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 ship-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/ship-pr)<a href="https://agentmods.dev/skills/shreypaharia/octomux/ship-pr"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/ship-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/ship-pr"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/ship-pr.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00070 | $0.00859 |
| Opus 5 | $0.00035 | $0.00430 |
| Sonnet 5 | $0.00014 | $0.00172 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
ship-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 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship a PR end-to-end (review-gated, self-monitoring)
Runs the whole path from a task branch to a green, monitored PR: walkthrough → review gate → PR → monitor & fix → refresh walkthrough.
Use create-pr instead when you just want to open a PR with no review gate or
monitoring. This skill is the autonomous version.
Steps
-
Get the task context.
octomux get-task <task-id>→branch,repo_path,base_branch(defaultmain), and the worktree path. The branch must already have commits. -
Write the walkthrough (its own step, NOT the PR body). Produce a reviewer-facing walkthrough of the change and write it to
<worktree>/.octomux/pr-walkthrough.md. Keep it structured:- Intent — what this change accomplishes and why.
- Change tour — the meaningful files/areas grouped by theme, one line each on what changed and why (skip trivial/mechanical files).
- Risk & blast radius — what could break, what to watch.
- Testing — what was run / added and the evidence it passes.
This artifact is deliberately separate from the PR description. Surfacing it in the dashboard PR info tab is a follow-up octomux code task; for now it just lives as this file so the review and monitoring steps can lean on it.
-
Review gate — do NOT open the PR until this is green. Attach a reviewer agent to the SAME task (see the
add-agentskill) and have it run/code-reviewover the branch diff (working tree /base_branch..HEAD). Also make sure the repo's own checks pass locally first (tests / lint / build perrepo_configs). Then:- Address every actionable finding with fixes committed to the branch.
- Re-run the review until it comes back clean.
- Only proceed once review is clean AND local checks are green.
-
Open the PR. Follow the
create-prskill exactly (walkthrough of What / Why / Testing in the PR body, user confirmation,gh pr create). The PR body is the normal create-pr body — the.octomux/pr-walkthrough.mdartifact stays separate.
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.
- 12d ago First seen · 65 lines · 70 tokens per session scan A 3155e330ebc8
ship-pr is a skill published in the GitHub repository ShreyPaharia/octomux (22 stars, last pushed 10d ago), licensed MIT. It adds 70 tokens to every session and 859 once invoked, about $0.0003 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.
Other skills, from other repositories
code-review
AI code review for PR or local changes.
change-review
Validate CRM/PM changes before PR.
code-review-quality
Conduct context-driven code reviews focusing on quality, testability, and maintainability. Use when reviewing code, providing feedback, or establishing review practices.
agentplane-task-closure-recovery
Use when Agentplane task completion, direct finish, branchpr integration, hosted-close, close-tail PRs, PR metadata, dirty task artifacts, or remote branch divergence need diagnosis or recovery.
reviewing-code-quality
Reviews a diff or module for slipping standards, favoring deletion over rearranging, and ends in one honest verdict. Use when a change risks oversized files, needless layers, feature logic leaking into shared code, or clever indirection. Do not use for a trivial obvious edit, or for a check that is only about whether…
audit-code
Run a two-pass, multidisciplinary code audit led by a tie-breaker lead, combining security, performance, UX, DX, and edge-case analysis into one prioritized report with concrete fixes. Use when the user asks to audit code, perform a deep review, stress-test a codebase, or produce a risk-ranked remediation plan across…