AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Commit

skill-kriscard-skills-commit · by kriscard

>-

No reviews yet
0 installs
37 views
0.0% view→install

Install

$ agentstack add skill-kriscard-skills-commit

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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 Used
  • 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-kriscard-skills-commit)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Commit? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

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

# 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.

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

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.