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 commands/touheedcode/claude-dev-workflow/prdgit clone --depth 1 https://github.com/TouheedCode/claude-dev-workflowWhat 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 | $0.00000 | $0.00405 |
| Opus 5 | $0.00000 | $0.00202 |
| Sonnet 5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
prd 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.
What it actually says
/prd — Generate Product Requirements Document
Arguments
$ARGUMENTS— Project name and a brief description of what to build
Instructions
You are generating a Product Requirements Document (PRD) for the project described below.
Project input: $ARGUMENTS
Step 1: Gather Context
If the input is vague or missing critical details, ask the user clarifying questions before generating. You need at minimum:
- A clear project/feature name
- What problem it solves
- Who the target users are
Step 2: Generate the PRD
Create a structured PRD file at docs/PRD-{name}.md where {name} is a kebab-cased version of the project name.
The PRD must contain these sections:
# PRD: {Project Name}
## Overview
One paragraph summary of the project. What is it and why does it matter?
## Problem Statement
What problem does this solve? What's the current pain point? Be specific.
## Target Users
Who are the primary users? What are their characteristics and needs?
## Core Features
Numbered list of features. Each feature should have:
- **Feature name** — One-line description
- Acceptance criteria (bulleted)
## User Experience
Describe the key user flows. How does someone use this feature end-to-end?
## Technical Constraints
- What tech stack is being used?
- Are there performance requirements?
- Security considerations?
- Integration requirements?
## Success Metrics
How will we know this is successful? Define measurable outcomes.
## Out of Scope
What are we explicitly NOT building in this iteration?
Step 3: Output
- Write the PRD to
docs/PRD-{name}.md - Print a summary: the project name, feature count, and file path
- Remind the user to run
/storynext to break the PRD into user stories
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 First seen · 65 lines · 0 tokens per session scan A ca5a073a7774
prd is a command published in the GitHub repository TouheedCode/claude-dev-workflow (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 405 tokens. 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 commands, from other repositories
auto-work
给一个需求,AI自动完成调研→方案→方案Review→开发→开发Review全流程.
develop-review
Review feature-developing 生成的代码,检查遗漏和宪法违规.
developing
Command "developing" from chaohong-ai/ai-auto-work, covering 参数解析, 你的角色, 工作流程, 第一步:建立完整上下文 and 第二步:确认实现范围.
manual-work
带人工检查点的开发流程:前期需求/方案重点把关,后期自主执行.
plan-review
Review生成的plan,检查边界情况、场景覆盖、架构合理性.
analyze
分析 auto-work 产出中遗漏/缺陷的根因,定位流程断点并输出修复方案+工作流优化建议.