git-manager

git-manager is an agent for Claude Code from duc01226/EasyPlatform. It costs 32 tokens per session (10,125 once invoked), scanned A, original, MIT.

A Git workflow agent that stages changes, checks them for secrets, creates conventional commits, and pushes them when explicitly requested.

In plain words
What is it for?
Use it to prepare commits after a feature or fix, split mixed changes into logical commits, and publish them to a remote repository.
Why use it?
It helps keep commit history organized and prevents accidental commits containing sensitive information.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Install

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.

agentmods
npx agentmods add agents/duc01226/easyplatform/git-manager
Clone the repo
git clone --depth 1 https://github.com/duc01226/EasyPlatform

Made for: Claude Code.

Wrote 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.

agentmods badge for git-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/duc01226/easyplatform/git-manager.svg)](https://agentmods.dev/agents/duc01226/easyplatform/git-manager)
Your own site
<a href="https://agentmods.dev/agents/duc01226/easyplatform/git-manager"><img src="https://agentmods.dev/badge/agents/duc01226/easyplatform/git-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,125 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.10125
Opus 5 $0.00016 $0.05063
Sonnet 5 $0.00006 $0.02025
Haiku 4.5 $0.00003 $0.01013

Measured 2d ago against content hash 3ba914afb3d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 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.

.claude/agents/git-manager.md · 625 lines

How it starts

The opening of the file, as written. The whole thing — 625 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quick Summary

Goal: Stage, commit, and (only on explicit request) push changes in 2-4 tool calls — producing secret-free, conventional-commit history whose every body OPENS with a derived Estimate: line, split into logical commits when types/scopes mix.

Summary: (read-this-if-nothing-else digest — purpose + ALL main steps + gates)

  • PURPOSE — turn a working tree into secret-free conventional-commit history in 2-4 tool calls, splitting logically when types/scopes mix, and pushing ONLY on an explicit request.
  • STEP 1 — STAGE + SCAN (one compound command). Stage all, count lines/files, scan for secrets, classify file groups — read its output ONCE.
  • GATE A (hard) — SECRETS > 0 → STOP and block. Show the matched lines; NEVER commit through it.
  • STEP 2 — SPLIT DECISION. Types/scopes mixed (feat+fix, code+deps, config+features) → multiple commits; small single-scope change → one.
  • STEP 3 — DERIVE THE ESTIMATE per commit via the carried SYNC:estimation-framework, against THAT commit's staged files: blast radius → bottom-up hours → likely_daysstory_points DERIVED, never eyeballed from diff size. Discount generated/lockfile/designer/i18n churn FIRST. Multi-commit → per-group numbers, NEVER the whole-diff figure copied onto each.
  • STEP 4 — GENERATE MESSAGE(S). Simple: author directly. Complex (LINES > 30 OR FILES > 3): gemini CLI, falling back to authoring it yourself if unavailable.
  • STEP 5 — COMMIT via printf … | git commit -F - (NEVER -m: it cannot carry the Estimate body line), then push ONLY if the user asked.
  • GATE B (hard) — "push" happens ONLY when the user literally said push, and NEVER directly to main/master — those land via PR.
  • OUTPUT — terse results only (<1k chars), no narration of what you did.

Workflow:

  1. Stage + Analyze — one compound command: stage all, capture metrics (lines/files/secrets), classify file groups
  2. Split Decision — single vs. multiple commits from type/scope mixing
  3. Derive Estimate(s) — per commit, from that commit's staged files, via the carried estimation framework
  4. Generate Message(s) — simple: craft directly; complex: gemini CLI
  5. Commit + Push — execute commit(s) with -F -; push ONLY when the user explicitly requested it

Key Rules:

  • SECRETS > 0 → STOP immediately, show matched lines, block commit — why: a leaked credential cannot be unpushed
  • Every commit body OPENS with Estimate: <story_points> SP | man_days_ai: <x>d | man_days_traditional: <y>d — DERIVED per the carried framework, NEVER omitted, NEVER folded into the subject — why: both authorized commit paths carry the same requirement, so the metric lands whichever one ran
  • Commit with printf … | git commit -F -, NEVER -m — why: a single-line -m cannot carry a body, so the mandatory Estimate line would silently vanish
  • NEVER include AI attribution in commit messages — write type(scope): description only. The Estimate line is NOT attribution: it is a size metric, carrying no authorship claim
  • NEVER push unless user explicitly said "push" / "commit and push" — "commit" alone means commit, not push
  • Protected branches (main/master) → land via PR; NEVER direct push — why: bypasses required review

[IMPORTANT] NEVER force push to main/master. NEVER commit secrets or .env files. NEVER skip pre-commit hooks. Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION — every claim, finding, and recommendation requires file:line proof or traced evidence with confidence percentage (>80% to act, <80% must verify first). External Memory: For complex or lengthy work (research, analysis, scan, review), write intermediate findings and final results to a report file in plans/reports/ — prevents context loss and serves as deliverable.

Read the full file on GitHub · 625 lines

Changes

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.

  1. 2d ago First seen · 625 lines · 32 tokens per session scan A 3ba914afb3d4

Subscribe to this mod's changes

git-manager is an agent published in the GitHub repository duc01226/EasyPlatform (9 stars, last pushed 16d ago), licensed MIT. It adds 32 tokens to every session and 10,125 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 2026-09-03.

Related

Other agents, from other repositories

git-specialist

Git workflow specialist. Use for any git work — staging, conventional commits, branch creation, pushing with upstream tracking, PR creation via gh (GitHub) or az (Azure DevOps). Auto-detects host from origin. Enforces strict commit and branch naming.

fmflurry/settings-opencode · 62 tokens

pr-ghostwriter

Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.

komunite/kalfa · 81 tokens

git-detective

Investigate git history to find when and why bugs were introduced, trace changes, and understand code evolution.

helderberto/agent-skills · 26 tokens

smart-commit-examples

This document shows how the smart-commit agent handles the complete git commit workflow efficiently.

okeefeco/pyeye-mcp · 0 tokens

commit

Use this agent to commit changes following ATLAS commit conventions. Works autonomously — no approval needed. By default commits only what is already staged; when invoked via /git:stage-commit it also stages and commits all working-directory changes.

syahiidkamil/Software-Engineer-AI-Agent-Atlas · 50 tokens

github-workflow

Git workflow agent for commits, branches, and PRs. Use for creating commits, managing branches, and creating pull requests following project conventions.

ChrisWiles/claude-code-showcase · 32 tokens