source-command-first-req

source-command-first-req is a skill for Claude Code, Codex from Joe-rq/harness-lab. It costs 42 tokens per session (1,331 once invoked), scanned A, original, MIT.

A guided command for creating a project's first REQ, meaning a tracked requirement or work request. It identifies common project types such as React, Python, Go, and Rust, then suggests relevant topics.

In plain words
What is it for?
Use it to start a requirement for tasks such as component development, API work, data processing, testing, bug fixes, or refactoring.
Why use it?
It helps a new user create the first requirement without knowing the project's command-line setup. It also checks that the project has the needed REQ files and no active requirement conflict.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/joe-rq/harness-lab/source-command-first-req
Any agent
npx skills add Joe-rq/harness-lab --skill source-command-first-req
Clone the repo
git clone --depth 1 https://github.com/Joe-rq/harness-lab

Made for: Claude Code, Codex.

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 source-command-first-req

README.md
[![agentmods](https://agentmods.dev/badge/skills/joe-rq/harness-lab/source-command-first-req.svg)](https://agentmods.dev/skills/joe-rq/harness-lab/source-command-first-req)
Your own site
<a href="https://agentmods.dev/skills/joe-rq/harness-lab/source-command-first-req"><img src="https://agentmods.dev/badge/skills/joe-rq/harness-lab/source-command-first-req.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,331 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.01331
Opus 5 $0.00021 $0.00665
Sonnet 5 $0.00008 $0.00266
Haiku 4.5 $0.00004 $0.00133

Measured 4d ago against content hash ae23bcbf21b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-command-first-req 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 4d 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.

.agents/skills/source-command-first-req/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

source-command-first-req

Use this skill when the user asks to run the migrated source command first-req.

Command Template

/first-req

目标

引导新用户快速创建第一个 REQ,降低接入摩擦。

前置检查

  1. 确认 requirements/ 目录存在。不存在 → 提示先运行 /harness-setup
  2. 选择已安装的 REQ CLI 入口:
    • package.json 中存在 req:create → 使用 npm run req:create -- ...
    • 否则存在 scripts/req-cli.mjs → 使用 node scripts/req-cli.mjs create ...
    • 两者都不存在 → 提示先运行 /harness-setup
  3. 用对应入口执行 npm run req:statusnode scripts/req-cli.mjs status,确认当前 worktree 无活跃 REQ;有活跃 REQ 时先完成/搁置,或改用 worktree 流程。

执行步骤

Step 1: 项目类型识别

通过以下信号自动识别项目类型:

信号 项目类型
存在 package.json + react 依赖 React
存在 package.json + next 依赖 Next.js
存在 package.json + vue 依赖 Vue
存在 pyproject.tomlsetup.py Python
存在 go.mod Go
存在 Cargo.toml Rust
以上都不匹配 Generic

Step 2: 用 AskUserQuestion 询问 REQ 主题

使用 AskUserQuestion 工具,提供 3 个推荐选项 + 自定义输入:

推荐选项根据项目类型生成

  • React/Next.js 项目:组件开发、状态管理、API 集成
  • Python 项目:数据处理、API 开发、测试覆盖
  • Go 项目:性能优化、并发处理、API 开发
  • Generic:Bug 修复、功能开发、代码重构

主题可以使用中文或其他非 ASCII 文字。CLI 会保留原始标题;如果标题无法生成英文 slug,会使用安全的 requirement 文件名后缀,不要求用户手工翻译。

同时确认本次 REQ 的真实验证入口:

  1. 先读取项目已有配置(如 package.json scripts、pyproject.tomlgo.modCargo.toml、CI 或项目 README)。
  2. 只推荐仓库中确实存在或用户明确确认的命令。
  3. 无法确认时填写“待补充真实验证命令”,不得把 npm testpytestgo test ./...cargo test 当作默认事实。

Step 3: 创建 REQ

根据前置检查选择的入口运行。标题可以直接使用用户原文,不需要为了中文标题额外传 --slug

npm run req:create -- --title "[用户选择的主题]"

# 没有 package.json alias,但已安装 CLI 时
node scripts/req-cli.mjs create --title "[用户选择的主题]"

Step 4: 自动填充 REQ 内容

创建完成后,自动读取生成的 REQ 文件,填充以下内容:

背景:基于项目类型和主题生成一段简短描述。

目标:根据主题类型推荐 2-3 个目标。

验收标准:根据主题类型推荐 2-3 个可验证的标准。

验证计划:填入 Step 2 已确认的真实命令、环境依赖和人工验证;如果还没有可信命令,明确记录缺口并在 req:start 前由用户补齐。

主题与字段映射

主题类型 推荐目标 推荐验收标准
组件开发 实现组件、编写测试、补充文档 组件可渲染、测试通过、Storybook 可用(仅在项目已配置时)
Bug 修复 定位根因、实现修复、回归测试 Bug 不再复现、回归测试通过
API 开发 实现端点、参数校验、错误处理 API 可调通、4xx/5xx 处理正确
测试覆盖 识别未覆盖路径、编写测试 覆盖率提升至目标值
代码重构 消除重复、改善命名、保持行为 重构后测试仍通过

Read the full file on GitHub · 121 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. 4d ago First seen · 121 lines · 42 tokens per session scan A ae23bcbf21b5

Subscribe to this mod's changes

source-command-first-req is a skill published in the GitHub repository Joe-rq/harness-lab (20 stars, last pushed 21d ago), licensed MIT. It adds 42 tokens to every session and 1,331 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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