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 ShreyPaharia/octomux --skill review-deepgit clone --depth 1 https://github.com/ShreyPaharia/octomuxWrote 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/shreypaharia/octomux/review-deep)<a href="https://agentmods.dev/skills/shreypaharia/octomux/review-deep"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/review-deep/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/shreypaharia/octomux/review-deep"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/review-deep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.02917 |
| Opus 5.5 | $0.00021 | $0.01167 |
| Sonnet 5.5 | $0.00010 | $0.00583 |
| Haiku 4.5 | $0.00005 | $0.00292 |
Grade A, and why
review-deep 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 1mo 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Deep
You are the deep-review agent for an automated PR review running inside an octomux worktree. The walkthrough agent has already run and ingested a structured walkthrough. Your job is to use that walkthrough as orientation, run the deep-review findings engine (a workflow), draft the surviving inline comments, and complete the review run.
Hard rules
- DO use
octomux review <subcommand>for every piece of output (check-previous, draft-comment, 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.
- DO NOT re-derive the walkthrough — consume the one returned by
start.
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,base_branch,pr_url,worktree.last_reviewed_sha— head sha of the last completed review run (null on first review). The delta base for a re-review; never guess it from git.walkthrough— the structured walkthrough the walkthrough agent already ingested. Do NOT re-derive it; use it directly as orientation.playbook—{ index: <INDEX.md body>, files: [{ slug, body }] }. Project-level review orientation. Pass it to the engine; skip any entry whose cited files/symbols no longer exist (a light stale guard).learnings— array of{ id, why }the human has told you in the past. Apply them ruthlessly: do NOT re-flag anything a learning says is intentional.previous_review— null on first review; otherwise the previously published review's head_sha, verdict, walkthrough, andcomments[](id, file_path, line, side, body, severity, bucket, kind).carry_forward— drafts/accepted comments from prior runs that survived auto-staleness; consider them while you draft (do not duplicate).
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.
- 1mo ago First seen · 189 lines · 52 tokens per session scan A 5e9f4b13ed33
review-deep is a skill published in the GitHub repository ShreyPaharia/octomux (25 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 2,917 once invoked, about $0.0002 per session on Opus 5.5. 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
supermux-core
Use when building an app, script, bot or service in TypeScript that drives Claude Code, Codex, Cursor, OpenCode, Grok Build or Antigravity through the @supermux/core library.
output-eval-error-analysis
Systematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval project, after significant pipeline changes, or when production quality drops.
skill
Skill "skill" from wavyrai/tmux-ide, covering tmux-ide — claude code skill, when to use, the agent contract, coordinating with other agents and fleet control from the cli.
coding-standards
Detects code smells, anti-patterns, and readability issues. Use when implementing features, reviewing code, or refactoring.
install-jazz-github-action
Set up Jazz as a GitHub Action for automated PR code review and on-demand /jazz PR assistance. Use when the user asks to add Jazz to CI, create a GitHub Action workflow, set up PR review automation, enable /jazz commands on PRs, or integrate Jazz with GitHub.
architecture-audit
Systematic architecture audit and refactoring methodology for Rust + TypeScript codebases. Use when performing refactoring, cleanup, unification, code review, dead code removal, module reorganization, or tech debt elimination. Ensures no naming confusion, semantic overloading, hidden defaults, duplicate logic, or…