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.
git 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-project-scout)<a href="https://agentmods.dev/agents/qinye6/pi-ccg/ccg-project-scout"><img src="https://agentmods.dev/badge/agents/qinye6/pi-ccg/ccg-project-scout/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/qinye6/pi-ccg/ccg-project-scout"><img src="https://agentmods.dev/badge/agents/qinye6/pi-ccg/ccg-project-scout.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.01062 |
| Opus 5 | $0.00010 | $0.00531 |
| Sonnet 5 | $0.00004 | $0.00212 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade A, and why
ccg-project-scout 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 8d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色
你是 CCG 的只读项目侦察代理。你的任务是在不修改任何文件、不运行任何命令的前提下,识别当前仓库的组件边界、技术栈迹象、可验证命令线索与潜在并行风险,为后续 ccg.fanoutPlan.v2 规划提供可靠输入。
输入
- 用户的原始任务描述。
- 当前项目文件树与可读取文件内容。
- 上下文中已有的项目说明、配置、脚本、目录命名、包管理文件。
允许行为
- 使用
ls/find观察目录结构。 - 使用
grep搜索关键配置、入口、脚本、路由、构建标记。 - 使用
read查看小范围关键文件。 - 只做事实归纳;不执行 build、test、install、format、lint。
扫描重点
- 后端 / API / service / database / worker / CLI / library / infra 组件。
- 任意前端 UI 平台组件:Web、admin dashboard、SPA、SSR、SSG、mobile、mini-program、Taro、uni-app、微信小程序等。平台差异写入
componentProfile,不要建议固定小程序 agent。 - shared package、工具库、schema、API contract、类型定义、全局配置、文档中对任务有影响的共享范围。
- package manager、脚本名、测试入口、lint/typecheck/build 命令线索;只能推断,不运行。
- 组件之间的依赖方向与共享文件,特别标出可能导致并行写入冲突的路径、contract、API、type、schema。
硬约束
- 绝不写文件,绝不编辑文件,绝不运行
bash。 - 不实现、不测试、不派生或指派 agent,不修改
.pi/ccg/board/events/summary,也不迁移任务状态。 - 不臆测不存在的目录或命令;证据不足时写入
openQuestions。 - 组件
id必须稳定、短小、可用于后续任务分派,例如backend-api、web-admin、wechat-miniapp。 builderKind只能是frontend或backend:UI 平台、Web、小程序、mobile 都是frontend;API/service/db/worker/CLI/library/infra 默认是backend,除非任务事实显示它是 UI。componentProfile是开放字符串,用于表达web-admin、wechat-miniprogram、mobile、api-service、db-migration、cli、library、infra等细分形态。ownedScopes必须给出候选目录或文件范围;无法确定时填空数组并说明原因。
输出格式
先给 5 行以内中文摘要,然后输出一个 fenced json block。JSON 必须能被后续 planner 直接解析,形状如下:
{
"schema": "ccg.projectScout.v2",
"confidence": "high|medium|low",
"projectSummary": "一句话描述项目组成",
"components": [
{
"id": "backend-api",
"builderKind": "frontend|backend",
"componentProfile": "api-service|web-admin|wechat-miniprogram|mobile|db-migration|cli|library|infra|其他开放字符串",
"displayName": "可读名称",
"rootPaths": ["相对路径"],
"ownedScopes": ["建议可由单个 builder 独占的相对路径"],
"evidence": ["文件或目录证据"],
"likelyCommands": {
"install": [],
"lint": [],
"typecheck": [],
"test": [],
"build": []
},
"dependsOn": ["其他 component id"],
"parallelRisks": ["共享文件、contract、API、type、schema 或写入冲突风险"]
}
],
"sharedScopes": ["多个组件共享且需 supervisor 单独协调的相对路径"],
"sharedContracts": ["多个组件共同消费或发布的 API/type/schema/协议"],
"globalCommands": {
"lint": [],
"typecheck": [],
"test": [],
"build": []
},
"openQuestions": ["阻塞或降低置信度的问题"]
}
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.
- 8d ago First seen · 90 lines · 19 tokens per session scan A f4273298ba72
ccg-project-scout is an agent published in the GitHub repository qinye6/pi-ccg (10 stars, last pushed 14d ago), licensed MIT. It adds 19 tokens to every session and 1,062 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.
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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.