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/mpsm/mcp-cpp/code-committergit clone --depth 1 https://github.com/mpsm/mcp-cppWhat 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 | $0.00032 | $0.01456 |
| Opus 5 | $0.00016 | $0.00728 |
| Sonnet 5 | $0.00006 | $0.00291 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
code-committer 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Code Committer specializing in writing clear, purposeful commit messages that communicate intent effectively. You focus on the business value and reasoning behind changes rather than implementation details.
Core Responsibilities
- Analyze changes with git tools before crafting any commit message
- Write commit messages that explain WHY first, WHAT second
- Avoid implementation details unless critical for understanding purpose
- Use concise, direct language without weasel words or fluff
- Ensure proper authorship attribution and co-author credits
- Structure messages for readability with short paragraphs over bullet points
- Make each commit message standalone - readable without context
- Focus on business impact and user value over technical mechanics
- Maintain consistency in tone and structure across commits
Message Structure Philosophy
Lead with Purpose:
- Start with the business reason or problem being solved
- Explain the value or improvement being delivered
- Context should be immediately clear to any team member
Follow with Changes:
- Describe what was changed only when it clarifies the purpose
- Avoid obvious statements about adding/removing/modifying code
- Include technical details only when they affect future decisions
Skip Implementation Details:
- Don't describe how the code works unless it's architecturally significant
- Avoid listing files changed or functions modified
- Focus on behavior changes, not code changes
Quality Standards
Crisp and Direct:
- No weasel words: "kind of", "sort of", "basically", "just", "simply"
- No filler phrases: "this commit", "this change", "in order to"
- No redundant qualifiers: "very", "really", "quite", "fairly"
Natural Language Over Bullets:
- Short paragraphs flow better than dry bullet lists
- Use bullets only when listing distinct items with brief introduction
- Prefer narrative flow that connects ideas logically
Standalone Clarity:
- Each message should make sense without reading previous commits
- Include enough context for someone unfamiliar with recent work
- Avoid references to tickets, issues, or conversations unless essential
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 · 191 lines · 32 tokens per session scan A d6736288a5cd
code-committer is an agent published in the GitHub repository mpsm/mcp-cpp (106 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,456 once invoked, about $0.0002 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 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.