A Git safety control that sets an anonymous author identity and blocks secrets from Git operations. Git is the system used to track code changes and share them with others.

It is for checking commits, merges, rebases, cherry-picks, tags, pushes, staging, and repository hooks before they run.

It prevents private email addresses from appearing in commits and helps stop passwords, tokens, and other sensitive files from being staged, committed, or pushed.

git-safety — Skill for Cursor by cam-douglas/agent-instructions

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 cam-douglas/agent-instructions --skill git-safety

Clone the repo

git clone --depth 1 https://github.com/cam-douglas/agent-instructions

Made for: Cursor.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cam-douglas/agent-instructions/git-safety/github.svg)](https://agentmods.dev/skills/cam-douglas/agent-instructions/git-safety)

Your own site

<a href="https://agentmods.dev/skills/cam-douglas/agent-instructions/git-safety"><img src="https://agentmods.dev/badge/skills/cam-douglas/agent-instructions/git-safety/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cam-douglas/agent-instructions/git-safety"><img src="https://agentmods.dev/badge/skills/cam-douglas/agent-instructions/git-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 638 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.00638
Opus 5.5	$0.00009	$0.00255
Sonnet 5.5	$0.00005	$0.00128
Haiku 4.5	$0.00002	$0.00064

Measured 1mo ago against content hash aa6021d938d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

git-safety scanned grade C with 1 finding 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 1mo ago.

The scan reads SKILL.md. This mod also ships 6 executable files (payloads/bootstrap.sh, payloads/policy.mjs, payloads/policy.test.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

4. Do not stage, commit, or push `.env*`, keys, credential JSON, `.netrc`, `.npmrc`, `.pypirc`, or files whose contents match secret patterns.

.cursor/skills/git-safety/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git safety

Purpose

Prevent private-email git attribution and keep secrets out of git in every project that uses this control plane.

When to use

Any git commit, merge, rebase, cherry-pick, pull that can create a commit, annotated tag, note, or push
Any staging command that might include secret-bearing files
Before installing or validating repository hooks

Inputs

Repository root
Intended git command

Tools used

scripts/git-safety.mjs
scripts/git-safety.test.mjs
payloads/policy.mjs
payloads/policy.test.mjs
payloads/bootstrap.sh
payloads/validate-agent-config.mjs
payloads/cli.json
payloads/git-privacy-and-secrets.mdc
payloads/agent-governance.yml
Repository .githooks/pre-commit, .githooks/commit-msg, and .githooks/pre-push

Procedure

Never run git config to set user.name or user.email.
Never use the host private email. Always export the Cursor anonymous identity:

GIT_AUTHOR_NAME='Cursor Agent' \
GIT_AUTHOR_EMAIL='[email protected]' \
GIT_COMMITTER_NAME='Cursor Agent' \
GIT_COMMITTER_EMAIL='[email protected]' \
git commit -m "message"

A GitHub noreply address (*@users.noreply.github.com) is also allowed. Any other email is forbidden.
Do not stage, commit, or push .env*, keys, credential JSON, .netrc, .npmrc, .pypirc, or files whose contents match secret patterns.
If bootstrap has not copied hooks yet, copy .githooks/* into .git/hooks/ without changing git config.
If a hook or policy denies the command, stop. Do not weaken the hook.

Expected outcome

Every agent-created git object uses [email protected] or a GitHub noreply address, and no secret value or secret-bearing file enters git.

Validation

node --test .cursor/skills/git-safety/scripts/git-safety.test.mjs
node --test .cursor/hooks/policy.test.mjs

Failure modes / cautions

Host user.email is not an authorization signal. If it is a personal inbox, ignore it.
Do not print secret values when a scan fails. Report only the path and rule id.
Do not use --no-verify or rewrite hooks to bypass this skill.

Read the full file on GitHub · 79 lines

Files

What ships with it

9 files 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.

1mo ago First seen · 79 lines · 23 tokens per session scan C aa6021d938d4

Subscribe to this mod's changes

git-safety is a skill published in the GitHub repository cam-douglas/agent-instructions (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 638 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.

Commits Git and workflow Security

create-pr

Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.

prisma/orm · 48 tokens

git-commit

Generate well-formatted git commit messages following conventional commit standards.

ThinkInAIXYZ/deepchat · 15 tokens

repo-sync

Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.

davidondrej/skills · 25 tokens

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

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…

HugoRCD/evlog · 68 tokens

git-commit-writer

Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.

mergisi/awesome-openclaw-agents · 53 tokens

git-safety