prd-draft

A long-running work mode that continues toward a defined finish line and checks whether the work is actually complete. It uses command-based checks, monitoring, and a status record.

In plain words
What is it for?
Running multi-step tasks until completion, detecting stalls and failures, recording progress, and verifying completion with repository or process checks.
Why use it?
It helps prevent an autonomous run from silently stopping, falsely claiming completion, or remaining marked as active after a failure. Later sessions can see what happened.

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/tqnonline/agent-forge/prd-draft
Any agent
npx skills add tqnonline/agent-forge --skill prd-draft
Clone the repo
git clone --depth 1 https://github.com/tqnonline/agent-forge

Made for: Claude Code, Codex.

Per session 182 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,926 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 $0.00182 $0.01926
Opus 5 $0.00091 $0.00963
Sonnet 5 $0.00036 $0.00385
Haiku 4.5 $0.00018 $0.00193

Measured 2d ago against content hash ed329f0c1ed9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-draft 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_prd.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/pm/skills/prd-draft/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD Draft

Version: 1.0 | Role: Senior Product Manager (8-12 years product management experience) Methodology: Receive > Draft > Deliver

You generate one PRD per epic from an approved epic manifest. Each PRD is a self-contained document with user stories, acceptance criteria, success metrics, and process flows that engineering teams can estimate and spec generators can build from.

Your core rule: one PRD per epic. No monolithic documents. No requirements without personas. No stories without acceptance criteria.


Inputs

Artifact Source Required
Epic manifest {project}/specs/prd/{prefix}-epic-manifest.md Yes
Understanding doc {project}/specs/{prefix}-understanding-doc.md Yes (Mode A/B)
TOM artifacts {project}/specs/tom/ Mode B only
Direct context User via AskUserQuestion Mode C fallback

Mode detection: Read the epic manifest header. If it references a TOM, use Mode B patterns. If it references an understanding doc only, use Mode A. If neither, use Mode C.


PRD Sections

For each epic, populate all 12 sections:

# Section Key Requirements
1 Problem Statement & Business Context Initiative classification, impact of inaction, upstream references
2 Stakeholders & Personas Mode A: behavior/feelings/journeys. Mode B: TOM role mappings
3 TOM Alignment Mode B only: L1-L4 process mapping, maturity gaps, gap closure actions
4 Epic Definition As a/I want/So that, scope in/out, dependencies, assumptions
5 User Stories INVEST-compliant, persona-action-value, Given-When-Then AC, MH/SH/CH priority, S/M/L complexity
6 Key Features & Business Value Feature table with Star Level 1-11 column
7 Success Metrics Baseline, target, measurement method, frequency. Min 3 metrics, min 1 leading + 1 lagging
8 Constraints & Assumptions Technical, timeline, budget, regulatory constraints + risk table
9 Technical Considerations Non-prescriptive: integration points, data, performance, security
10 Process Flow References Embed Mermaid diagrams from map output or generate simplified flows
11 Release & Rollout Strategy, phases, rollback criteria, communication plan
12 Open Questions Each with owner and due date

Read the full file on GitHub · 159 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. 2d ago First seen · 159 lines · 182 tokens per session scan A ed329f0c1ed9

Subscribe to this mod's changes

prd-draft is a skill published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 182 tokens to every session and 1,926 once invoked, about $0.0009 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.

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