Borrowing it
Nothing to install: this file belongs to qinye6/pi-ccg. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/qinye6/pi-ccg/main/CLAUDE.mdgit clone --depth 1 https://github.com/qinye6/pi-ccgWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/qinye6/pi-ccg/claude-md)<a href="https://agentmods.dev/instructions/qinye6/pi-ccg/claude-md"><img src="https://agentmods.dev/badge/instructions/qinye6/pi-ccg/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03169 | $0.03169 |
| Opus 5 | $0.01584 | $0.01584 |
| Sonnet 5 | $0.00634 | $0.00634 |
| Haiku 4.5 | $0.00317 | $0.00317 |
Grade A, and why
pi-ccg 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CCG for Pi CLI
Last Updated: 2026-08-25 (v3.2.8)
当前架构为 Pi-only。历史变更见 CHANGELOG.md。
项目定位
CCG 为 Pi CLI 提供动态、有上限的智能开发工作流。Pi 是唯一 supervisor,不再由 Claude 主控,也不再通过 Codex/Gemini wrapper 充当固定外部角色。
标准流程:
ccg-project-scout
→ ccg-planner
→ supervisor contract relay + START approval
→ Pi 动态 builder fanout(N frontend + M backend,按 component/profile/wave)
→ builder FINISH handoff
→ ccg-test-runner
→ ccg-reviewer
→ componentId 定向修复(最多 2 轮)
六个 Pi role templates
| Role template | 责任 |
|---|---|
ccg-project-scout |
只读项目/组件发现 |
ccg-planner |
组件拆分、文件边界、ownership、依赖、waves、测试计划 |
ccg-backend-builder |
通用后端、服务、API、数据与基础设施组件 |
ccg-frontend-builder |
通用前端组件;Web、管理后台、小程序/微信等通过 componentProfile 区分 |
ccg-test-runner |
测试、typecheck、lint、build |
ccg-reviewer |
独立正确性、质量、安全审查 |
ccg-miniprogram-builder 已退休,不属于当前 active runtime。小程序/微信只作为 frontend componentProfile,由通用 ccg-frontend-builder 实例处理。
模型映射:
frontendModel → generic ccg-frontend-builder instances
backendModel → generic ccg-backend-builder instances
reviewModel → ccg-reviewer + ccg-test-runner
scout/planner → Pi subagents.defaultModel
动态 fanout 上限
effectiveDevParallelism = min(
devAgentCap,
globalConcurrencyLimit,
parallel.concurrency,
parallel.maxTasks
)
requiredSpawns = 2 + (N_frontend + M_backend) + 1 + 1
默认:
devAgentCap = 4
globalConcurrencyLimit = 4
maxSpawnsPerSession = 24
maxSubagentDepth = 1
所有 CCG agents 使用 defaultContext: fresh;supervisor 以 context: "fresh" 调用。跨 run 的 plan/build/test context 必须内联进 task string,不能依赖另一个 run 的相对 reads。
Supervisor 协调规则
ccg-planner输出稳定componentId、component/profile、文件 ownership、依赖 waves、测试计划和修复路由。- Pi supervisor 在 builder 写入前 relay contract,并等待 supervisor
STARTapproval。 - Pi 按 wave 派生 builder 实例;同一 wave 的有效并发不得超过 caps。
- 每个 builder 只修改自己 ownership 范围内的文件;跨组件变更必须回报 supervisor。
- 每个 builder 完成时必须返回
FINISHhandoff,包含componentId、变更文件、验证、假设和风险。 - test-runner/reviewer 的失败必须携带
componentId,供 Pi 定向回派 owning builder。 - componentId 定向修复最多两轮。
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.
- 6d ago First seen · 250 lines · 3,169 tokens per session scan A 0c73d3d5237f
pi-ccg CLAUDE.md is an instructions file published in the GitHub repository qinye6/pi-ccg (10 stars, last pushed 12d ago), licensed MIT. It adds 3,169 tokens to every session, about $0.0158 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.