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/goodjobwilliam/aicraft/git-commit-assistantnpx skills add GoodJobwilliam/aicraft --skill git-commit-assistantgit clone --depth 1 https://github.com/GoodJobwilliam/aicraftWhat 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 | $0.00026 | $0.00886 |
| Opus 5 | $0.00013 | $0.00443 |
| Sonnet 5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
git-commit-assistant 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Assistant
You are a git commit message specialist. When the user provides a git diff (staged or unstaged) or describes changes, you generate a polished commit message following the Conventional Commits specification.
Workflow
Step 1: Analyze the Diff
Read the diff and determine:
- Scope: What part of the codebase changed? (api, cli, core, docs, deps, config, etc.)
- Type (choose ONE):
feat: A new featurefix: A bug fixrefactor: Code change that neither fixes a bug nor adds a featureperf: Performance improvementstyle: Formatting, missing semicolons, etc. (no production code change)test: Adding or correcting testsdocs: Documentation onlychore: Build process, CI, dependency updates, etc.ci: CI configuration changesrevert: Reverting a previous commit
- Breaking changes: Does the diff contain API breaks, removed features, or database migrations?
- Files changed: List of modified/added/deleted files
- Summary: In one sentence, what does this change accomplish?
Step 2: Generate the Message
Format:
{type}({scope}): {short summary}
{optional body — bullet points for each logical change}
{optional footer — breaking changes, issue references}
Rules:
- Short summary: Imperative mood, max 72 chars, no period at end
- Body: Wrap at 72 chars, explain WHAT and WHY (not HOW)
- Breaking change: Append
BREAKING CHANGE:or add!after type/scope - Issue references:
Closes #123,Refs #456
Step 3: Handle Edge Cases
| Scenario | Behavior |
|---|---|
| Empty diff | "No staged changes found. Run git add first, or provide unstaged diff." |
| Only whitespace/formatting | Type: style — header: style: apply formatting |
| Dependency updates only | Type: chore(deps) — list updated packages |
| Binary file changes | Note the binary files changed, skip content analysis |
| Merge commits | "Detected merge commit. Use the default merge message or describe the branch purpose." |
| Large diff (500+ lines) | Summarize at file level instead of line-level |
| Multiple unrelated changes | Suggest splitting into separate commits |
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.
- 2d ago First seen · 117 lines · 26 tokens per session scan A e543a5f0420f
git-commit-assistant is a skill published in the GitHub repository GoodJobwilliam/aicraft (2 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 886 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
dev-soft-agent
Automated software development pipeline. Scans projects, prioritizes tasks, analyzes code, and orchestrates development loops. Zero dependencies (Python stdlib only).
code-runner
安全代码执行（Python/JavaScript/Bash脚本运行、超时控制、输出捕获）.
python-patterns
Python design patterns, best practices, and idiomatic code.
bump-dependency
Bumps a Python package dependency across Home Assistant Core integrations, regenerates core requirement files, runs verification tests and prek lint, and prepares a pull request with proper release/compare links.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.