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/21pounder/terminalagent/git-commitnpx skills add 21pounder/terminalAgent --skill git-commitgit clone --depth 1 https://github.com/21pounder/terminalAgentWhat 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 | $0.00033 | $0.00674 |
| Opus 5 | $0.00016 | $0.00337 |
| Sonnet 5 | $0.00007 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
git-commit 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit
Create well-structured git commits with conventional commit messages based on staged changes.
Parameters
{
"type": "object",
"properties": {
"message": {
"type": "string",
"description": "Optional commit message override"
},
"type": {
"type": "string",
"enum": ["feat", "fix", "docs", "style", "refactor", "test", "chore"],
"description": "Conventional commit type",
"default": "auto"
},
"scope": {
"type": "string",
"description": "Optional scope for the commit"
}
}
}
When to Use
- User asks to "commit" changes
- User wants to "save" their work to git
- User asks for help with commit messages
- User wants to stage and commit files
Methodology
Phase 1: Status Check
- Run
git statusto see current state - Run
git diff --stagedto see staged changes - Run
git diffto see unstaged changes - Check recent commit history for message style
Phase 2: Analysis
- Categorize Changes: Identify what changed (new files, modifications, deletions)
- Determine Type: Is this a feature, fix, refactor, etc.?
- Identify Scope: What component/module is affected?
- Summarize Purpose: What does this change accomplish?
Phase 3: Commit Creation
- Stage relevant files if not already staged
- Generate conventional commit message
- Execute the commit
- Verify success with
git status
Phase 4: Output
Report:
- What was committed
- The commit message used
- The new commit hash
Guidelines
- Follow Conventional Commits format:
type(scope): description - Keep subject line under 72 characters
- Use imperative mood ("Add feature" not "Added feature")
- Don't commit sensitive files (.env, credentials, etc.)
- Don't use --force or --amend unless explicitly requested
- Include meaningful description of WHY, not just WHAT
Examples
Example 1: Auto Commit
User Input: "Commit my changes"
Expected Behavior:
- Run
git statusandgit diffto understand changes - Analyze the nature of changes
- Generate appropriate commit message
- Stage files if needed
- Create commit and report success
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 · 100 lines · 33 tokens per session scan A 7382718fb581
git-commit is a skill published in the GitHub repository 21pounder/terminalAgent (120 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 674 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
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…