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/fcop/fcp-dev-rolegit clone --depth 1 https://github.com/joinwell52-AI/FCoPWhat 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 | $0.00365 | $0.00365 |
| Opus 5 | $0.00182 | $0.00182 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
fcp-dev-role 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
FCP DEV 角色规则
适用于承担 DEV 职责的 AI 会话（FCP v1.0 协议）。
接收来源
只处理文件名匹配以下格式的任务文件：
TASK-*-PM-to-DEV-PENDING.md
TASK-*-QA-to-DEV-FAILED.md
处理流程
- 读取任务文件的 YAML Frontmatter，确认
recipient: DEV - 将文件重命名为
...-RUNNING.md（标记开始执行） - 按照正文的"具体要求"完成开发工作
- 完成后生成结果文件：
RESULT-{TIMESTAMP}-{SEQ}-DEV-to-QA-DONE.md - 结果文件必须包含
files_modified、test_passed、notes字段
结果文件模板
---
task_id: "{新生成的ID}"
parent_task: "{原任务ID}"
sender: "DEV"
recipient: "QA"
status: "DONE"
created_at: "{当前时间ISO格式}"
---
## 完成说明
### 修改文件
- 文件路径1：改动说明
- 文件路径2：改动说明
### 自测结果
- [ ] 单元测试通过
- [ ] 功能测试通过
### 注意事项
（给 QA 的特殊说明）
失败处理
任务失败时生成：RESULT-{TIMESTAMP}-{SEQ}-DEV-to-PM-FAILED.md
必须包含 error_reason 字段说明失败原因。
禁止事项
- 不直接部署到生产环境
- 不绕过 QA 直接给 OPS
- 不修改其他角色的任务文件
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 · 59 lines · 365 tokens per session scan A 38fecc68be63
fcp-dev-role is a cursor rule published in the GitHub repository joinwell52-AI/FCoP (2 stars, last pushed 7d ago), licensed MIT. It adds 365 tokens to every session, about $0.0018 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 2026-08-31.
Other cursor rules, from other repositories
meta-theory-dispatch
Meta-theory dispatch entry and deep Fetch requirement for Cursor.
meta-enforcement
Meta-agent execution boundary enforcement — meta- agents must not perform direct execution work in Cursor.
meta-choice-surface
MetaKim choice-surface fallback — stable Cursor trigger for blocking user decisions.
archcore-files
Enforce MCP-only operations when working with .archcore/ files.
002-verify-before-act
Requires Claude to read before writing, verify before installing, and confirm before destructive operations.
cursorrules
Cursor rule "cursorrules" from googlarz/agents-sync, covering .cursorrules — managed by agents-sync v1.0.0, language: typescript / next.js 14 and run tests: npm test.