Install
$ agentstack add skill-dnd-mapp-agent-skills-commit ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Commit
Groups all working-tree changes by intent and commits them using Conventional Commits format. Never pushes to remote.
Workflow
- Collect changes — run all three in parallel:
git diff HEAD(tracked modifications)git diff --cached(already staged)git status --short(untracked files)
- 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.
- Draft commit messages — for each group, produce a full message following the rules in [RULES.md](RULES.md).
- 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.
- 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.
- 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
- Source: dnd-mapp/agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.