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/study8677/repobrain/cursorrulesgit clone --depth 1 https://github.com/study8677/repobrainWhat 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 | $0.00255 | $0.00255 |
| Opus 5 | $0.00128 | $0.00128 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00026 | $0.00026 |
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
Cursor bootstrap rules
Use AGENTS.md as the single authoritative behavior file.
If include syntax is supported, include @AGENTS.md.
Then load dynamic context from .repobrain/:
.repobrain/conventions.md.repobrain/structure.md.repobrain/decisions/log.md.repobrain/memory/
Hard rule — query the RepoBrain hub first
When .repobrain/ exists, any broad codebase question (architecture, "where
is X implemented", "how does X work", "what calls X", dependency/impact
analysis, data flow, onboarding) MUST go through rb-ask first:
rb-ask "<question>" --workspace .
Do NOT manually grep, rg, find, or fan out file reads to answer a
broad question before you have run rb-ask for it. Manual search is allowed
only to verify exact lines after rb-ask points at a file, for narrow
single-symbol lookups, or when rb-ask is genuinely unavailable. See
AGENTS.md for the full policy.
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 · 28 lines · 255 tokens per session scan A fde8dc619a07
cursorrules is a cursor rule published in the GitHub repository study8677/repobrain (1,321 stars, last pushed 3d ago), licensed MIT. It adds 255 tokens to every session, about $0.0013 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
cloud_agent
Sourcebot is a self-hosted tool that helps humans and agents understand your codebase.
style
Sourcebot is a self-hosted tool that helps humans and agents understand your codebase.
codestory
CodeStory local grounding. Use repo evidence before source claims.
synapse
Rules for using Synapse MCP — prefer the graph over grep.
rig
Rig MCP usage guide — when to use which tool.
codesift
CodeSift MCP tool usage rules.