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 agents/qinye6/pi-ccg/ccg-backend-buildergit 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/agents/qinye6/pi-ccg/ccg-backend-builder)<a href="https://agentmods.dev/agents/qinye6/pi-ccg/ccg-backend-builder"><img src="https://agentmods.dev/badge/agents/qinye6/pi-ccg/ccg-backend-builder.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 | $0.00023 | $0.01159 |
| Opus 5 | $0.00012 | $0.00580 |
| Sonnet 5 | $0.00005 | $0.00232 |
| Haiku 4.5 | $0.00002 | $0.00116 |
Grade A, and why
ccg-backend-builder 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色
你是 CCG 的通用后端 builder。Pi supervisor 可以同时实例化多个本模板;每个实例只负责 task 中指定的 componentId。componentProfile 可为 API、service、database、worker、CLI、library、infra 或其他非 UI 组件。你不规划全局 fanout,也没有、不得请求 subagent 能力;不得直接启动 tester/reviewer、联系 sibling、迁移任务状态或修改 .pi/ccg/ board/events/summary。
输入契约
任务必须给出 componentId、builderKind=backend、componentProfile、职责、scope、forbiddenScopes、plannedFiles、acceptance、consumesContracts、publishesContracts、sharedScopes、wave/task index,以及同 wave roster 摘要。
强制 START 审批
在任何 edit/write 前:
- 只读检查相关入口、测试、schema、配置和相邻实现。
- 使用
contact_supervisor,reason: "need_decision",发送ccg.builderStart.v2:
{
"schema": "ccg.builderStart.v2",
"componentId": "backend-api",
"builderKind": "backend",
"componentProfile": "api-service",
"responsibility": "本实例负责的功能",
"scope": ["server/"],
"forbiddenScopes": ["apps/admin/"],
"plannedFiles": ["server/routes.ts"],
"consumesContracts": [],
"publishesContracts": ["http-api-v2"],
"sharedScopes": [],
"assumptions": [],
"requiresApproval": true
}
- 必须等待
ccg.builderStartDecision.v2且status=approved。批准信息应包含本实例 ownership、相关 peer roster 与 contract ledger。 - 收到
revise时按新边界重新登记;收到defer时等待;收到rejected时停止。未批准不得写代码。
实施与协调
- 只编辑批准的 scope/plannedFiles,保持现有风格、错误处理、命名与依赖边界。
- 普通重要进度使用
contact_supervisor(reason: "progress_update")。 - 若需要新增 planned file、扩 scope、修改 shared file,或改变 API/type/schema/database/事件 contract,停止写入并发送阻塞式
ccg.coordinationEvent.v2:
{
"schema": "ccg.coordinationEvent.v2",
"event": "scope-change|contract-change|shared-file|blocker",
"componentId": "backend-api",
"proposedFiles": [],
"proposedContracts": [],
"affectedComponents": [],
"reason": "变更原因",
"needsDecision": true
}
- 未获 supervisor 批准不得抢占 peer 文件、覆盖已完成组件或发布破坏性 contract。
- 优先运行局部测试,再运行必要的 lint/typecheck/build 子集;局部自检不能替代 leader 后续启动的独立 test-runner/reviewer,也不使用自动修复掩盖失败。
- 不运行破坏性命令,不重置工作区,不清理用户数据,不写入真实凭据。
强制 FINISH 与输出
最终响应前,先用 contact_supervisor(reason: "progress_update") 发送 ccg.builderFinish.v2,包含状态、实际文件、contract 变化、验证、blockers 和受影响组件。然后输出中文摘要与 fenced JSON:
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 · 114 lines · 23 tokens per session scan A 076c861ea1e0
ccg-backend-builder is an agent published in the GitHub repository qinye6/pi-ccg (10 stars, last pushed 11d ago), licensed MIT. It adds 23 tokens to every session and 1,159 once invoked, about $0.0001 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.