lld-writer

lld-writer is a skill for Claude Code, Codex from TestAny-io/testany-agent-skills. It costs 41 tokens per session (2,236 once invoked), scanned A, original, MIT.

A guide for writing a low-level design, which describes modules, interfaces, implementation details, error handling, concurrency, and tests.

In plain words
What is it for?
It is for producing an LLD document, a design manifest, and links showing how the design traces back to earlier requirements and contracts.
Why use it?
It turns approved product and architecture decisions into details that engineers can implement without changing the agreed requirements.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: names the AskUserQuestion tool.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **语言规则**:默认跟随用户输入语言;用户显式指定时以用户指定为准;不要因为本 `SKILL.md` 是中文而强制输出中文;`TRACEABILITY-METADATA` 的字段名、枚举值、ID、comment markers 始终保持英文。若本 skill 使用模板或派发子任务,继续传递同一个 `output_la.

Part of the testany-eng plugin — 21 skills, 21 commands shipped together

Good fit It is for producing an LLD document, a design manifest, and links showing how the design traces back to earlier requirements and contracts.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/TestAny-io/testany-agent-skills
agentmods
npx agentmods add skills/testany-io/testany-agent-skills/lld-writer

Made for: Claude Code, Codex.

Or install testany-eng, the plugin that ships this one along with the rest of its 21 skills, 21 commands.

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 lld-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/lld-writer/github.svg)](https://agentmods.dev/skills/testany-io/testany-agent-skills/lld-writer)
Your own site
<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/lld-writer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/lld-writer/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 lld-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/lld-writer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/lld-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,236 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00041 $0.02236
Opus 5 $0.00020 $0.01118
Sonnet 5 $0.00008 $0.00447
Haiku 4.5 $0.00004 $0.00224

Measured 12d ago against content hash 35a6154dd628, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lld-writer 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 12d 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.

plugins/testany-eng/skills/lld-writer/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLD Writer

语言规则:默认跟随用户输入语言;用户显式指定时以用户指定为准;不要因为本 SKILL.md 是中文而强制输出中文;TRACEABILITY-METADATA 的字段名、枚举值、ID、comment markers 始终保持英文。若本 skill 使用模板或派发子任务,继续传递同一个 output_language。详见 ../../references/language-policy.md

你是一个低层设计(LLD)写作助手。你的目标是把 HLD/Contract 的决策落地为可实现的设计细节,并通过模块化模板确保不漏关键工程约束。

核心原则

原则 说明
承接 PRD/HLD/Contract LLD 只能细化,不得新增边界或改写契约
Contract 是事实源 LLD 只引用,不重定义接口
基于证据 技术现状/既有能力必须有依据;缺失就 AskUserQuestion
模块化组合 LLD = Core + Add-ons + Profile + Guardrails
Guardrails 最高优先级 项目约束文档优先于个人偏好
先做 Guardrails trigger check 若本次 LLD 反向暴露项目级约束缺口,先判断是否必须更新 Guardrails
复用优先 优先复用已有模块/共享服务/第三方方案

内容边界

LLD 应包含:模块结构、接口签名、关键流程/伪代码、错误处理、并发/事务/幂等、测试设计、追溯映射

LLD 不应包含:业务 Why(PRD)、系统级架构决策(HLD)、完整代码、与 Contract 冲突的接口

模块化模板机制

层级 说明
Core 必选,核心设计内容
Add-ons 按能力触发:API/Storage/Async/Infra/Observability 等
Profile 快速组合包(如 saas-serverless、web-app)
Guardrails 项目约束,强制覆盖

必需产出:LLD 文档 + LLD Manifest + 追溯映射表


执行进度清单

执行时使用 TodoWrite 工具跟踪以下进度,完成一项后立即标记为 completed:

□ Phase 0: 基线与上下文
  □ 0.1 Glob 扫描项目文档
  □ 0.2 AskUserQuestion 确认基线
  □ 0.3 读取 PRD/HLD/Contract
  □ 0.4 确认 Guardrails
  □ 0.5 执行 Guardrails trigger check
  □ 0.6 输出「上下文收集报告」

□ Phase 1: Profile 与模块选择
  □ 1.1 提取 Guardrails 强制模块
  □ 1.2 AskUserQuestion 选择 Profile
  □ 1.3 识别触发模块
  □ 1.4 AskUserQuestion 确认 Add-ons
  □ 1.5 生成 LLD Manifest 初稿

□ Phase 2: 组装 LLD 文档
  □ 2.1 创建文档骨架
  □ 2.2 填写文档信息与基线引用
  □ 2.3 插入 LLD Manifest
  □ 2.4 填写 Core 章节
  □ 2.5 追加 Add-on 章节
  □ 2.6 填写追溯映射表
  □ 2.7 记录待确认问题

□ Phase 3: 一致性自检
  □ 3.1 PRD 覆盖检查(100%)
  □ 3.2 HLD 决策承接检查
  □ 3.3 Contract 一致性检查
  □ 3.4 Guardrails 强制项检查
  □ 3.5 复用清单检查
  □ 3.6 Traceability Metadata 生成与校验
  □ 3.7 输出自检报告

工作流程

Phase 0:基线与上下文

目标:收集上游文档,确认基线版本

  1. 文档扫描:Glob 扫描 PRD/HLD/Contract/Guardrails/ADR
  2. 基线确认:AskUserQuestion 确认最新批准基线(模板见 references/askuser-templates.md
  3. 读取文档:提取 PRD 需求、HLD 决策、Contract 接口
  4. Guardrails 确认:AskUserQuestion 确认是否存在
  5. Trigger check:基于 ../../references/guardrails-trigger-check.md 执行一次 Guardrails trigger check
    • no_trigger:继续阶段 1
    • suggest_guardrails:记录影响域与推荐动作后继续
    • require_guardrails_before_design:停止当前 LLD 写作,明确建议先运行 guardrails-writer
  6. 输出:「上下文收集报告」(格式见 references/output-templates.md

Read the full file on GitHub · 185 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. 12d ago First seen · 185 lines · 41 tokens per session scan A 35a6154dd628

Subscribe to this mod's changes

lld-writer is a skill published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 2,236 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens