review-orchestrator

review-orchestrator is a skill for Claude Code from ShreyPaharia/octomux. It costs 41 tokens per session (2,217 once invoked), scanned A, original, MIT.

A workflow for reviewing pull requests with the octomux review command-line tool. It creates a structured walkthrough and draft inline comments for a human to check.

In plain words
What is it for?
Starting a review task, producing draft pull-request comments, checking earlier review output, and completing the review through octomux.
Why use it?
It keeps review comments from being published automatically, reducing the risk of sending an unchecked comment to GitHub.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the octomux plugin — 20 skills, 1 agent shipped together

Good fit Starting a review task, producing draft pull-request comments, checking earlier review output, and completing the review through octomux.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shreypaharia/octomux/review-orchestrator
Install

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.

Any agent
npx skills add ShreyPaharia/octomux --skill review-orchestrator
Clone the repo
git clone --depth 1 https://github.com/ShreyPaharia/octomux

Made for: Claude Code.

Or install octomux, the plugin that ships this one along with the rest of its 20 skills, 1 agent.

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-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/shreypaharia/octomux/review-orchestrator/github.svg)](https://agentmods.dev/skills/shreypaharia/octomux/review-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/shreypaharia/octomux/review-orchestrator"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/review-orchestrator/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.

agentmods 80×15 button for review-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/shreypaharia/octomux/review-orchestrator"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/review-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,217 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00041 $0.02217
Opus 5 $0.00020 $0.01108
Sonnet 5 $0.00008 $0.00443
Haiku 4.5 $0.00004 $0.00222

Measured 12d ago against content hash c6056dd63bb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-orchestrator 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 12d 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.

plugin/skills/review-orchestrator/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Orchestrator

You are reviewing a pull request from inside an octomux worktree. Octomux owns the publishing step; your job is to produce draft output that a human will triage before it lands on GitHub.

Hard rules

  • DO use octomux review <subcommand> for every piece of output (walkthrough, drafts, check-previous, complete).
  • DO NOT call gh api, gh pr review, gh pr comment, gh issue comment, or any other GitHub-writing command.
  • DO NOT post to chat. Everything you produce goes through the CLI.
  • DO NOT edit files. Reviews are read-only.

Phase 1: Bootstrap

Your task id: every octomux review command below takes --task <task_id>. The <task_id> is the Review task id: value printed at the top of your prompt — your own review task. Do NOT use any other id you see in the prompt (e.g. a "Source task (context only)" id or a PR's source task); passing the wrong id writes the run and comments under a task the dashboard never reads, so the review shows up empty.

Run octomux review start --task <task_id> first. It prints JSON containing:

  • review_run_id — pass this to subsequent commands implicitly (the CLI infers from the running run; you don't need to repeat it).
  • pr_head_sha, base_sha, pr_url, worktree.
  • last_reviewed_sha — head sha of the last completed review run (null on first review). This is the delta base for a re-review; never guess it from git.
  • previous_review — null on first review; otherwise contains the previously published review's head_sha, verdict, walkthrough, and comments[] (id, file_path, line, side, body, severity, bucket, kind).
  • learnings — array of { id, why } strings the human has told you in the past. Apply them ruthlessly: do NOT re-flag anything a learning says is intentional.
  • instruction_files — array of { path, scope, size }. Read these next.
  • carry_forward — drafts/accepted comments from prior runs that survived auto-staleness; consider them while you draft (do not duplicate).

Read the full file on GitHub · 210 lines

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. 12d ago First seen · 210 lines · 41 tokens per session scan A c6056dd63bb3

Subscribe to this mod's changes

review-orchestrator is a skill published in the GitHub repository ShreyPaharia/octomux (22 stars, last pushed 11d ago), licensed MIT. It adds 41 tokens to every session and 2,217 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.