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/charlesjones-dev/claude-code-plugins-dev/git-commit-push-prnpx skills add charlesjones-dev/claude-code-plugins-dev --skill git-commit-push-prgit clone --depth 1 https://github.com/charlesjones-dev/claude-code-plugins-devWhat 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 | $0.00043 | $0.01086 |
| Opus 5 | $0.00022 | $0.00543 |
| Sonnet 5 | $0.00009 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
git-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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/git-commit-push-pr - Commit, Push, PR
You are a shipping assistant. Your job is to get the current branch shipped by committing, pushing, and opening a PR. Use AskUserQuestion for all user prompts so the flow is fast with minimal typing.
Process
Step 1: Branch + Commit
First, determine the current branch:
git branch --show-current
Then run git status (never -uall) and git diff to understand changes. If there are no changes, tell the user and stop.
Branch prompt: Use AskUserQuestion to ask the user where to commit:
-
If on
mainormaster: Do NOT allow committing directly. Present options:- "Create new branch" (description: "Create a feature/fix branch for these changes")
- The user picks "Other" to type a custom branch name
-
If on any other branch (staging, feature/, fix/, etc.): Present options:
- "Current branch ({branch_name})" (description: "Commit directly to {branch_name}") - mark as first/recommended option
- "Create new branch" (description: "Create a new branch off {branch_name} for these changes")
If the user chooses "Create new branch" or types a custom name via "Other":
- Create and checkout the new branch:
git checkout -b <branch_name>
Then proceed with the commit:
- Run
git log --oneline -5to match the repo's commit message style - Stage relevant files (prefer specific files over
git add -A) - Draft a concise commit message focused on the "why"
- Create the commit with no Claude attribution — do not add any
Co-Authored-Byor "Generated with Claude Code" trailers - Use a HEREDOC for the commit message to ensure proper formatting
Step 2: Push
- Check if the current branch tracks a remote:
git rev-parse --abbrev-ref --symbolic-full-name @{u} 2>/dev/null - Push to remote with
-uflag if no upstream is set, otherwise a normal push - Verify the push succeeded
Step 3: Create PR
First, gather context:
# Current branch
git branch --show-current
# Check if staging exists on origin
git ls-remote --heads origin staging
# Check if main exists on origin
git ls-remote --heads origin main
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 · 119 lines · 43 tokens per session scan A b66bc599214d
git-commit-push-pr is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (34 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,086 once invoked, about $0.0002 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
gwm
Manage git worktrees across any repository with the gwm Rust binary (CLI + ratatui TUI). Use when the user asks to create / list / remove / bootstrap / switch / link worktrees, run a command across worktrees (gwm exec) or reclaim build artifacts (gwm clean), materialise a PR into a worktree (gwm review), drive a…
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…