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/enuno/unifi-mcp-server/workflowgit clone --depth 1 https://github.com/enuno/unifi-mcp-serverWhat 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 | $0.00000 | $0.00493 |
| Opus 5 | $0.00000 | $0.00246 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
workflow 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.
What it actually says
Development Workflow
Before Starting Work
- Pull latest changes:
git pull origin main - Create feature branch:
git checkout -b feature/your-feature - Review existing patterns in similar files
- Read
CLAUDE.mdandAGENTS.mdfor project-specific AI assistant guidelines
During Development
- Write tests first (TDD approach)
- Implement feature following patterns above
- Run tests frequently:
pytest -v - Check types:
mypy src/ - Format code:
black src/ tests/andisort src/ tests/
Before Committing
- Run full test suite:
pytest --cov=src --cov-report=term-missing - Ensure coverage ≥80%: Check coverage report
- Run linter:
ruff check src/ tests/ --fix - Type check:
mypy src/ - Run pre-commit hooks:
pre-commit run --all-files - Update documentation if needed
Commit Message Format
Follow Conventional Commits:
<type>: <short summary>
<optional body>
Types: feat, fix, docs, test, refactor, style, chore
Examples:
feat: add DPI statistics tool for bandwidth analysis
fix: correct device restart timeout handling
docs: update API.md with WiFi management tools
test: add integration tests for port forwarding
refactor: simplify client blocking logic
Code Quality Checklist
Before submitting a PR, verify:
- All tests pass (
pytest) - Code coverage ≥80% (
pytest --cov) - Type checking passes (
mypy src/) - Linting passes (
ruff check src/ tests/) - Code formatted (
black,isort) - Security checks pass (
bandit -r src/) - Pre-commit hooks pass
- Documentation updated (docstrings, API.md)
- CHANGELOG.md updated for user-facing changes
- No hardcoded secrets or API keys
- Audit logging added for mutating operations
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.
- 2d ago First seen · 70 lines · 0 tokens per session scan A 689275d226fa
workflow is a cursor rule published in the GitHub repository enuno/unifi-mcp-server (242 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 493 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.
Other cursor rules, from other repositories
incremental-verify
Verify each behavior before building the next. One test, one implementation, one commit. No bulk-writing tests for behavior that does not yet exist.
cmd-build
Implement the next task incrementally — build, test, verify, commit.
git-commit-attribution
Git commits must use the human developer identity only; never Cursor Agent co-authorship.
test_first_workflow
Enforce test-first or test-alongside development. Load when implementing new features, APIs, or UI components.
no-cursor-commit-attribution
Never add Cursor co-author or attribution trailers to git commits or PRs.
git-commits
description: "Reference and apply the git commits skill for Conventional Commit formatting and pre-push checks." alwaysApply: true.