git-guardrails

A set of Git safety rules for an AI coding agent, covering commands that can discard history or remove files.

In plain words
What is it for?
Use it to enforce repository guardrails and validate records and tests before committing.
Why use it?
It prevents risky actions such as force-pushing, hard resets, cleaning untracked files, and interactive rebases on pushed commits.

Skill for Claude CodeCodex

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 skills/aveproject/ave/git-guardrails
Any agent
npx skills add aveproject/ave --skill git-guardrails
Clone the repo
git clone --depth 1 https://github.com/aveproject/ave

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 99 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 $0.00000 $0.00099
Opus 5 $0.00000 $0.00049
Sonnet 5 $0.00000 $0.00020
Haiku 4.5 $0.00000 $0.00010

Measured 2d ago against content hash 4abc24c5a86a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-guardrails 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/skills/git-guardrails/SKILL.md · 13 lines

What it actually says

git-guardrails — ave

Block: push --force, reset --hard, clean -fd, rebase -i on pushed commits.

Before commit: python scripts/validate_records.py # all records valid pytest tests/ -x -q # rules fire correctly

Record-specific

NEVER renumber an ave_id. Once AVE-2026-00001 is published, that number is permanent. A wrong record gets deprecated, not renumbered.

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 · 13 lines · 0 tokens per session scan A 4abc24c5a86a

Subscribe to this mod's changes

git-guardrails is a skill published in the GitHub repository aveproject/ave (17 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 99 tokens. 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 2026-08-30.