ccg-project-scout

ccg-project-scout is an agent for Claude Code from qinye6/pi-ccg. It costs 19 tokens per session (1,062 once invoked), scanned A, original, MIT.

A read-only project scout that examines a repository to identify its components, technologies, commands, dependencies, and parallel-work risks. It does not change files or run project commands.

In plain words
What is it for?
Use it before splitting a task into parallel frontend or backend work, to find ownership boundaries, shared files, contract dependencies, and likely build or test commands.
Why use it?
It gives later planning work evidence about the project's structure without risking changes or treating guesses as facts.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it before splitting a task into parallel frontend or backend work, to find ownership boundaries, shared files, contract dependencies, and likely build or test commands.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/qinye6/pi-ccg/ccg-project-scout
Install

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.

Clone the repo
git clone --depth 1 https://github.com/qinye6/pi-ccg

Made for: Claude Code.

Wrote 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.

agentmods badge for ccg-project-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/qinye6/pi-ccg/ccg-project-scout/github.svg)](https://agentmods.dev/agents/qinye6/pi-ccg/ccg-project-scout)
Your own site
<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.

agentmods 80×15 button for ccg-project-scout

Your own site · 80×15
<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>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,062 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash f4273298ba72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

templates/pi/agents/ccg-project-scout.md · 90 lines

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

  1. 使用 ls / find 观察目录结构。
  2. 使用 grep 搜索关键配置、入口、脚本、路由、构建标记。
  3. 使用 read 查看小范围关键文件。
  4. 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-apiweb-adminwechat-miniapp
  • builderKind 只能是 frontendbackend: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-adminwechat-miniprogrammobileapi-servicedb-migrationclilibraryinfra 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"]
}

Read the full file on GitHub · 90 lines

Changes

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.

  1. 8d ago First seen · 90 lines · 19 tokens per session scan A f4273298ba72

Subscribe to this mod's changes

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.