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 galihcitta/code-review-agents --skill reviewgit clone --depth 1 https://github.com/galihcitta/code-review-agentsWrote 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/galihcitta/code-review-agents/review)<a href="https://agentmods.dev/skills/galihcitta/code-review-agents/review"><img src="https://agentmods.dev/badge/skills/galihcitta/code-review-agents/review.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.03589 |
| Opus 5 | $0.00007 | $0.01795 |
| Sonnet 5 | $0.00003 | $0.00718 |
| Haiku 4.5 | $0.00001 | $0.00359 |
Grade A, and why
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 7d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the lead of a PR review agent team. You will create a team of 5 teammates, each running in its own tmux pane so the user can watch all reviewers work simultaneously.
Model strategy: Use the configured reviewer model for T1-T4 (focused review tasks with narrow context). Use the configured oracle model for T5 Oracle (synthesis, validation, scoring). You (the lead) run on whatever model the user started with.
Phase 1: Parse Arguments and Load Config
1a. Parse Arguments
Parse: $ARGUMENTS
Single-repo format: <repo-path> <branch-name> [--spec <epic-name>]
Multi-repo format: <repo1>:<branch1> [<repo2>:<branch2> ...] [--spec <epic-name>]
Detection: if any argument contains : (and is not --spec), treat as multi-repo format.
Extract:
- REPOS[] — array of {path, branch} objects
- Single-repo: one entry from positional args
- Multi-repo: one entry per
path:branchpair
- SPEC_NAME (optional, after --spec)
If no repos detected, ask the user.
Examples:
# Single repo
/code-review-agents:review /path/to/my-service feature/user-auth --spec user-auth
# Multi repo
/code-review-agents:review /path/to/api:feature/payments /path/to/gateway:feature/payments --spec payments
1b. Load Configuration
Derive PLUGIN_ROOT: resolve the absolute path two levels up from this SKILL.md file's location (i.e., the root of the code-review-agents plugin directory).
Config resolution order (each layer shallow-merges; arrays replace):
- DEFAULTS — built-in values:
base_branches: [develop, main, master] remote: origin language: auto references_dir: null scoring_file: null output_dir: ~/.claude/pr-review reviewer_model: sonnet oracle_model: opus specs_dir: null reviewer_timeout: 600 oracle_timeout: 900 - PLUGIN_CONFIG — read
{PLUGIN_ROOT}/config.yamlif it exists - PROJECT_CONFIG — read
{REPOS[0].path}/.claude/pr-review.yamlif it exists (first repo) - CLI_FLAGS — any explicit flags from $ARGUMENTS override everything
What ships with it
5 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.
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.
- 7d ago First seen · 289 lines · 14 tokens per session scan A 34a2cb7b57b9
review is a skill published in the GitHub repository galihcitta/code-review-agents (2 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 3,589 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 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…