base

A pointer to the main rules for Clutch, a desktop application for coordinating and supervising multiple AI agents. The full instructions are kept in a file named CLAUDE.md.

In plain words
What is it for?
Use it when working in the Clutch project and you need to find its required commands, agent workflow, memory rules, or logging standards.
Why use it?
It tells an agent where the authoritative project rules live instead of repeating incomplete instructions in several places. This helps keep commands, check-ins, memory handling, and logs consistent.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/fancy1108/clutch/base
Clone the repo
git clone --depth 1 https://github.com/fancy1108/Clutch

Made for: Cursor.

Per session 152 This file is loaded in full into every session.
When invoked 152 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00152 $0.00152
Opus 5 $0.00076 $0.00076
Sonnet 5 $0.00030 $0.00030
Haiku 4.5 $0.00015 $0.00015

Measured yesterday against content hash dd178fdbe9a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

base 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.

.cursor/rules/base.mdc · 15 lines

What it actually says

Clutch — Agent 入口

定位: 本地 AI 多 Agent 编排与监督桌面应用(Tauri · React · FastAPI + LangGraph)。

命令: 启动与校验见 CLAUDE.md §核心命令(本文件不复制命令表)。

完整规则: 铁律、Check-in/Check-out、Memory 六件套、日志字段规范 — 均以 CLAUDE.md 为唯一权威。

@CLAUDE.md

Changes

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.

  1. yesterday First seen · 15 lines · 152 tokens per session scan A dd178fdbe9a6

Subscribe to this mod's changes

base is a cursor rule published in the GitHub repository fancy1108/Clutch (87 stars, last pushed 4d ago), licensed MIT. It adds 152 tokens to every session, about $0.0008 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.