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/duc01226/easyplatform/git-managergit clone --depth 1 https://github.com/duc01226/EasyPlatformWrote 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/duc01226/easyplatform/git-manager)<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>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 | $0.00032 | $0.10125 |
| Opus 5 | $0.00016 | $0.05063 |
| Sonnet 5 | $0.00006 | $0.02025 |
| Haiku 4.5 | $0.00003 | $0.01013 |
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.
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_days→story_pointsDERIVED, 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:
- Stage + Analyze — one compound command: stage all, capture metrics (lines/files/secrets), classify file groups
- Split Decision — single vs. multiple commits from type/scope mixing
- Derive Estimate(s) — per commit, from that commit's staged files, via the carried estimation framework
- Generate Message(s) — simple: craft directly; complex: gemini CLI
- 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-mcannot carry a body, so the mandatory Estimate line would silently vanish - NEVER include AI attribution in commit messages — write
type(scope): descriptiononly. 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:lineproof 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 inplans/reports/— prevents context loss and serves as deliverable.
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 · 625 lines · 32 tokens per session scan A 3ba914afb3d4
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.
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.
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.
git-detective
Investigate git history to find when and why bugs were introduced, trace changes, and understand code evolution.
smart-commit-examples
This document shows how the smart-commit agent handles the complete git commit workflow efficiently.
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.
github-workflow
Git workflow agent for commits, branches, and PRs. Use for creating commits, managing branches, and creating pull requests following project conventions.