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-prgit 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-pr)<a href="https://agentmods.dev/skills/shreypaharia/octomux/review-pr"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/review-pr/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-pr"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 35 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00039 | $0.01414 |
| Opus 5.5 | $0.00016 | $0.00566 |
| Sonnet 5.5 | $0.00008 | $0.00283 |
| Haiku 4.5 | $0.00004 | $0.00141 |
Grade A, and why
review-pr 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 2mo 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review & Post
Review a PR using parallel specialized agents, present findings to user, then post as a pending GitHub review with inline comments.
Inputs
- PR URL or number — from user args or current branch
- Base branch — from PR metadata or user override
- Review focus — optional, e.g. "focus on correctness and test coverage"
Steps
1. Gather PR Context
gh pr view <number> # title, description, base branch
gh pr diff <number> # full diff
gh pr diff <number> --name-only # changed files
gh pr view <number> --json headRefOid -q '.headRefOid' # commit SHA for review API
Also read CLAUDE.md and any service-specific CLAUDE.md files (e.g. internal/hedging/CLAUDE.md) to understand project conventions.
2. Launch Review Agents in Parallel
Launch all agents in a single message using the Agent tool. Each agent gets the full diff and changed file list. Agents should read CLAUDE.md for project conventions.
Agents:
| Agent | Focus |
|---|---|
| Code Reviewer | Up to 5 ranked improvements (impact vs effort). Watch for project-specific conventions. |
| Security & Financial Safety | Input validation, decimal precision, race conditions, secrets, data leakage. |
| Quality & Style | Complexity, dead code, duplication, naming, logging, constructor patterns. |
| Test Quality | Coverage gaps, test patterns, anti-patterns, assertion quality. |
| Performance & Concurrency | N+1 queries, goroutine leaks, race conditions, channel misuse, lock contention. |
| Dependency & Deployment | Breaking changes, config safety, migration safety, rollback safety. |
| Simplification | Over-abstraction, unnecessary complexity, change atomicity. |
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.
- 2mo ago First seen · 159 lines · 39 tokens per session scan A 963cedeec4a5
review-pr is a skill published in the GitHub repository ShreyPaharia/octomux (25 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,414 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.
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…
video-provider-capabilities
Resolve an AI-video model's live official API schema and turn it into a durable request, continuity, cost, and review plan before any paid video call. Use for Kling, Seedance, Veo, or any other video model when selecting a model, preparing or retrying a request, assigning image/video/audio references, using first or…
hyperframes-quality
Review and gate an editable HyperFrames composition or its rendered video before delivery. Use after building, revising, diagnosing, or rendering a HyperFrames project when layout, contrast, deterministic timing, transitions, animation choreography, rendered-frame fidelity, or high-quality acceptance needs…
longform-cinematic-video
Direct a coherent cinematic video of any duration from story architecture through deterministic or generated sequences, continuity-controlled clips, editorial stitching, sound, and final seam review. Use as the default director for every new Video Studio production so scenes feel like one continuous authored film…
typescript-maintainable-design
Use when reviewing or refactoring TypeScript modules and services for excessive coupling, invalid inheritance, broad interfaces, dependency injection, unsafe assertions, mutable shared state, swallowed errors, circular imports, or maintainability and anti-pattern concerns. Apply SOLID through explicit behavior…