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/joinwell52-ai/codeflowmu-open/fcop-rulesgit clone --depth 1 https://github.com/joinwell52-AI/CodeFlowMu-openWhat 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 | $0.21132 | $0.21132 |
| Opus 5 | $0.10566 | $0.10566 |
| Sonnet 5 | $0.04226 | $0.04226 |
| Haiku 4.5 | $0.02113 | $0.02113 |
Grade A, and why
fcop-rules 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.
This is a copy
97% identical to fcop-rules — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FCoP Rules · FCoP 协议规则
本文件定义 FCoP 协议的规则，由
fcopMCP 自动部署。 这些规则在具体场景里怎么用——文件怎么命名、YAML 怎么写、目录怎么组织、 巡检怎么触发——属于协议解释，见同目录的fcop-protocol.mdc。 两个文件冲突时，以本文件为准。This file defines the rules of the FCoP protocol. It is auto-deployed by the
fcopMCP. How each rule actually applies in practice — file naming, YAML shape, directory layout, patrol triggers — is the job of the protocol commentary infcop-protocol.mdc(same directory). In case of conflict between the two, this file wins.
目的 / Purpose
让 Agent 通过 FCoP 与团队协同工作。
Enable agents to coordinate with a team via FCoP.
"团队"可以是多 Agent 多角色，也可以是单 Agent（solo 模式）。任何情况下：
- 协作走文件（Rule 0.a）
- 决策与执行不能由同一个角色独自完成（Rule 0.b）
- 落到文件里的必须是真的（Rule 0.c）
A "team" can be multi-agent/multi-role or single-agent (solo). In every
case: coordination goes through files (Rule 0.a), no single role completes
decision-plus-execution alone (Rule 0.b), and what gets landed in a file
must be truthful (Rule 0.c).
FCoP 的定位与七大核心概念 / Protocol Position & Seven Core Concepts
协议层定位 / Protocol Layer
FCoP 是多 Agent 协作中的行为治理协议层——约束 Agent 行为，而非调度任务。 它定义 Agent 如何"说清楚自己在做什么"，以及"别人如何验证它做过什么"。 三件核心事：让行为可见（report）、让行为可审计（review）、让行为可约束（capability governance）。
FCoP is the behavior governance protocol layer for multi-agent collaboration — governing agent behavior, not scheduling tasks. It defines how agents declare what they are doing, and how others verify what they have done. Three core responsibilities: observability (report), auditability (review), capability governance.
┌─────────────────────────────────────────────────────┐
│ 应用层 / Application Layer │
│ CodeFlow / Cursor / Claude Desktop │
├─────────────────────────────────────────────────────┤
│ 宿主适配层 / Host Adapter Layer │
│ fcop-mcp / fcop-cli / @fcop/claude │
├─────────────────────────────────────────────────────┤
│ ★ FCoP 协议层 ★ ← 本协议所在层 │
│ Agent 协作 / 行为报告 / Review / │
│ Capability Governance / 事件语义 / 审计边界 │
├─────────────────────────────────────────────────────┤
│ 参考实现层 / Reference Implementation │
│ fcop（Python Library） │
├─────────────────────────────────────────────────────┤
│ 执行基底 / Execution Substrate │
│ LLM APIs / MCP Tools / 文件系统 / OS │
│ （FCoP 治理行为，不拥有执行层） │
└─────────────────────────────────────────────────────┘
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 · 1,360 lines · 21,132 tokens per session scan A 24f42cfe7606
fcop-rules is a cursor rule published in the GitHub repository joinwell52-AI/CodeFlowMu-open (2 stars, last pushed 8d ago), licensed MIT. It adds 21,132 tokens to every session, about $0.1057 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to fcop-rules, differing in 4 lines, and is treated as a copy.
Other cursor rules, from other repositories
architecture-constraints
GolemBot architecture hard constraints — must check before modifying any src/ code.
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.
model-compatibility
Model compatibility guide: prompt hierarchy, M3-first model selection, tool discipline, read-before-edit safety, and context control across models.
moyu
当检测到过度工程模式时自动激活：修改用户未要求的代码、创建不必要的抽象层、 添加未要求的注释/文档/测试、引入不必要的依赖、重写整个文件而非最小编辑、 diff 超出请求范围。用户说"太多了"、"只改 X"、"简单点"时触发。 Activates on over-engineering: modifying unrequested code, unnecessary abstractions, unsolicited comments/docs/tests, unrequested dependencies, full file rewrites, scope-exceeding diffs. Triggers on "too…
context_gathering
Standardized patterns for gathering and processing context from multiple sources in Task Master commands, particularly for AI-powered features.
skill-and-agent-references
Reference skills, agents, and commands by their registered name (never by filesystem path), and decompose oversized commands or agents by extracting sections into skills with by-name references.