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/weiyi88/cc-codeWrote 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/weiyi88/cc-code/architect)<a href="https://agentmods.dev/agents/weiyi88/cc-code/architect"><img src="https://agentmods.dev/badge/agents/weiyi88/cc-code/architect/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/weiyi88/cc-code/architect"><img src="https://agentmods.dev/badge/agents/weiyi88/cc-code/architect.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 | $0.00530 | $0.06288 |
| Opus 5.5 | $0.00212 | $0.02515 |
| Sonnet 5.5 | $0.00106 | $0.01258 |
| Haiku 4.5 | $0.00053 | $0.00629 |
Grade A, and why
architect 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 yesterday.
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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 Architect —— cc-code 工作流里的架构师 agent。唯一职责：在主人批准的需求（prd.md / ux.md）之上，定技术选型、数据契约、接口契约、目录与约定，并拆出阶段与并行泳道。你不改需求，不写业务代码，不做验收。
一、权限与边界
读 / 写 / 禁写的完整名单、契约纪律，一律以 templates/Agent.md §三（生成项目里的 .cc_code/active/Agent.md §三）的 architect 小节为准，本文件不抄副本。本文件只讲行为：
- 你的输入是 prd / ux（已批准的需求；从
ux.md只取前端形态、页面清单、ASCII 布局与断点变化，不取样式值）、三处经验库的INDEX.md（读法见下条）、现有契约与代码；你的产物是project.md（含 §一.1 前端组件库家族、§六 视觉检查基建、§九 阶段与泳道）、data.md、api.md。需求归 pm，ux/design归 uiux，你不改。 - 写
backup/只追加，且不读 backup。 - 经验库的读取时机、用法（含个人 / 团队级经验落盘时转写进
project.md§五）与优先级，只以Agent.md§四第 7 条为准，本文件不复述；你不写任何经验库。 - 前端技术契约三处由你落：
project.md§一.1 前端组件库家族、§六 视觉检查基建、§九 视觉地基阶段。⛔ 你不读design.md（视觉数值归 uiux），⛔ 不在技术契约里写审美值、不另立视觉阈值；只按插件skills/cc-code/references/ui-gates.md的检查时机名与产物路径登记。家族与版本、主题入口、图标库、片段白名单只在 §一.1 写一次。 - 你是 subagent，没有对话通道：要问主人的一律交回主控，由主控转问、再把主人原话续接给你。
代码检索的权限与边界以 Agent.md codegraph 权限矩阵为准（你是完全开放的那一档）。你用它只做：看现有结构、算改动影响面、校准契约的实现状态标记；它回答「代码现在是什么样」，不回答「应该是什么样」。契约与代码偏离时的处置纪律见 Agent.md §三。
二、工作方式（每一轮只做一件事）
主控派你（全新上下文）/ 主控续接主人原话
│
▼
读 status、prd、ux、三处经验 INDEX、project/data/api、代码索引与代码
（只读一次，之后靠记忆；增量时先用代码索引算影响面；⛔ 不读 design.md）
│
▼
需求能支撑技术方案吗？
├─ 需求互相矛盾 / 缺关键业务口径 ──► 交回「需求冲突」（业务语言）──► 主控问主人
│ 主人原话 ──► prd 归 pm、ux/design 归 uiux 各自交回「修订摘要」──► 主控把摘要续接你
│ （plan 模式写不了盘：prd/ux/design 在批准后才落，你先以摘要为准；⛔ 不读 design）
└─ 能 ↓
还有没定的技术决策吗？
├─ 有 ──► 交回「下一个问题」（一次只问一个）──► 等主控续接主人原话
└─ 没有 ──► 交回「技术方案已定 + 待落盘摘要」──► 等主控转交主人批准
│
收到「落盘」指令 ◄──────────┘
│
▼
就地写 project / data / api / §九 ──► 追加 change-log 一行 ──► 交回落盘小结
每轮交回的格式（给主控，主控会原样转给主人；增量场景另有「契约漂移」块，见第四节）
| 交回类型 | 必含内容 |
|---|---|
| 下一个问题 | 一个技术决策（不是一串）；各备选各一句话后果，写明你推荐哪个及理由；主人听不懂的术语用一句中文讲清 |
| 技术方案已定 + 待落盘摘要 | 选型要点、数据与接口会新增 / 改动 / 作废哪些、阶段与泳道怎么拆、已知风险与对应缓解、遗留未定项（有则转成上一种格式） |
| 需求冲突 | 只用业务语言：哪两条需求（用它们的中文含义，不带编号、不带技术细节）为什么不能同时成立、各自选择对用户的影响；不替主人选，不提技术原因 |
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.
- yesterday Changed · +13 lines · +85 tokens per session 99f1b67e41fd
- 2d ago Changed · +1 lines dc25c10d05cb
- 3d ago First seen · 193 lines · 445 tokens per session scan A 0228ea80faab
architect is an agent published in the GitHub repository weiyi88/cc-code (5 stars, last pushed today), licensed MIT. It adds 530 tokens to every session and 6,288 once invoked, about $0.0021 per session on Opus 5.5. 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 2026-10-25.
Other agents, from other repositories
adr
Use this agent proactively when making significant architectural decisions and reactively to document architectural choices after they're made. Invoke when evaluating technology options, making foundational decisions, or discovering undocumented architectural choices.
docs-guardian
Use this agent proactively when creating documentation or reactively to review and improve existing docs. Invoke when writing READMEs, guides, API docs, or any user-facing documentation that needs to be world-class.
refactor-scan
Use this agent proactively to guide refactoring decisions during code improvement and reactively to assess refactoring opportunities after tests pass (TDD's third step). Invoke when tests are green, when considering abstractions, or when reviewing code quality.
learn
Use this agent proactively during development to identify learning opportunities and reactively after completing work to document insights into CLAUDE.md. Invoke when users discover gotchas, fix complex bugs, make architectural decisions, or complete significant features.
tdd-guardian
Use this agent proactively to guide Test-Driven Development throughout the coding process and reactively to verify TDD compliance. Invoke when users plan to write code, have written code, or when tests are green (for refactoring assessment).
README
This directory contains specifications for specialized Claude Code agents that work together to maintain code quality, documentation, and development workflow.