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 instructions/bubblelabai/bubblelab/claude-mdgit clone --depth 1 https://github.com/bubblelabai/BubbleLabWhat 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 | $0.00022 | $0.00022 |
| Opus 5 | $0.00011 | $0.00011 |
| Sonnet 5 | $0.00004 | $0.00004 |
| Haiku 4.5 | $0.00002 | $0.00002 |
Grade A, and why
BubbleLab CLAUDE.md 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
Read .cursor/rules/bubblelab.mdc to understand bubble lab, ALWAYS Read this before every conversation.
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 · 2 lines · 22 tokens per session scan A 40f5259686d0
BubbleLab CLAUDE.md is an instructions file published in the GitHub repository bubblelabai/BubbleLab (1,094 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 22 tokens to every session, 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 instructions, from other repositories
cs CLAUDE.md
Instructions for boyter/cs, covering claude.md, project overview, build & test commands, architecture and query pipeline (pkg/search/).
CheatSheetSeries CLAUDE.md
Claude Code instructions for OWASP/CheatSheetSeries, covering claude.md and for maintainers.
Public AGENTS.md
Instructions for TazWake/Public, covering agents.md, repository purpose, working conventions and safety.
flow-like AGENTS.md
AGENTS.md instructions for Rheosoph/flow-like, covering repository prose standard, start with the reader, voice and structure, patterns to remove and technical prose.
q-code AGENTS.md
Instructions for v833/q-code, covering q-code 项目协作说明, 项目概览, 环境与工具, 常用命令 and cli 子命令.
flow-like frontend.instructions.md
Instructions for Rheosoph/flow-like, covering project coding standards for typescript and react, typescript guidelines, react guidelines, ui framework and code quality.