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 gullitmiranda/.cursor --skill safetygit clone --depth 1 https://github.com/gullitmiranda/.cursorWrote 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/gullitmiranda/.cursor/safety)<a href="https://agentmods.dev/skills/gullitmiranda/.cursor/safety"><img src="https://agentmods.dev/badge/skills/gullitmiranda/.cursor/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.
<a href="https://agentmods.dev/skills/gullitmiranda/.cursor/safety"><img src="https://agentmods.dev/badge/skills/gullitmiranda/.cursor/safety.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 | $0.00041 | $0.00558 |
| Opus 5 | $0.00020 | $0.00279 |
| Sonnet 5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
safety 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 8d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safety Rules
Git Safety
Absolute Rules (Cannot be broken)
- Do not commit unless explicitly requested
- Do not push unless explicitly requested
- Never commit to main/master branch unless explicitly requested
- Never run
git reset --hardwithout explicit user approval
Core Safety Guidelines
- Do not change git stage without being asked
- Do not make commits without reviews unless explicitly requested
- Always create feature branches for changes
- Use
/git-branchcommand for safe branch creation /commitcommand automatically creates feature branch when on main/master- Verify branch before committing
- Never commit unstaged changes without explicit request
- Always validate conventional commit format
- Create backups before destructive operations
- Show what will be committed before execution
- Never push directly to main/master
- Always create pull requests for main branch changes
- Use
/pr-createcommand for safe PR creation - Verify remote branch exists before pushing
Command Safety
Shell Safety
- Prefer terminal commands over GUI operations when possible
Kubernetes Safety
- Never execute
kubectl deleteorkubectl apply - Use
/k8s-checkfor safe inspection - Use
/k8s-validatefor manifest validation - Use
/k8s-difffor change preview
Git Destructive Operations
- Never run
git reset --hardwithout explicit approval - Use
/git-resetfor safe reset with backup - Always create stash before destructive operations
- Provide recovery instructions
Data Safety
- Always create backups before destructive operations
- Use git stash for uncommitted changes
- Document recovery procedures
- Test backup restoration
Workspace Safety
Multi-Repository Handling
- Always check current working directory and understand repository boundaries
- Never assume single git repository when working in multi-repo workspace
- Always verify which repository operations are targeting before execution
- When working with staged changes, identify which specific repository they belong to
- Navigate to correct repository directory before running git operations
- Treat each repository as separate entity with its own git state
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.
- 8d ago First seen · 82 lines · 41 tokens per session scan A 89fa9f04d27c
safety is a skill published in the GitHub repository gullitmiranda/.cursor (2 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 558 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 2026-08-31.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…