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-docsgit 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 | $0.00000 | $0.00545 |
| Opus 5 | $0.00000 | $0.00272 |
| Sonnet 5 | $0.00000 | $0.00109 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
selectools-docs 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.
What it actually says
Documentation Rules
MkDocs Site Structure
- Config:
mkdocs.yml(Material theme, tab nav, emoji, code copy) - Landing page:
docs/index.md - Module docs:
docs/modules/<NAME>.md - Guides:
docs/QUICKSTART.md,docs/ARCHITECTURE.md - Custom CSS:
docs/stylesheets/extra.css - CHANGELOG.md is copied from root at build time (not tracked in docs/)
Link Rules
- Within docs/: use relative paths (
modules/AGENT.md,../ARCHITECTURE.md) - To files outside docs/ (ROADMAP.md, examples/, notebooks/): use absolute GitHub URLs
Example:
https://github.com/johnnichev/selectools/blob/main/examples/01_hello_world.py - Anchor format for MkDocs:
#heading-text(lowercase, hyphens, no special chars)## Tool Policy & Human-in-the-Loop→#tool-policy-human-in-the-loop(not double hyphen)
When Adding a New Feature
- Create
docs/modules/<FEATURE>.mdwith full API reference and examples - Add nav entry in
mkdocs.ymlunder the appropriate tab - Update
docs/index.mdfeature table - Update
docs/README.mddocumentation index - Update
docs/QUICKSTART.md"next steps" table if user-facing - Update
docs/ARCHITECTURE.mdif it adds a new system component - Add section to
notebooks/getting_started.ipynb - Verify build:
cp CHANGELOG.md docs/CHANGELOG.md && mkdocs build
Hardcoded Counts
These appear in multiple files and MUST be updated together:
- Model count (currently 146): index.md, README.md, MODELS.md, QUICKSTART.md, ARCHITECTURE.md
- Test count: README.md, index.md, CHANGELOG.md
- Example count: README.md, index.md
- Tool count (24): index.md, README.md, TOOLBOX.md
Style
- Use admonitions (
!!! tip,!!! warning) for callouts - Use tabbed content (
=== "Tab Name") for install/usage variants - Use Material icons (
:material-icon-name:) for feature cards - Code examples should be complete and runnable
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 · 46 lines · 0 tokens per session scan A 63251713fbd8
selectools-docs is a cursor rule published in the GitHub repository johnnichev/selectools (11 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 545 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
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.