skills (magento2-code-review, magento2-linter guidance). Prefer this
when the reviewer has no container rights or the MR is not meant to run.
Container-free analysis is available for this case. govard audit run no longer
needs a container when the check itself does not:
# Works on a bare worktree: no stack, no .govard.yml, no Docker.
govard audit run --checks integrity --scope project --format json
# A module inside a project, or a detached review tree:
govard audit run --checks integrity --mode module_in_project --format json
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.
- yesterday Changed · +18 lines edc31b33761f
- 12d ago First seen · 62 lines · 65 tokens per session scan A 69300a53eea6
review-in-worktree is a skill published in the GitHub repository ddtcorex/maestro-skills (4 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 738 once invoked, about $0.0003 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 skills, from other repositories
pr-review
Comprehensive code review for pull requests using parallel multi-agent analysis. Audits CLAUDE.md compliance, checks for bugs, analyzes git history, reviews comments, and filters by confidence score. Use when reviewing a GitHub PR, mentions "code review", "review this PR", or "/code-review".
swarm-pi-review
Review a Git working tree or branch with read-only Pi workers. Use standard for bugs, security, regressions, and missing tests; use lean for diff-bound simplification, deletion, reuse, YAGNI, or native replacements. Route one question to ask and broader risk analysis to orchestrate.
gh-pr-review-loop
Statically review one user-specified GitHub pull request and publish one review. Do not use for general review drafting, local code review, or multi-PR work.
dev-git-workflow
Use for non-trivial Git state such as branch strategy, worktrees, merge/rebase decisions, conflicts, reviewer-facing PR preparation, tags, and release notes. Do not trigger for a routine commit, push, or PR that needs no strategy decision.
dev-pr-review
Use for reviewing a branch, pull request, local diff, or implementation plan before merge, including alignment of existing PR metadata with the diff and delivery state.
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.