Borrowing it
Nothing to install: this file belongs to AmitGurbani/mcp-server-woocommerce. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AmitGurbani/mcp-server-woocommerce/main/.claude/commands/commit.mdgit clone --depth 1 https://github.com/AmitGurbani/mcp-server-woocommerceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/amitgurbani/mcp-server-woocommerce/commit)<a href="https://agentmods.dev/commands/amitgurbani/mcp-server-woocommerce/commit"><img src="https://agentmods.dev/badge/commands/amitgurbani/mcp-server-woocommerce/commit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/amitgurbani/mcp-server-woocommerce/commit"><img src="https://agentmods.dev/badge/commands/amitgurbani/mcp-server-woocommerce/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00007 | $0.00751 |
| Opus 5.5 | $0.00003 | $0.00300 |
| Sonnet 5.5 | $0.00001 | $0.00150 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
commit 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 2mo ago.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a git commit following the project's conventional commit format with emoji prefixes.
Commit Message Format
<type>(<scope>): <emoji> <subject>
[optional body]
[optional footer]
Types and Emojis
feat: ✨ New featurefix: 🐛 Bug fixdocs: 📝 Documentation changesstyle: 💄 Code style/formatting (no logic changes)refactor: ♻️ Code refactoringperf: ⚡ Performance improvementstest: ✅ Adding or updating testschore: 🔧 Maintenance tasks, dependenciesci: 👷 CI/CD changesbuild: 📦 Build system changesrevert: ⏪ Revert previous commit
Scopes
Common scopes in this project:
tools- MCP tool files (products, orders, categories, etc.)services- Base service layer, WooCommerce clientserver- Server setup, entry pointconfig- tsconfig, package.json, .mcp.jsondeps- Dependency updates
CRITICAL: No Attribution in Commits
DO NOT add any Claude Code attribution to commit messages.
Commit messages must be clean and end after the optional body/footer. Never include:
- ❌ "Generated with Claude Code"
- ❌ "Co-Authored-By: Claude"
- ❌ Links to claude.com
- ❌ Any other attribution lines
The commit message should contain ONLY:
- ✅ Type, scope, emoji, and subject line
- ✅ Optional body explaining "why"
- ✅ Optional footer (issue references, breaking changes)
Instructions
- Run
git statusto see what files are staged/modified - Run
git diff --stagedto review staged changes - Run
git log --oneline -10to see recent commit style - Analyze the changes and determine:
- Type (feat, fix, docs, etc.)
- Scope (which area affected)
- Clear, concise subject line (50 chars max)
- Body if needed to explain "why" not "what"
- Stage any unstaged files that should be included:
git add <files> - Create the commit with proper format (NO ATTRIBUTION!)
- Run
git statusafter committing to confirm
Examples
# New MCP tool
git commit -m "feat(tools): ✨ add product variation tools"
# Bug fix in service layer
git commit -m "fix(services): 🐛 handle WooCommerce API timeout errors"
# Documentation update
git commit -m "docs(config): 📝 update CLAUDE.md with new tools"
# Dependency upgrade
git commit -m "chore(deps): ⬆️ upgrade zod to v4"
# Refactoring
git commit -m "refactor(services): ♻️ extract pagination logic to helper"
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.
- 2mo ago First seen · 102 lines · 7 tokens per session scan A 9348a2e61473
commit is a command published in the GitHub repository AmitGurbani/mcp-server-woocommerce (2 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 751 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-31.
Other commands, from other repositories
fest-commit
Commit changes with festival traceability metadata.
merge
You are executing the /hydra:merge command. Merge a worktree branch back into the current branch.
template
Create a git commit.
umt-doctor
Diagnose UMT MCP server setup — builds, environment variables, and config health.
umt
Survey the Universal MCP Toolkit — available servers, install state, and how to connect them to any harness.
commit
Create git commits aligned with task completion, maintaining clean version control synchronized with task progress.