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 agentmods add skills/jeffh/claude-plugins/commit-push-prnpx skills add jeffh/claude-plugins --skill commit-push-prgit clone --depth 1 https://github.com/jeffh/claude-pluginsWhat 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 | $0.00120 | $0.00804 |
| Opus 5 | $0.00060 | $0.00402 |
| Sonnet 5 | $0.00024 | $0.00161 |
| Haiku 4.5 | $0.00012 | $0.00080 |
Grade A, and why
commit-push-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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit, Push, and Create PRs
Execute the complete workflow from uncommitted changes to open pull requests:
- Commit — Describe changes with proper commit messages
- Bookmark — Create bookmarks for the stack
- Push & PR — Push to origin and create/update pull requests
Context expectations
When invoked from /jj:commit-push-pr, the GitHub user login, remotes, working-copy status, stack log, open PRs, and any repo PR template are already in context. Do not re-fetch them. If invoked directly, gather them first:
gh api user -q '.login'
jj git remote list
jj status --no-pager
jj log --no-pager -r 'trunk()..@'
jj log -r 'trunk()..@' --no-graph -T 'separate(" | ", change_id.short(), if(description, description.first_line(), "(no description)"), bookmarks) ++ "\n"'
gh pr list --json number,title,headRefName,url,baseRefName --state open
From that context, identify: commits needing descriptions, existing bookmarks, existing PRs, and the GitHub username for the bookmark prefix.
Defaults (no prompting)
Bookmarks:
- One bookmark per commit in the stack
- Prefix
<github-username>/; name derived from the commit description (lowercase, dash-separated)
PRs:
- One PR per bookmark (stacked PRs)
- Base each PR on its parent bookmark (or trunk for the first PR)
- Published (not draft), pushed to
origin
Steps
Execute without additional confirmation prompts.
Step 1: Commit — Invoke the jj:commit skill with the appropriate revset (skip if all commits have descriptions).
Step 2: Create Bookmarks (skip if commits already have bookmarks):
jj bookmark create <prefix><name> -r <change_id>
jj bookmark track <bookmark> --remote=origin
Step 3: Push and Create PRs (skip if no bookmarks need PRs):
jj git push
gh pr create --head <bookmark> --base <base> --title "<title>" --body "<body>"
Honor PR templates
If a PR template was found in context (e.g. .github/PULL_REQUEST_TEMPLATE.md), use its sections and checkboxes verbatim as the PR body, filling each section from the actual changes. When no template exists, write a concise body and do NOT include a "Test plan" section.
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.
- 2d ago First seen · 79 lines · 120 tokens per session scan A 36352503aa1f
commit-push-pr is a skill published in the GitHub repository jeffh/claude-plugins (12 stars, last pushed 17d ago), licensed Apache-2.0. It adds 120 tokens to every session and 804 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…