agentmods.dev

review-watch

review-watch is a skill for Claude Code from rlajous/claude-code-commands. It costs 108 tokens per session (2,778 once invoked), scanned A, original, MIT.

An automated pull-request reviewer that checks code and keeps reviewing until the reported problems are fixed. A pull request is a proposed code change awaiting review.

In plain words
What is it for?
Use it to monitor pull requests assigned to you, run linters and known-issue checks, request changes when problems remain, or approve clean changes with a readable summary.
Why use it?
It reduces the repeated work of checking a pull request, finding issues, and updating its review status. It also runs quick checks before spending time on a full review.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the git-workflow plugin — 21 skills, 8 agents, 2 hooks shipped together

not rated 30repo 9d ago A scan 108 tokens original MIT

Good fit Use it to monitor pull requests assigned to you, run linters and known-issue checks, request changes when problems remain, or approve clean changes with a readable summary.

Compare 6 skills from other repositories ↓
View source ↗ rlajous/claude-code-commands agents.navarrolajous.com
Install

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.

Claude Code
/plugin marketplace add rlajous/claude-code-commands
Claude Code
/plugin install git-workflow

Made for: Claude Code.

Or install git-workflow, the plugin that ships this one along with the rest of its 21 skills, 8 agents, 2 hooks.

Wrote 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.

agentmods badge for review-watch

README.md
[![agentmods](https://agentmods.dev/badge/skills/rlajous/claude-code-commands/review-watch.svg)](https://agentmods.dev/skills/rlajous/claude-code-commands/review-watch)
Your own site
<a href="https://agentmods.dev/skills/rlajous/claude-code-commands/review-watch"><img src="https://agentmods.dev/badge/skills/rlajous/claude-code-commands/review-watch.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,778 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00108 $0.02778
Opus 5 $0.00054 $0.01389
Sonnet 5 $0.00022 $0.00556
Haiku 4.5 $0.00011 $0.00278

Measured 8d ago against content hash e1f16cf0cf82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

review-watch 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 8d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/notify.sh, scripts/review-watch-tools.sh, scripts/review-watch.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/review-watch/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-runtime: follow runtime compatibility for invocation, delegation, configuration precedence, state paths, and permissions.

You are the worker side of the review-watch tool. The skill-local scripts/review-watch.sh daemon listens for PRs where your review was requested and pings you; this skill does the actual review and decides whether to request changes or approve. Goal: loop a PR until it is clean, cheaply. Follow each step in order.

Step 1: Parse Arguments and Pick Targets

First resolve {SKILL_DIR} to the absolute, physical directory containing this loaded SKILL.md. If the host cannot expose the loaded path, use PLUGIN_ROOT, then CLAUDE_PLUGIN_ROOT, only to locate skills/review-watch/SKILL.md. Verify requested resources exist. Never substitute an empty variable or silently fall back to /scripts.

  • --doctor → run bash "{SKILL_DIR}/scripts/review-watch-tools.sh" --doctor, report its output, and exit. This checks paths, dependencies, configuration, and gh authentication without querying PRs, publishing reviews, or changing GitHub state.

  • --daemon-command → run bash "{SKILL_DIR}/scripts/review-watch-tools.sh" --daemon-command, print the absolute command unchanged so the user can paste it into another terminal, and exit.

  • A PR URL or number → review just that PR.

  • --drain (or no argument) → process every queued PR in the daemon queue file ${XDG_STATE_HOME:-$HOME/.local/state}/git-workflow/review-watch-queue.jsonl (dedupe by repo#number@headRefOid; newest entry per PR wins). Remove entries as you finish them. New entries include the nullable PR-author login as author; accept older entries where that field is absent and fetch the author with the PR metadata below.

  • --comment-only → never post REQUEST_CHANGES/APPROVE, only a COMMENT review (safe mode).

For each target resolve {owner}/{repo} and PR number (parse from the URL, or use the current repo for a bare number).

Read the full file on GitHub · 181 lines

Files

What ships with it

4 files 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.

Changes

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.

  1. 8d ago First seen · 181 lines · 108 tokens per session scan A e1f16cf0cf82

Subscribe to this mod's changes

review-watch is a skill published in the GitHub repository rlajous/claude-code-commands (30 stars, last pushed 9d ago), licensed MIT. It adds 108 tokens to every session and 2,778 once invoked, about $0.0005 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.

Claude CodeCode reviewTestingagent-skillsai-agentscodexdeveloper-tools
Related

Other skills, from other repositories

cli-command

Design, implement, or review Composio CLI commands under ts/packages/cli using Effect, @effect/cli, services, output conventions, configuration and environment variables, and local vendor references. Use for CLI command UX, command wiring, service changes, or CLI source edits. Do not use for CLI E2E-only work; use…

ComposioHQ/composio · 77 tokens

gentle-ai-bench

Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.

Gentleman-Programming/gentle-ai · 49 tokens

go-testing

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

Gentleman-Programming/gentle-ai · 26 tokens

verify-implementation

A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.

sangrokjung/claude-forge · 37 tokens

semgrep-rule-variant-creator

Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.

waybarrios/opencode-power-pack · 50 tokens

ln-23-test-suite-auditor

Audits existing tests for meaningful coverage, trustworthy oracles, and maintenance value. Not for test implementation or a single delivery review.

levnikolaevich/claude-code-skills · 35 tokens