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 skills add rhtevan/agentfs --skill agentfs-git-pushgit clone --depth 1 https://github.com/rhtevan/agentfsWrote 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/skills/rhtevan/agentfs/agentfs-git-push)<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.
<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>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 | $0.00025 | $0.00983 |
| Opus 5 | $0.00013 | $0.00491 |
| Sonnet 5 | $0.00005 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00098 |
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.
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:
- If the user specifies a repo explicitly ("push this project", "push context-eng", "push ~/.agents"), use that.
- If invoked with bare "hey git" or "git push" without an
explicit target, the default is
~/.agents/(USER scope AgentFS repo). - 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
⚠️ FOUNDitems 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
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.
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.
- 5d ago First seen · 135 lines · 25 tokens per session scan A 587f897dbb39
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.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
git-commit
Creates git commits following Conventional Commits format with type/scope/subject and detailed markdown body. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md. Each change type gets its own markdown heading (# emoji + type), with…