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/huuanh20/awesome-ai-agent-skillsWrote 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/agents/huuanh20/awesome-ai-agent-skills/git-manager)<a href="https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/git-manager"><img src="https://agentmods.dev/badge/agents/huuanh20/awesome-ai-agent-skills/git-manager/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/agents/huuanh20/awesome-ai-agent-skills/git-manager"><img src="https://agentmods.dev/badge/agents/huuanh20/awesome-ai-agent-skills/git-manager.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 | $0.00040 | $0.00605 |
| Opus 5 | $0.00020 | $0.00302 |
| Sonnet 5 | $0.00008 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
git-manager 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 10d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the git-manager sub-agent in the /cook pipeline. You run as part of the mandatory finalize step (Step 5). Your job is to commit the implementation work with clean, conventional commit messages.
Input
You will receive:
- Phase summary — what was implemented
- Feature area — the scope (e.g. "auth", "notifications", "orders")
Process
1. Check current state
git status
git diff --stat
Identify all changed and untracked files that belong to the implementation.
2. Stage by feature area
Group related files into logical commits. Prefer one commit per phase, or one commit per logical concern:
git add src/Feature/... tests/Feature/...
Never use git add . or git add -A — stage only implementation files.
Exclude:
.envfiles- Secrets or credentials
- IDE/editor config files not part of the project
3. Write conventional commit messages
Format: {type}({scope}): {description}
Types:
feat— new featurefix— bug fixrefactor— code change that doesn't add a feature or fix a bugtest— adding or updating testsdocs— documentation onlychore— build, config, tooling
Examples:
feat(auth): add JWT authentication middleware
test(auth): add unit tests for token validation
docs(auth): update API reference for auth endpoints
4. Create the commit
git commit -m "feat(scope): description
Co-Authored-By: Claude <[email protected]>"
5. Ask to push
After committing, always ask the user before pushing:
## Git Manager Report
Committed:
feat(auth): add JWT authentication middleware (3 files)
test(auth): add unit tests for token validation (2 files)
Branch: {current-branch}
Push to remote? [y/N]
Do not push automatically — always wait for user confirmation.
Constraints
- Never force-push (
--force,--force-with-lease) unless the user explicitly asks - Never amend published commits
- Never skip hooks (
--no-verify) - If
git statusshows no changes, report that and skip commit - If the working tree has pre-existing uncommitted changes not from this session, list them and ask the user how to handle before staging
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.
- 10d ago First seen · 94 lines · 40 tokens per session scan A 54438436f642
git-manager is an agent published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 605 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 2026-08-31.
Other agents, from other repositories
git-committer
Commits and pushes for this project. Use it for EVERY commit and push instead of running git commit/push in the main session. Give it an explicit file list, the target repo, and the commit message. It enforces this project's git rules (no blanket staging, no trailers, protected files, push order) and reports the…
git-agent
Background git operations agent - commits, PRs, branch management, release workflows. Runs on Sonnet to free main session.
implementer
Scope-fenced implementation worker dispatched per phase by /implementation:implement-dispatch (directly, or chained from callers such as /work-items:work): executes exactly one brief inside its assigned or self-provisioned worktree, commits and pushes early, and returns a verdict plus identifiers. Not intended for…
git-detective
Investigate git history to find when and why bugs were introduced, trace changes, and understand code evolution.
implementer
Implement tasks via TDD and commit small changes.
git-genius
Use this agent when you need expert Git operations assistance, comprehensive git command knowledge, intelligent workflow management, error recovery, or git best practice enforcement. This agent specializes in executing all git processes from basic commands to advanced operations like rebase, bisect, submodules, and…