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 skills/silenceinsect/aidocxworkflow/aidocx-s3-prototypenpx skills add SilenceInsect/AIDocxWorkFlow --skill aidocx-s3-prototypegit clone --depth 1 https://github.com/SilenceInsect/AIDocxWorkFlowWrote 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/skills/silenceinsect/aidocxworkflow/aidocx-s3-prototype)<a href="https://agentmods.dev/skills/silenceinsect/aidocxworkflow/aidocx-s3-prototype"><img src="https://agentmods.dev/badge/skills/silenceinsect/aidocxworkflow/aidocx-s3-prototype.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 | $0.00131 | $0.02993 |
| Opus 5 | $0.00066 | $0.01496 |
| Sonnet 5 | $0.00026 | $0.00599 |
| Haiku 4.5 | $0.00013 | $0.00299 |
Grade A, and why
aidocx-s3-prototype 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDocxWorkFlow S3 — 原型导出
独立阶段：可单独调用。上游材料（S2 backlog）审查合格后开始，失败写失败报告。
模式选择
SSOT：
.cursor/rules/DESIGN_AND_EXECUTION_STANDARDS.mdc§4.3AIDOCX_S3_MODE
S3 支持两种模式，按需切换：
| 模式 | 触发条件 | 产出深度 | 适用场景 |
|---|---|---|---|
| lightweight | AIDOCX_S3_MODE=lightweight |
页面清单 + 核心流图 | 纯后端需求 / 轻 UI |
| depth（默认） | 未设置环境变量（默认 v16+） | 页面清单 + 完整 UI 节点清单 + 交互状态机 + Mermaid | 默认模式，S5/S6 UI 节点锚点 |
判定规则（LLM 在 S2 → S3 切换时执行）：
import os
# v16+ 默认 depth，lightweight 需要显式强制
forced = os.environ.get("AIDOCX_S3_MODE")
if forced == "lightweight":
mode = "lightweight"
else:
# 默认 depth（S5/S6 需要 UI 节点锚点）
mode = "depth"
决策树（判定流程图示）：
开始
↓
A. 用户强制 lightweight？ → AIDOCX_S3_MODE=lightweight → lightweight（强制）
↓ 否
B. 默认 → depth（强制）
v16+ 变更：默认 depth，lightweight 需要
AIDOCX_S3_MODE=lightweight显式强制。 原因：S5/S6 生成测试用例需要引用 UI 节点 ID，S3 不可跳过。
输出差异：
- depth 版（默认）：在 lightweight 基础上必须追加
§UI 节点清单（见下方 §输出） - lightweight 版：
prototype.md仅含 §3 关键页面布局 + §4 Mermaid 页面流图
⭐ v16+ 推荐默认 depth：S5/S6 测试用例生成需要引用 UI 节点 ID，depth 模式的 UI 节点清单是 S5/S6 的锚点来源。
阶段入口
触发：/aidocx-s3-prototype 或粘贴 S2 backlog
前置材料：S2 backlog.md：workflow_assets/<req_name>/<version>/「S2 需求拆解」/backlog.md
材料缺失时：生成失败报告，停止 S3。
§1.4 LLM 必读材料（阶段前置）
生成原型前，必须先 Read 以下材料。
| # | 材料 | 路径 | 必读原因 |
|---|---|---|---|
| 1 | 8 模块总表 | .cursor/MODULES.md（§1 总表） |
UI 模块 Story 对应页面原型；其他模块 Story 生成文本描述 |
| 2 | S2 backlog | workflow_assets/<req_name>/<version>/「S2 需求拆解」/backlog.md |
每个 Story 的功能点是原型生成的核心输入 |
§5 一致性检查（SKILL ↔ Rule 自动对齐）
触发时机：本节读取后、正式执行前。仅执行一次（同一次对话中多次触发本阶段，不重复检查）。
检查类型：A = 必读材料对齐 / B = 输出路径对齐 / C = 字段名对齐 / D = 模块枚举对齐
from ai_workflow.consistency_check import run_consistency_check
result = run_consistency_check(stage="s3")
if not result["passed"]:
print(f"[一致性检查] 发现 {len(result['issues'])} 个问题（见日志）")
检查结果不阻断阶段执行，仅输出到日志供人工参考。
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 · 271 lines · 131 tokens per session scan A 1863c0648893
aidocx-s3-prototype is a skill published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 1mo ago), licensed MIT. It adds 131 tokens to every session and 2,993 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…