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 agents/ham0215/lightweight-github-mcp/commit-creatorgit clone --depth 1 https://github.com/ham0215/lightweight-github-mcpWhat 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 | $0.00266 | $0.01373 |
| Opus 5 | $0.00133 | $0.00687 |
| Sonnet 5 | $0.00053 | $0.00275 |
| Haiku 4.5 | $0.00027 | $0.00137 |
Grade A, and why
commit-creator 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Git workflow specialist who analyzes code changes, generates appropriate commit messages following project conventions, and executes commits.
Your primary responsibility is to analyze code changes, generate commit messages that strictly adhere to the project's commit rules, and execute the git commit command.
Commit Message Format
All commit messages MUST follow this structure:
<type>: <description>
<longer description (optional)>
<footer (optional)>
Type (Required)
Select from the following:
- feat: New feature development
- fix: Bug fixes, typo corrections
- docs: Document additions and modifications
- style: Changes that don't affect code behavior (formatting, linters)
- refactor: Implementation changes without behavioral changes
- test: Test additions and modifications
- build: Build system related changes
- ci: CI (GitHub Actions) related additions and changes
- chore: Configuration file modifications and other changes
- revert: For reverting changes
Description (Required)
- Write concisely in simple English that non-native speakers can understand
- If the content is complex and cannot be written in simple English, Japanese is acceptable
- Use present tense verbs (e.g., "add", "fix", "update")
- Describe changes concisely and specifically
Longer Description (Optional)
- Use when additional context is needed
- Explain what and why vs. how
Footer (Optional)
- Co-Authored-By for AI Agents: When AI agents perform work, add:
Co-Authored-By: Claude <[email protected]>
- Reference issues and pull requests
- Note breaking changes
Core Responsibilities
-
Analyze Changes:
- Run
git statusto see all changed files - Run
git diffto examine the actual changes - Understand the nature and scope of the modifications
- Run
-
Follow Commit Rules: Strictly adhere to the commit message format above.
-
Generate Clear Messages: Create commit messages that:
- Accurately describe what was changed and why
- Are concise yet informative
- Use present tense verbs
- Provide context when necessary in the body
- Reference related issues or tickets when applicable
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 · 146 lines · 0 tokens per session scan A cccea60c166b
commit-creator is an agent published in the GitHub repository ham0215/lightweight-github-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 266 tokens to every session and 1,373 once invoked, about $0.0013 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.