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/shopwarelabs/ai-coding-tools/commit-message-writingnpx skills add shopwareLabs/ai-coding-tools --skill commit-message-writinggit clone --depth 1 https://github.com/shopwareLabs/ai-coding-toolsWhat 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 | $0.00160 | $0.01310 |
| Opus 5 | $0.00080 | $0.00655 |
| Sonnet 5 | $0.00032 | $0.00262 |
| Haiku 4.5 | $0.00016 | $0.00131 |
Grade A, and why
commit-message-writing 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 yesterday.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Message Generation
Generate conventional commit messages for Shopware core. Squash merge titles (title-only) for trunk merges and full commit messages (title + body) for branch work.
Output scope: Presents formatted commit message text. Does not create commits, write files, or modify git state.
Phase 1 — Detect Mode and Gather Context
Determine what we're generating — a squash merge title or a branch commit message.
- Parse user input:
- Commit ref provided (SHA, HEAD, HEAD~3, etc.) -> branch mode, resolve to SHA
- Branch ref, "squash", "current branch", or "merge commit" -> squash mode
- Nothing specific -> branch mode, use HEAD
- Gather the diff:
- Branch mode:
git show <sha> --name-status --format=''andgit show <sha> --format='' - Squash mode: Continue to step 3
- Branch mode:
- Squash mode only — detect base branch: Load
references/branch-and-pr-detection.mdand execute Steps 1-4. Route ascommit-message-writing. - Squash mode only — get branch diff:
git diff <base>...HEAD --statandgit diff <base>...HEADgit log <base>..HEAD --oneline
Phase 2 — Analyze and Generate
Type Detection
Analyze the diff to determine the commit type. Priority-ordered decision tree:
- Revert commit? ->
revert - Only docs (*.md, docblocks, inline comments)? ->
docs - Only formatting/whitespace changes? ->
style - Only test files? ->
test - Only build/dependency files (composer.json, package.json, Dockerfile)? ->
build - Only CI config (.github/workflows/, .gitlab-ci.yml)? ->
ci - Adds new user-facing functionality? ->
feat - Fixes broken behavior? ->
fix - Performance improvement (caching, query optimization, reduced allocations)? ->
perf - Code restructuring without behavior change? ->
refactor - Otherwise ->
chore
When ambiguous (e.g., both feat and fix equally present), ask the user:
AskUserQuestion(
question="This branch contains both new functionality and bug fixes. Which type best represents the primary purpose?",
options=[
{label: "feat", description: "The main goal is new functionality"},
{label: "fix", description: "The main goal is correcting broken behavior"}
]
)
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 131 lines · 160 tokens per session scan A fdb18d4443d5
commit-message-writing is a skill published in the GitHub repository shopwareLabs/ai-coding-tools (42 stars, last pushed 4d ago), licensed MIT. It adds 160 tokens to every session and 1,310 once invoked, about $0.0008 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
audit-instructions
Audit locally-owned Claude Code instruction surfaces, including CLAUDE.md, .claude/rules, skill bodies, agent definitions, hook instruction text and output styles, for instructions current models no longer need (prior-model workarounds, over-prescriptive scaffolding, stale examples), instructions that misstate Claude…
batch-simplify
Batch-run simplification across changed files, or across an entire repository, grouped by ecosystem and dependency order. Use when: 'batch simplify', 'simplify recent changes', 'simplify everything', 'forgot to run simplify', 'catch up on simplify', 'simplify my branch changes', 'simplify the whole repo', 'simplify…
audit-permission-state
Report the Claude Code permission state actually in effect. Discovers every settings scope (managed policy, user-global, project, local, and the pre-v2.1.211 start-directory copy), merges them into the effective allow/ask/deny set with each rule's source and precedence mechanic named, and classifies which allow rules…
lanes
Start, restart, stop, and check loop lanes as named background Claude Code sessions seeded from canonical prompt files, the scripted replacement for the manual morning refresh (cancel loop, clear, re-paste the canonical prompt) across N lanes on a machine. start/restart first pull the repo and refresh the plugin…
audit-automation-gaps
Audit a repo's Claude Code automation landscape, covering hooks, MCP servers, skills, subagents and scheduled tasks, against the enforcement hierarchy, producing PASS/REJECT/CONDITIONAL verdicts backed by evidence. The default verdict is REJECT because most gaps are already covered by compiler/analyzer/build-time…
audit-prompting-postures
Audit locally-owned instruction components, including skill bodies, agent definitions, hook instruction text, output styles, CLAUDE.md and rules, for MISSING posture guidance the official prompting guide says their purpose needs: delegation criteria/caps in orchestration components, minimal-scope and anti-test-gaming…