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/nrl-ai/chub/cursorrulesgit clone --depth 1 https://github.com/nrl-ai/chubWhat 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 | $0.00468 | $0.00468 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
cursorrules 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
Project Rules
- This is a Rust CLI + library project (workspace with chub-core and chub-cli crates)
- Run
cargo fmt --allandcargo clippy --all -- -D warningsbefore committing - All business logic goes in chub-core; CLI/output/MCP concerns go in chub-cli
- Maintain byte-for-byte format compatibility with the original JS Context Hub
- Use serde(rename) attributes to keep camelCase JSON field names
- Tests are inline #[cfg(test)] blocks, not separate test files (except integration tests)
- Do not add Co-Authored-By trailers to commits
Pinned Documentation
Use chub get <id> to fetch these docs when working with these libraries:
- serde/derive (rust) — Core serialization framework — used everywhere for JSON/YAML
- clap/derive (rust) — CLI argument parsing with derive macros
- tokio/runtime (rust) — Async runtime for MCP server and HTTP serving
- axum/routing (rust) — HTTP framework for chub serve
Project Context
Use chub get project/<name> or ask Chub for these:
- project/architecture — Crate layout, data flow, and key design decisions
- project/conventions — Rust coding standards and patterns used in this project
- project/team-features — How team features work and how to extend them
Module: cli (crates/chub-cli/**)
- Each command in its own file under src/commands/
- Use owo-colors for terminal output, support --json flag on all commands
- MCP tools use schemars::JsonSchema for parameter schema generation
Module: core (crates/chub-core/**)
- No CLI concerns (no stdout/stderr, no clap, no owo-colors)
- All public functions return Result using crate::error::Error
- Search pipeline: tokenizer -> BM25 -> inverted index -> lexical boost
Module: team (crates/chub-core/src/team/**)
- Team features live in .chub/ directory (git-tracked)
- Three-tier config: ~/.chub/ -> .chub/ -> .chub/profiles/
- All team modules must work gracefully when .chub/ doesn't exist
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 · 38 lines · 468 tokens per session scan A d71666e14362
cursorrules is a cursor rule published in the GitHub repository nrl-ai/chub (11 stars, last pushed 5mo ago), licensed MIT. It adds 468 tokens to every session, about $0.0023 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
cursorrules
Cursor rule "cursorrules" from Wolfe-Jam/faf-cli, covering faf:start, .cursorrules, authored from project.faf — faf-cli v6, stack and faf:end.
matt-skills-core
Matt Pocock skills as the primary coding workflow router.
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.