# Commit

> Analyses all working-tree changes, groups them by intent, and creates well-formed Conventional Commits. Use when the user wants to commit changes, says "commit this", or needs staged, unstaged, and untracked work turned into structured commits.

- **Type:** Skill
- **Install:** `agentstack add skill-dnd-mapp-agent-skills-commit`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [dnd-mapp](https://agentstack.voostack.com/s/dnd-mapp)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [dnd-mapp](https://github.com/dnd-mapp)
- **Source:** https://github.com/dnd-mapp/agent-skills/tree/main/skills/commit

## Install

```sh
agentstack add skill-dnd-mapp-agent-skills-commit
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Commit

Groups all working-tree changes by intent and commits them using Conventional Commits format. Never pushes to remote.

## Workflow

1. **Collect changes** — run all three in parallel:

   - `git diff HEAD` (tracked modifications)
   - `git diff --cached` (already staged)
   - `git status --short` (untracked files)

2. **Group by intent** — identify logical groups across all changes. A single file may be split across commits when it contains changes of different intent. Use `git add -p` / patch-mode to stage exact hunks when partial file staging is needed.

3. **Draft commit messages** — for each group, produce a full message following the rules in [RULES.md](RULES.md).

4. **Validate and fix** — for each drafted message, run [validate.sh](validate.sh):

   - If exit 0: message is valid, continue.
   - If exit 1: read the `VIOLATION:` lines from stderr. Apply fixes using your own judgment, then re-run the script on the corrected message. Repeat until exit 0.

   Never present a message that has not passed validation.

5. **Present plan** — show all proposed commits with their full messages. Allow the user to edit any message before proceeding. Do not execute until the user approves the plan. A prior approval from another skill in the same chain does not carry over — this skill always requires its own explicit confirmation.

6. **Execute** — stage the exact hunks for each commit and run `git commit`. If a pre-commit hook fails on any commit, abort the entire plan immediately and report the failure.

## Defaults

| Concern            | Default                                     | Override                               |
|:-------------------|:--------------------------------------------|:---------------------------------------|
| Input scope        | Everything (staged + unstaged + untracked)  | "staged only", "this file only", etc.  |
| Untracked files    | Included                                    | "ignore untracked"                     |
| Push after commit  | Never                                       | —                                      |

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [dnd-mapp](https://github.com/dnd-mapp)
- **Source:** [dnd-mapp/agent-skills](https://github.com/dnd-mapp/agent-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-dnd-mapp-agent-skills-commit
- Seller: https://agentstack.voostack.com/s/dnd-mapp
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.