# Commit

> >-

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

## Install

```sh
agentstack add skill-kriscard-skills-commit
```

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

## About

# Commit

## Workflow

**Step 1 — Check for changes**

Run `git status` and `git diff` in parallel. If there's nothing to commit, stop and say so.

**Step 2 — Stage thoughtfully**

Add specific files by name rather than `git add .` or `git add -A`. Broad staging risks accidentally committing `.env` files, credentials, or build artifacts. Scan `git status` for anything that looks like a secret before staging.

**Step 3 — Write a conventional commit**

Format: `(): `

- Subject line: ≤ 72 chars, ideally ≤ 50. Imperative mood ("add X", not "added X").
- Body: **optional**. Only include if the *why* isn't obvious from the diff. 1–2 sentences max, never a bullet list.
- If the subject line is self-explanatory, omit the body entirely.

Common types: `feat`, `fix`, `chore`, `docs`, `refactor`, `test`, `style`, `perf`

```bash
# No body needed — subject is self-explanatory
git commit -m "fix(auth): handle expired token on page refresh"

# Body only when the why is non-obvious
git commit -m "$(cat <<'EOF'
feat(auth): add refresh token rotation

Single-use tokens prevent session hijacking after a token is stolen —
the old token is invalidated on first use.
EOF
)"
```

**Step 4 — Handle pre-commit hook failures**

If a hook fails (lint, typecheck, tests), the commit did NOT happen. Fix the issue, re-stage the modified files, then create a NEW commit. Never use `--amend` after a hook failure — that would modify the previous commit, potentially losing work.

**Step 5 — Ask about pushing**

Use AskUserQuestion: "Push to remote?" — don't push silently.

## Safety

- Never commit `.env`, `*.pem`, `*credentials*`, `*secret*`, `*token*` files
- Never force push without an explicit request
- Never amend commits on shared branches (`main`, `master`, `develop`)
- Never add AI/Claude attribution to commit messages

## Conventional Commit Types

| Type | When |
|------|------|
| `feat` | New capability |
| `fix` | Bug fix |
| `refactor` | Code change with no behavior change |
| `test` | Adding or fixing tests |
| `docs` | Documentation only |
| `chore` | Tooling, deps, config |
| `perf` | Performance improvement |
| `style` | Formatting, whitespace |

## Source & license

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

- **Author:** [kriscard](https://github.com/kriscard)
- **Source:** [kriscard/Skills](https://github.com/kriscard/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:** yes
- **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-kriscard-skills-commit
- Seller: https://agentstack.voostack.com/s/kriscard
- 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%.