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 create-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/create-pr)<a href="https://agentmods.dev/skills/shreypaharia/octomux/create-pr"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/create-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/create-pr"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/create-pr.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 | $0.00026 | $0.00973 |
| Opus 5 | $0.00013 | $0.00487 |
| Sonnet 5 | $0.00005 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
create-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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create PR for an octomux task
Create a GitHub pull request directly using gh pr create. The octomux dashboard will auto-detect the PR within 30 seconds.
Steps
-
Identify the task branch and repo:
- Ask the user which task, or infer from context
- Get the task details (branch, repo_path, worktree):
octomux get-task <task-id> - You need
branch,repo_path, andbase_branch. The task'sbase_branchis the PR base branch. If not set, default tomain.
-
Gather context for the PR description:
Use the task's
base_branchas<base>:git -C <worktree> log <base_branch>..HEAD --oneline git -C <worktree> diff <base_branch>...HEAD --stat -
Check if branch is pushed and push if needed:
# Check if remote tracking branch exists git -C <repo_path> ls-remote --heads origin <branch>If the branch is not pushed yet, push it:
git -C <repo_path> push -u origin <branch>If already pushed, check if local is ahead and push any new commits:
git -C <worktree> status -sb # check if ahead of remote git -C <repo_path> push origin <branch> # push if ahead -
Draft the PR title and body, then confirm with the user:
Title: Conventional commit format, under 70 chars, min 10 char description:
<type>(<scope>): <description>Types:
feat,fix,chore,refactor,docs,test,perfExamples:feat(hooks): add permission prompt tracking,fix(terminal): clean up orphaned tmux sessionsBody: Must include all three sections — What, Why, and Testing:
## What <Description of what this PR does — summarize the changes> ## Why <Explanation of why this change is needed — the motivation> Resolves <link> ## Testing <How this was tested — commands run, manual verification, etc.>Linking tickets/issues:
- If the task was created from a Jira ticket, include the Jira link
- If the task was created from a GitHub issue, include:
Resolves #<issue-number> - Infer the ticket/issue from the branch name. Jira-style keys match
[A-Z][A-Z0-9]+-\d+(e.g.,feat/PROJ-123-...->PROJ-123); numeric branches resolve to GitHub issues (fix/42-...->#42). - If no ticket/issue is associated, omit the
Resolvesline
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 · 106 lines · 26 tokens per session scan A 82d52b5374da
create-pr is a skill published in the GitHub repository ShreyPaharia/octomux (22 stars, last pushed 11d ago), licensed MIT. It adds 26 tokens to every session and 973 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 2026-08-30.
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…