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/sixz-ai/prd-workflow/prd_executornpx skills add Sixz-AI/prd-workflow --skill prd_executorgit clone --depth 1 https://github.com/Sixz-AI/prd-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/skills/sixz-ai/prd-workflow/prd_executor)<a href="https://agentmods.dev/skills/sixz-ai/prd-workflow/prd_executor"><img src="https://agentmods.dev/badge/skills/sixz-ai/prd-workflow/prd_executor.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 | $0.00079 | $0.02068 |
| Opus 5 | $0.00039 | $0.01034 |
| Sonnet 5 | $0.00016 | $0.00414 |
| Haiku 4.5 | $0.00008 | $0.00207 |
Grade A, and why
prd-executor 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Executor Skill
Overview
This skill guides a Dev Agent through executing a prd_decomposer breakdown located at
docs/[Feature_Name]_breakdown/. It enforces three hard gates:
- Requirements confirmation (brainstorming all 10 closure dimensions) before any coding
- TDD workflow during implementation
- Git commit per completed REQ, push per completed Phase
When to Use
- A breakdown directory exists at
docs/[Feature_Name]_breakdown/ - User says "start executing", "start development", "implement this PRD", "execute breakdown"
- Dev Agent is handed a breakdown directory and needs to know how to proceed
Workflow
Step 1: Initialize
Read docs/[Feature_Name]_breakdown/outline.md.
Extract:
- Total Phases and REQs
- Dependency graph between REQs
- Current status of each REQ (look at the Status column)
Announce to the user: which REQs are pending, which (if any) are already in progress or done.
Step 2: Select Next Phase
Find the first Phase in outline.md whose status is ⬜ (not started) and whose REQ dependencies (if any cross-Phase) are all ✅ or ⚠️.
If no such Phase exists:
- If all Phases are ✅: announce completion, done.
- If a Phase is 💬 or 🔍 or 🚧 or 🧪: resume that Phase from the appropriate stage below.
Stage A: Discussion — Discuss All REQs in the Phase [HARD GATE 1]
- Update Phase status in
outline.mdto 💬 (Discussing) - For each REQ in this Phase, in order:
a. Open the REQ file. Check whether
🔍 详细需求确认still contains⚠️ [待填充]. b. If YES (placeholder present):- Update REQ status in REQ file and
outline.mdto 💬 - Invoke
superpowers:brainstormingwith the REQ content as context - Ensure ALL 10 closure dimensions are addressed:
- API closure
- Business logic closure
- UI/UX closure
- Error handling closure
- Data consistency closure
- Permission/security closure
- Performance boundary closure
- Testing closure (unit test scenarios + manual UAT checkpoints)
- Analytics/tracking closure
- Compatibility closure
- Replace the entire
⚠️ [待填充]placeholder block with the brainstorming conclusions c. If NO (placeholder already replaced): skip brainstorming for this REQ.
- Update REQ status in REQ file and
- YOU ARE FORBIDDEN FROM WRITING ANY IMPLEMENTATION CODE DURING STAGE A
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 216 lines · 79 tokens per session scan A a35430c5c434
prd-executor is a skill published in the GitHub repository Sixz-AI/prd-workflow (2 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 2,068 once invoked, about $0.0004 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
vibe-workflow
Complete 5-step workflow to build an MVP from idea to launch. Use when the user wants to start a new project from scratch, go through the full workflow, or says "help me build an MVP", "start new project", or "vibe coding workflow".
project-butler
Project memory workflow for init/upgrade, profile-aware setup, end session, normal/full close, file organization, document archiving, language switching, versioned update logs, rule review, status, wiki sync, and context recovery. Use for /project-butler, setup/初始化, foundation setup, profile setup, end session/收工…
work-step
Execute the next approved Codument delivery-plan step, using the relevant implementation and verification skills.
trellis-workflow-enhancer
Audit and apply real, project-local Trellis integrations for Matt Pocock and Waza skills, with phase routing, hook injection, durable artifact handoffs, and smoke-test evidence. Use when a user wants to strengthen, compare, modernize, integrate, or debug Trellis with Matt/Waza workflows, especially when skills are…
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
tasks
Generate a dependency-ordered task list (tasks.md) with sub-phases and cross-artifact consistency analysis from design.md in specs/{feature}/.