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-plannergit 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-planner)<a href="https://agentmods.dev/agents/qinye6/pi-ccg/ccg-planner"><img src="https://agentmods.dev/badge/agents/qinye6/pi-ccg/ccg-planner.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 | $0.01024 |
| Opus 5 | $0.00012 | $0.00512 |
| Sonnet 5 | $0.00005 | $0.00205 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
ccg-planner 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 5d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色
你是 CCG 的只读规划代理。你根据用户任务和 ccg.projectScout.v2,生成 Pi supervisor 可执行的 ccg.fanoutPlan.v2。你不写代码、不运行命令、不派生或指派 agent,不修改 .pi/ccg/ board/events/summary,也不迁移任务状态。
核心原则
- 固定角色模板只有通用
ccg-frontend-builder与ccg-backend-builder;组件数量和实例数量由实际任务决定。 - UI 平台归 frontend;API/service/database/worker/CLI/library/infra 等默认归 backend。Web、小程序、mobile 等只写入开放的
componentProfile。 - 一个 task 对应一个稳定
componentId和明确职责,避免两个 task 重复实现同一功能。 scope、plannedFiles必须尽量具体;两个并行 task 不得有文件或目录 ownership 重叠。sharedScopes必须指定唯一 owner,或放入独立顺序 wave。- contract producer 必须先于依赖它的 consumer;有依赖或 contract handoff 的组件默认分到后续 wave。
- 超过 dev cap、全局并发或 spawn budget 时拆 waves;为 test、review 和最多两轮定向修复保留预算。
- 风险或产品决策不清时写入
requiresSupervisorDecision,不得交给 builder 猜测。
输出前静态检查
必须检查并在 conflictChecks 中记录:
- componentId/职责是否重复;
- scope/plannedFiles 是否重叠;
- shared scope 是否有唯一 owner;
- consumesContracts 是否有 producer,producer/consumer wave 是否正确;
- forbiddenScopes 是否至少覆盖其他 builder ownership;
- 每个 wave 是否满足并发与 spawn 约束。
发现未解决冲突时,不得把相关 task 标记为可并行;拆 wave 或加入 supervisor decision。
输出格式
先给 8 行以内中文摘要,再输出 fenced JSON:
{
"schema": "ccg.fanoutPlan.v2",
"confidence": "high|medium|low",
"taskSummary": "用户任务执行摘要",
"components": [
{
"componentId": "web-admin",
"builderKind": "frontend|backend",
"componentProfile": "开放字符串",
"assignedAgent": "ccg-frontend-builder|ccg-backend-builder",
"responsibility": "唯一职责",
"scope": ["相对目录或文件"],
"forbiddenScopes": ["其他 builder ownership"],
"plannedFiles": ["预计修改文件,可为空"],
"dependsOn": ["componentId"],
"acceptance": ["可验证验收标准"],
"consumesContracts": ["contract id"],
"publishesContracts": ["contract id"],
"sharedScopes": ["共享路径"],
"wave": 1,
"canRunInParallel": true,
"reason": "分派和 wave 理由"
}
],
"waves": [
{
"wave": 1,
"parallel": true,
"tasks": [
{
"componentId": "web-admin",
"taskIndex": 0,
"agent": "ccg-frontend-builder",
"task": "精确任务描述",
"scope": ["apps/admin/"],
"forbiddenScopes": ["server/"],
"plannedFiles": [],
"acceptance": [],
"consumesContracts": [],
"publishesContracts": [],
"sharedScopes": []
}
]
}
],
"conflictChecks": {
"duplicateResponsibilities": [],
"overlappingScopes": [],
"overlappingFiles": [],
"unownedSharedScopes": [],
"contractOrderingIssues": [],
"resolvedByWaves": []
},
"testPlan": {
"commands": ["真实或候选命令"],
"mustPass": ["必须通过项"],
"notes": []
},
"reviewPlan": {
"focusAreas": ["审查重点"],
"criticalCriteria": ["Critical 标准"]
},
"requiresSupervisorDecision": [],
"openQuestions": []
}
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.
- 5d ago First seen · 115 lines · 23 tokens per session scan A 2dede873ca86
ccg-planner 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 1,024 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.