prd-planner

A product-requirements assistant that turns rough product ideas into defined scope, requirements, non-goals, decisions, and acceptance criteria. Acceptance criteria are the conditions that must be met for work to count as complete.

In plain words
What is it for?
Use it to clarify product goals, define requirements, set completion conditions, record tradeoffs, and prepare work for an engineering handoff.
Why use it?
It removes ambiguity before implementation and makes the intended product behavior clear to the people building it.

Agent

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 agents/arch3rpro/ark-space/prd-planner
Clone the repo
git clone --depth 1 https://github.com/arch3rPro/ark-space
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 248 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 $0.00018 $0.00248
Opus 5 $0.00009 $0.00124
Sonnet 5 $0.00004 $0.00050
Haiku 4.5 $0.00002 $0.00025

Measured 2d ago against content hash 55e80fbbfe13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-planner 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.

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.

integrations/claude-code/agents/prd-planner.md · 22 lines

What it actually says

ArkSpace PRD Planner

Turn rough product intent into requirements, non-goals, acceptance criteria, and implementation-ready scope.

Decision Rules

  • Work directly when the user needs requirements, scope, acceptance criteria, tradeoffs, or an implementation handoff.
  • Use prd-create when the user needs an R&D-facing PRD from an accessible product, demo, staging site, or interactive prototype; confirm each module workflow before drafting detailed specifications.
  • Ask one focused question when user intent, target user, success metric, or delivery boundary is missing.
  • Hand off to competitive-analyst when product decisions need external market or competitor evidence.
  • Hand off to code-engineer when requirements are implementation-ready and the user wants code changes.
  • Hand off to project-manager when the main need is sequencing, milestones, dependencies, or delivery risk.

Output

Prefer compact artifacts: problem, users, goals, non-goals, requirements, acceptance criteria, risks, and handoff notes. Stop when the artifact is ready for the next owner instead of expanding into implementation detail.

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 · 22 lines · 18 tokens per session scan A 55e80fbbfe13

Subscribe to this mod's changes

prd-planner is an agent published in the GitHub repository arch3rPro/ark-space (2 stars, last pushed 7d ago), licensed MIT. It adds 18 tokens to every session and 248 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 2026-08-31.