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 agentmods add rules/danielvm-git/bigpowers/guard-gitgit clone --depth 1 https://github.com/danielvm-git/bigpowersWrote 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/rules/danielvm-git/bigpowers/guard-git)<a href="https://agentmods.dev/rules/danielvm-git/bigpowers/guard-git"><img src="https://agentmods.dev/badge/rules/danielvm-git/bigpowers/guard-git.svg" alt="Measured on agentmods" 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 | $0.00096 | $0.01870 |
| Opus 5 | $0.00048 | $0.00935 |
| Sonnet 5 | $0.00019 | $0.00374 |
| Haiku 4.5 | $0.00010 | $0.00187 |
Grade B, and why
guard-git scanned grade B 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Claude Code | `PreToolUse` (Bash) | `.claude/settings.json` or `~/.claude/settings.json` | How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guard Git
HARD GATE — HARD GATE — Before committing, verify: branch is not main/master, author is correct, git user is configured. Bad commits are hard to fix.
Installs a shared hook that blocks destructive git operations and enforces workflow discipline. Requires jq on the agent's PATH when the hook runs.
What gets blocked/enforced
- Safety:
git push --force,git reset --hard,git clean -f,git branch -D,git checkout .,git restore .. - Discipline: Blocks direct commits or pushes to protected branches (
main,master) unlessGIT_BIGPOWERS_LAND=1(set only byscripts/land-branch.sh). - Allows:
git push origin <feature-branch>for backup/CI; solo land push tomainonly insideland-branch.sh. - Standardization: Enforces Conventional Commits for all
git commitcommands. - Secrets: Blocks commits containing common secret patterns (
sk-,ghp_,AKIA,xoxb-,-----BEGINprivate keys) — see REFERENCE.md.
Quick start
- Scope: ask project-only vs global (paths differ per product).
- Write the hook bundle from REFERENCE.md into the client's hooks directory.
- Run
chmod +xonpre-tool-use.sh. - Merge the hook snippet from REFERENCE.md into the right settings file — do not wipe unrelated keys.
- Verify with the tests in REFERENCE.md.
| Client | Mechanism | Config |
|---|---|---|
| Claude Code | PreToolUse (Bash) |
.claude/settings.json or ~/.claude/settings.json |
| Cursor / Cursor CLI | beforeShellExecution |
.cursor/hooks.json or ~/.cursor/hooks.json |
| Gemini CLI | BeforeTool + run_shell_command |
.gemini/settings.json or ~/.gemini/settings.json |
| Google Antigravity | Built-in Terminal Deny list | Settings UI (no shell hook) |
Modes (env on the hook command): GIT_GUARDRAILS_MODE is claude (default) or cursor → stderr + exit 2 on block. Set gemini for Gemini CLI → JSON decision on stdout.
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.
- today First seen · 231 lines · 96 tokens per session scan B 528d90a61ee6
guard-git is a cursor rule published in the GitHub repository danielvm-git/bigpowers (163 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 1,870 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other cursor rules, from other repositories
stripe
Stripe payment integration, webhooks, checkout, and subscriptions.
nextjs
ContextOS rules for nextjs.
faststore-faststore-storefront-ref-project-structure-routes-and-config
FastStore project structure, routes, CLI build pipeline, store configuration (discovery.config.js), and naming conventions. Use when understanding how a FastStore project is organized, how the @faststore/cli works, what files to create or modify, how routing works, or how to configure store settings like SEO, API…
react-composition-patterns
React composition patterns for scalable component architecture including compound components, context providers, state management, boolean prop alternatives, render props vs children, and React 19 API changes. Use when refactoring components with many boolean props, building component libraries, designing flexible…
08-project-structure
Project organisation and package structure.
tdd
Test-driven development — red-green-refactor cycle.