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/taggartbg/bivvy/cursorgit clone --depth 1 https://github.com/taggartbg/bivvyWhat 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 | $0.00018 | $0.01999 |
| Opus 5 | $0.00009 | $0.01000 |
| Sonnet 5 | $0.00004 | $0.00400 |
| Haiku 4.5 | $0.00002 | $0.00200 |
Grade A, and why
cursor 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Description
When a user requests to start a new Climb(feature, bug, task, or exploration), you will start a 2-phase process: Step 1 is to define a Product Requirements Document (PRD) via conversation with the user; Step 2 is to build a task list (a.k.a. "Moves") from that PRD.
Once alerted, you will then begin working on the Climb, move-by-move, soliciting user feedback and approval. Moves can have "rest: true" on it, at which point you WILL ALWAYS stop after completion to check with the user on status. They can also have the status "skip" on them, in which case you will skip it and ASK the user at the end if they want to return to it. Once you reach the end of the Moves list and they've opted out of skipping, you will mark the Climb as complete in both the PRD and the Moves list, and move both files to the .bivvy/complete/ directory.
IMPORTANT RULES:
- YOU MUST STOP AND GET USER APPROVAL after:
- Creating the initial PRD draft
- Making any significant changes to the PRD
- Completing any move marked with "rest: true"
- NEVER work on tasks marked as "skip" unless explicitly requested by the user
- NEVER work ahead of the current move in the task list
- ALWAYS follow the moves in order, one at a time
File locations
- Active PRDs are found in .bivvy/[id]-climb.md (PRD) and .bivvy/[id]-moves.json (i.e. the task list).
- Completed PRDs are moved to .bivvy/complete/[id]-climb.md and .bivvy/complete/[id]-moves.json
- The [id] is a 4-character string where each character can be [A-z0-9], e.g. "02b7" or "xK4p" (enforce randomness here, also check that the id doesn't already exist in the .bivvy/complete/ directory)
Climb
IMPORTANT: When collecting information, we need to know if this is a feature, bug, task, or exploration. The top of the PRD should always be: STARTFILE [id]-climb.md
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 · 181 lines · 18 tokens per session scan A ebeb93f6fae6
cursor is a cursor rule published in the GitHub repository taggartbg/bivvy (189 stars, last pushed 17d ago), licensed MIT. It adds 18 tokens to every session and 1,999 once invoked, about $0.0001 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
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
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.
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.