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/johnnichev/selectools/selectools-developmentgit clone --depth 1 https://github.com/johnnichev/selectoolsWhat 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 | $0.00581 | $0.00581 |
| Opus 5 | $0.00291 | $0.00291 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
selectools-development 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Selectools Development Rules
Code Conventions
- Python 3.9+, line length 100, Black + isort formatting
- Explicit types everywhere, no
any— mypy enforced onsrc/ - No narration comments — only explain non-obvious intent
- Source layout:
src/selectools/, tests intests/ - Pre-commit hooks: black, isort, flake8, mypy, bandit, yaml check (--unsafe for mkdocs)
Testing Requirements
- Every new feature needs unit tests + integration tests
- Every bug fix needs a regression test in
tests/agent/test_regression.py - Use mock providers for unit tests, never real API calls
- Use
RecordingProviderpattern to verify exact args passed to providers - E2E tests use
@pytest.mark.e2e(skipped in CI) - Run
pytest tests/ -x -qand confirm ALL pass before any commit - Update model count assertions when adding/removing models
Feature Completeness Checklist
Every feature MUST include ALL of:
- Source code in
src/selectools/ - Public exports in
__init__.py - Unit tests in
tests/ - Example script in
examples/NN_name.py - Module doc in
docs/modules/NAME.md - Section in
notebooks/getting_started.ipynb - Entry in
docs/index.mdfeature table - Navigation entry in
mkdocs.yml - Links from relevant existing docs
Release Process
- Create feature branch:
git checkout -b feat/<name> - Implement + test + document (all checklist items above)
- Bump version in
__init__.py+pyproject.toml - Update: CHANGELOG.md, README.md ("What's New"), ROADMAP.md
- Update hardcoded counts (models, tests, examples) across ALL docs
mkdocs buildto verify no broken links- Commit, push, PR, merge to main
- Tag:
git tag -a vX.Y.Z - Push tags, build, publish to PyPI
- Verify GitHub Pages auto-deploys
Common Pitfalls
- Provider
stream()/astream()MUST passtoolsparam ToolCallobjects must not be stringified in streaming- OpenAI newer models need
max_completion_tokensnotmax_tokens response_msg.contentcan beNone— always useor ""- MkDocs links outside
docs/must use absolute GitHub URLs
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.
- yesterday First seen · 54 lines · 581 tokens per session scan A 7df06fbd8ee5
selectools-development is a cursor rule published in the GitHub repository johnnichev/selectools (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 581 tokens to every session, about $0.0029 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.
Other cursor rules, from other repositories
agentguard
AgentGuard local-first safety.
cursorrules
When working with AI agents in this project, use Authensor for safety.
llm-router
When the user asks about architecture, system design, project structure, or "how should I build X", ALWAYS use the planworkflow MCP tool first.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.