gitrules

A set of safety rules for using Git, the version-control system that records changes to code. It focuses on examining changes before undoing them and avoiding commands that can erase work.

In plain words
What is it for?
Reviewing a diff before undoing edits, manually reverting selected sections, and handling commits, branches, or cleanup operations safely.
Why use it?
It reduces the risk of permanently losing uncommitted files, detailed implementations, or other valuable changes during cleanup or reversion.

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/waynesutton/markdown-site/gitrules
Any agent
npx skills add waynesutton/markdown-site --skill gitrules
Clone the repo
git clone --depth 1 https://github.com/waynesutton/markdown-site

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 434 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 $0.00033 $0.00434
Opus 5 $0.00016 $0.00217
Sonnet 5 $0.00007 $0.00087
Haiku 4.5 $0.00003 $0.00043

Measured yesterday against content hash 06e4dd86106c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gitrules 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 yesterday.

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/gitrules/SKILL.md · 44 lines

What it actually says

Critical Git Safety Protocol

NEVER USE git checkout TO REVERT CHANGES.

MANDATORY GIT SAFETY RULES:

  • NEVER run git checkout -- <file> without first examining what you're about to destroy
  • ALWAYS use git diff <file> to see exactly what changes will be lost
  • MANUALLY undo changes by editing files to revert specific problematic sections
  • Preserve valuable work: if user says changes are bad, ask which specific parts to revert
  • git checkout destroys ALL changes: this can eliminate hours of valuable progress
  • When user asks to "undo" changes: Read the current file, identify problematic sections, and manually edit to fix them

Why this matters: Using git checkout blindly can destroy sophisticated implementations, complex prompts, provider-specific logic, and other valuable work that took significant time to develop.

Git Safety Rules

NEVER run these commands without explicit user approval:

  • git reset --hard: Destroys uncommitted changes permanently
  • git checkout -- .: Discards all working directory changes
  • git clean -fd: Deletes untracked files permanently
  • git stash drop: Deletes stashed changes

ALWAYS before any git operation:

  1. Run git status first to check for uncommitted changes
  2. If there are uncommitted changes, STOP and ASK the user before proceeding
  3. Suggest git stash to preserve changes if needed
  4. Never create a commit unless the user explicitly asked for one

If user asks to "revert" something:

  1. First clarify: revert committed changes or uncommitted changes?
  2. Show what will be affected before doing anything
  3. Get explicit confirmation for destructive operations

This rule exists because careless git operations destroyed 2 days of work.

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. yesterday First seen · 44 lines · 33 tokens per session scan A 06e4dd86106c

Subscribe to this mod's changes

gitrules is a skill published in the GitHub repository waynesutton/markdown-site (631 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 434 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 2026-08-30.

Related

Other skills, from other repositories

shieldcn-badges

Create polished shieldcn README badges, badge groups, charts, headers, sponsors grids, and full README hero sections. Use when a user wants shadcn/ui-styled badges, Shields.io replacement, npm/GitHub/CI/status badges, download charts, README header banners, contributor/sponsor images, or README Studio guidance.…

jal-co/shieldcn · 145 tokens

infisical-sync-skill

Expert knowledge for the Infisical Sync Hand — Infisical API reference, vault operations, error patterns, security guidance.

RightNow-AI/openfang · 31 tokens

soul-grader

Use when grading, reviewing, rewriting, or approving a Hermes Agent SOUL.md. Uses the SOUL.md field-guide research artifacts as the only normative source for what makes a good SOUL.md.

cobibean/soul-grader-skill · 45 tokens

mb-ads

Create and review ads, and prepare provider-safe launch plans/checks. Flexible entry points: full pipeline (copy + images), copy only, images only, creative variations (hook library), video scripts, long-form video ads/VSL-style paid creative, video repurpose, compliance review, launch-plan, instrumentation, check, or…

noontide-co/mainbranch · 136 tokens

mb-think

Combined research, decision, and codification workflow. Use when: (1) Exploring a question before committing (2) Making a decision that needs documentation (3) User says research, decide, figure out, explore, codify, enrich, retire stale source, sharpen this offer, improve the offer, add context, keyword gate, analyze…

noontide-co/mainbranch · 141 tokens

anakinscraper

Scrape any website into clean markdown or structured JSON. Anti-detect browser, smart proxy rotation, AI-powered data extraction.

Anakin-Inc/anakin · 30 tokens