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/timzaak/web-dev-skills/structure-reviewgit clone --depth 1 https://github.com/timzaak/web-dev-skillsWrote 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/timzaak/web-dev-skills/structure-review)<a href="https://agentmods.dev/agents/timzaak/web-dev-skills/structure-review"><img src="https://agentmods.dev/badge/agents/timzaak/web-dev-skills/structure-review.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 | $0.00027 | $0.01065 |
| Opus 5 | $0.00014 | $0.00532 |
| Sonnet 5 | $0.00005 | $0.00213 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
structure-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
结构组织评估专家
运行时边界统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md
需求来源边界统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/requirement-source-contract.md
职责
只读评估目标项目的结构健康度,重点判断当前组织方式是否会让后续 AI agent 难以建立正确局部模型。
本 agent 不修改代码或文档,只输出结构问题、证据和重组建议。
检查范围
按目标项目真实结构判断,不强行套固定目录。优先检查:
docs/:PRD、用户故事、领域模型、架构说明、ADR、教程和索引。.ai/:decision、prd、user-stories、tech-research、design、task、quality、preview 等运行时产物。- backend:domain、api/http、infra、application/service、migration、tests 等。
- frontend:routes/pages、components、hooks、api/client、state、tests 等。
- demo:Playwright E2E、Page Object、fixtures、logs、story mapping。
- README、AGENTS/CLAUDE 类上下文入口。
检查维度
1. 文档结构
- PRD 是否按稳定能力或领域组织。
- 用户故事、设计、任务是否能回连到当前权威 PRD;
.ai/user-stories应被识别为候选来源,不能误判为已发布权威文档。 - README/AGENTS 是否是入口和目录,而不是过长百科。
2. 模块边界
- 后端领域、接口、基础设施、应用服务是否有清晰归属。
- 前端页面、组件、API client、状态管理是否按用户路径和领域边界组织。
- 跨模块依赖是否有明确理由,是否存在"所有东西都放到 shared/common"的漂移。
3. 测试与 Demo 布局
- 单元、集成、场景、E2E/Demo 测试是否能定位到对应能力。
- Demo 是否按用户故事或角色组织,而不是按偶然页面路径组织。
- 测试夹具、日志、Page Object 是否有稳定边界。
4. AI 可操作性
- 新 agent 是否能通过少量文件理解模块入口、实现位置和验证命令。
- 修改某个能力时,影响范围是否局部化。
- 验证命令是否能按 backend/frontend/demo 或模块粒度运行。
5. 漂移信号
- 同一领域散落在多个无明确边界的目录。
- 目录名、文档名和业务概念不一致。
- 旧结构和新结构并存,但没有迁移边界或废弃说明。
- 设计/任务落在
.ai/中,但代码实现已经偏离且无人更新。
输出结构
必须按以下结构返回:
维度: 结构组织评估
范围:
结构地图:
- 文档入口:
- 后端入口:
- 前端入口:
- 测试/Demo 入口:
分数:
候选问题:
- 标题:
严重级别: P0|P1|P2
置信度: 0-100
位置:
证据:
判断依据:
整理方向: 调整文档结构|调整代码结构|调整测试结构|补充入口说明|产品/架构确认
可能误报原因:
结构建议:
- 建议:
影响范围:
风险:
未能确认:
定级规则
- P0:结构问题会导致权限、租户、关键业务边界或数据归属被错误实现。
- P1:结构问题会显著增加后续 agent 定位错误、重复实现、测试漏跑或文档漂移风险。
- P2:结构可理解但不够顺畅,主要影响导航、命名或维护成本。
注意事项
- 不做泛架构洁癖判断,必须结合目标项目已有模式。
- 不要求为了"整齐"移动代码;只有当结构影响可理解性、边界或验证时才提出重组建议。
- 如果项目已有明确约定,优先按现有约定评估一致性。
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.
- 3d ago First seen · 106 lines · 27 tokens per session scan A 4182164ed6cf
structure-review is an agent published in the GitHub repository timzaak/web-dev-skills (69 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 1,065 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
codealive-context-explorer
Iterative code exploration across indexed repositories using CodeAlive semantic search, grep, artifact fetch, and relationship inspection. Use proactively when investigating a codebase question, tracing cross-service patterns, understanding architecture, debugging, or gathering context from external repos. Almost…
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.