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.
git clone --depth 1 https://github.com/marmot-protocol/agent-configWrote 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/marmot-protocol/agent-config/commit)<a href="https://agentmods.dev/commands/marmot-protocol/agent-config/commit"><img src="https://agentmods.dev/badge/commands/marmot-protocol/agent-config/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/marmot-protocol/agent-config/commit"><img src="https://agentmods.dev/badge/commands/marmot-protocol/agent-config/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 | $0.00011 | $0.00575 |
| Opus 5.5 | $0.00004 | $0.00230 |
| Sonnet 5.5 | $0.00002 | $0.00115 |
| Haiku 4.5 | $0.00001 | $0.00057 |
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 1mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Command
You are creating a git commit for the currently staged changes.
Workflow
-
Check staged changes exist
- Run
git diff --cached --statto verify files are staged - If nothing is staged, inform the user and stop
- List the staged files for confirmation
- Run
-
Generate commit message
- Use the
/commit_messagecommand workflow to analyze staged changes - Use the
commit_messagetool to get type, scope, and subject suggestions - Draft a conventional commit message following the format below
- Use the
-
Create the commit
- Present the proposed commit message to the user
- Use the
committool with the full message to create the commit - The tool handles safety checks (secrets detection) and returns the commit hash
-
Report result
- Show the commit hash and summary from the tool response
- If the commit failed, report the error and hint
Commit Message Format
<type>(<scope>): <subject>
<body>
<footer>
Types
- feat: New feature
- fix: Bug fix
- docs: Documentation changes
- style: Code style (formatting, semicolons)
- refactor: Code restructuring without behavior change
- test: Adding or updating tests
- chore: Maintenance tasks
- perf: Performance improvements
Guidelines
- Subject line: 50 characters max, imperative mood ("add" not "added")
- Body: Explain what and why, not how
- Reference issues with "Fixes #123" or "Closes #456"
- Wrap body at 72 characters
Safety Rules
The commit tool enforces these automatically:
- Rejects commits with no staged changes
- Detects potential secrets (.env, credentials, keys) and blocks unless overridden
- Returns structured error messages with hints
Additional rules for the agent:
- NEVER use
--amendunless explicitly requested - NEVER use
--no-verifyto skip hooks - ALWAYS present the message to the user before committing
Example Output
Staged changes:
- src/auth/reset.ts (new file)
- src/auth/login.ts (modified)
Proposed commit message:
feat(auth): add password reset functionality
Implement password reset flow with email verification.
Users can now request a reset link that expires after 24 hours.
Closes #42
---
✓ Commit created: a1b2c3d feat(auth): add password reset functionality
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.
- 1mo ago First seen · 89 lines · 11 tokens per session scan A 3f40f9ce432e
commit is a command published in the GitHub repository marmot-protocol/agent-config (2 stars, last pushed 8mo ago), licensed MIT. It adds 11 tokens to every session and 575 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
standup
Review my git commits from the past workday and generate a standup summary.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
git-workflow
Run review, tests, and commit steps, then prepare a pull request.
commit
Context-aware Git commit assistant with smart pre-commit checks.