agentfs-git-push

agentfs-git-push is a skill for Claude Code, Codex from rhtevan/agentfs. It costs 25 tokens per session (983 once invoked), scanned A, original, Apache-2.0.

A safety procedure for staging, scanning, committing, and pushing changes to a Git repository. Git is a system for tracking code changes and sharing them with other developers.

In plain words
What is it for?
Use it when preparing a repository for commit and push, especially when the target repository or its uncommitted changes need to be checked first.
Why use it?
It helps catch secrets, personal information, private paths, and other sensitive data before changes are uploaded.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it when preparing a repository for commit and push, especially when the target repository or its uncommitted changes need to be checked first.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rhtevan/agentfs/agentfs-git-push
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.

Any agent
npx skills add rhtevan/agentfs --skill agentfs-git-push
Clone the repo
git clone --depth 1 https://github.com/rhtevan/agentfs

Made for: Claude Code, Codex.

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 agentfs-git-push

README.md
[![agentmods](https://agentmods.dev/badge/skills/rhtevan/agentfs/agentfs-git-push/github.svg)](https://agentmods.dev/skills/rhtevan/agentfs/agentfs-git-push)
Your own site
<a href="https://agentmods.dev/skills/rhtevan/agentfs/agentfs-git-push"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/agentfs-git-push/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.

agentmods 80×15 button for agentfs-git-push

Your own site · 80×15
<a href="https://agentmods.dev/skills/rhtevan/agentfs/agentfs-git-push"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/agentfs-git-push.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 983 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00025 $0.00983
Opus 5 $0.00013 $0.00491
Sonnet 5 $0.00005 $0.00197
Haiku 4.5 $0.00003 $0.00098

Measured 5d ago against content hash 587f897dbb39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agentfs-git-push 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 5d 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.

skills/agentfs-git-push/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Push Safety

Stage, scan, report, wait for confirmation, then commit and push. This skill absorbs the full Git Push Safety workflow previously inline in AGENTS.md Guardrail #10 (v4.x).

Workflow

Execute these steps in exact order. Do NOT skip or combine steps.

Step 0 — Resolve Target

Determine which git repo to operate on:

  1. If the user specifies a repo explicitly ("push this project", "push context-eng", "push ~/.agents"), use that.
  2. If invoked with bare "hey git" or "git push" without an explicit target, the default is ~/.agents/ (USER scope AgentFS repo).
  3. If the CWD is a different git repo with uncommitted changes, confirm with the user before assuming CWD.

All subsequent steps (git add, pre-push-scan.sh, git commit, git push) run inside the resolved target directory.

Step 1 — Stage

git add -A

Step 2 — Scan

bash ~/.agents/skills/agentfs-setup/scripts/pre-push-scan.sh

This scans the staged diff for secrets, hardcoded paths, username leakage, IP addresses, sensitive URLs, and PII.

Step 3 — Allowlist Filtering

Read .pre-push-allowlist (at repo root, e.g. ~/.agents/.pre-push-allowlist for USER scope). Semantically match each finding against the allowlist descriptions.

  • Findings matching a known false positive → report as ✅ Known FP
  • Findings NOT matching → report as ⚠️ FOUND
  • Only ⚠️ FOUND items count toward a blocking verdict

Step 4 — README Audit (conditional)

If pre-push-scan.sh output contains README_AUDIT_REQUIRED (emitted when skills/, knowledge/, or AGENTS.md are staged):

load_skill(name: "agentfs-readme-audit")

Follow that skill completely before continuing.

Step 5 — PII Review (conditional)

If memory files (.agents/memories/) are among the flagged findings, perform a semantic PII review of the staged memory content. Look for:

  • Real names, email addresses, phone numbers
  • Account identifiers, credentials
  • Location data, health data

Read the full file on GitHub · 135 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 135 lines · 25 tokens per session scan A 587f897dbb39

Subscribe to this mod's changes

agentfs-git-push is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 983 once invoked, about $0.0001 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 2026-09-04.