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/bullboy1/babycoding/frpgit clone --depth 1 https://github.com/bullboy1/babycodingWhat 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 | $0.02560 | $0.02560 |
| Opus 5 | $0.01280 | $0.01280 |
| Sonnet 5 | $0.00512 | $0.00512 |
| Haiku 4.5 | $0.00256 | $0.00256 |
Grade A, and why
frp 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rules — Function Registry Protocol (FRP) v1.4
Mandatory for every task in this repo. Goals: zero duplicate code, minimal token spend, clean layered architecture.
0. Session start
- Read
FUNCTIONS.md. If Stage 3 (sharded): read root index + only the shards of modules this task touches. - No
FUNCTIONS.md→ run §6 Bootstrap before anything else. - Function count crossed a §7 threshold → perform that stage upgrade within this task.
- Canvas on → read
docs/registry/inbox.mdif present; pending entries are user requests sent from the canvas: do them first, mark each[done YYYY-MM-DD]when finished.
1. Lookup — before writing ANY function
- Search
FUNCTIONS.md(name + desc columns) by capability keywords. - HIT → grep the code to confirm existence and signature → REUSE. Reimplementing a registered capability is a protocol violation.
- NEAR-HIT (covers ≥80% of the need) → EXTEND the existing function (add a param/option). Do not create a sibling.
- MISS → create, following §2–§4.
- Mandatory trace — print one line per decision in your reply, before writing code:
REGISTRY: HIT parseDate (L1) src/utils/time.pyREGISTRY: EXTEND fetchOrder (L3) src/orders/api.py — add includeDrafts flagREGISTRY: MISS -> new renderBadge (L2) src/ui/badge.tsx
2. Creation rules
- Names: verb+noun, repo's dominant casing (
parseInvoice/parse_invoice). Searchable; no abbreviations except: id, url, db, cfg, ctx. - One function, one responsibility. Function ≤ 50 lines. File ≤ 300 lines. Nesting ≤ 3 levels.
- Rule of Three: a 2nd duplication is tolerated; the 3rd MUST be extracted into a shared L1/L2 component and registered.
- Folders: depth ≤ 4 from repo root, lowercase, named by domain/feature — never by person, date, or version.
- Imports flow downward only: L4 → L3 → L2 → L1. L1 imports no project code. An upward import is a bug.
- Shared constants/types obey the same lookup-before-create rule (grep first).
- Comments explain WHY, never WHAT. One-line docstring required on L1/L2; on L3/L4 only when non-obvious.
- Minimal diff: touch nothing outside task scope. No drive-by refactors.
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 · 111 lines · 2,560 tokens per session scan A 653516b7734d
frp is a cursor rule published in the GitHub repository bullboy1/babycoding (4 stars, last pushed 1mo ago), licensed MIT. It adds 2,560 tokens to every session, about $0.0128 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 cursor rules, from other repositories
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.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.