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/yaukwan/my-claude-code-workflow/prd-task-docgit clone --depth 1 https://github.com/yaukwan/my-claude-code-workflowWrote 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/commands/yaukwan/my-claude-code-workflow/prd-task-doc)<a href="https://agentmods.dev/commands/yaukwan/my-claude-code-workflow/prd-task-doc"><img src="https://agentmods.dev/badge/commands/yaukwan/my-claude-code-workflow/prd-task-doc.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 | $0.00017 | $0.03273 |
| Opus 5 | $0.00009 | $0.01636 |
| Sonnet 5 | $0.00003 | $0.00655 |
| Haiku 4.5 | $0.00002 | $0.00327 |
Grade A, and why
prd-task-doc 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.
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Development Task Documentation Generator
Core Workflow
This command generates specification task documents from PRD files. Implementation work begins only after document review and approval.
Usage Examples
/prd-tasks # Basic generation
/prd-tasks -zen # Optimize with o3 (default)
/prd-tasks -zen pro # Optimize with gemini-pro
/prd-tasks -review # Review with gemini-pro (default)
/prd-tasks -review o3 # Review with o3
/prd-tasks -zen -review # Optimize with o3, review with gemini-pro
/prd-tasks -zen pro -review o3 # Optimize with gemini-pro, review with o3
Step 1: Requirements Analysis & Understanding
Execution Actions:
- Read and parse PRD document from
docs/specs/prd.txt - Parse all requirements in PRD into implementable specifications
- Identify interface contracts and system dependencies
- Extract acceptance criteria, workflows, and integration requirements
- Map specification implementation needs
- Check available tools and resources
- Group tasks by shared specification context and file dependencies
Step 2: Parameter Processing & Model Collaboration
Tips:
Bash(gemini -p "<prompt>"): gemini can be used to generate code snippets, documentation, and other content based on the provided prompt and file paths.- Chat with other model using English
Optimization (-zen):
If present, collect relevant file content and original PRD first, then:
- o3 (default): Use
mcp__zenchat method with full file paths infilesparameter to optimize task specification structure - pro: Use
gemini -p ”<prompt>“bash command with file paths as arguments
Review (-review):
- pro (default): Use
gemini -p "<prompt>“bash command for task specification review - o3: Use
mcp__zenchat method with full file paths infilesparameter
Collaboration Process (-zen parameter):
- Collect project-related file content using Glob and Read tools
- Organize original PRD content
- Prepare task structuring context:
- Include complete "Task Group Structuring & Splitting Guidelines"
- Provide "Development Task Specification Template Structure"
- Share current project file structure and dependencies
- Discuss with o3 model or gemini chat:
- Task decomposition rationality according to grouping guidelines
- Validate each Task Group represents a self-contained functional module
- Ensure all changes to the same module are in the same Task Group
- Check sub-task count (2-4 per group) and naming conventions
- Interface design best practices
- Technical architecture recommendations
- Implementation priority suggestions
- Optimize task specification structure based on o3 feedback
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.
- 4d ago First seen · 309 lines · 0 tokens per session scan A 9ab92142175d
prd-task-doc is a command published in the GitHub repository yaukwan/my-claude-code-workflow (44 stars, last pushed 1y ago), licensed MIT. It adds 17 tokens to every session and 3,273 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 commands, from other repositories
memory-audit
Audit project memory files for staleness, orphans, bloat, and duplication.
probe
Probe recent changes with 2-3 pointed questions.
lint
Run markdownlint on specified files or the whole project.
ponder
Surface a question worth sitting with.
install-statusline
Install duet statusline to /.claude for a lean, informative status bar.
capture-memory
Capture learnings to MEMORY.md, output compact summary.