prd

A command for writing a Product Requirements Document, or PRD: a structured document describing a product problem, its users, goals, scope, and dependencies. It saves the document in a numbered file under docs/prds/.

In plain words
What is it for?
Use it to create a PRD for a substantial user-facing feature, optionally interview stakeholders, or start from a Jira issue.
Why use it?
It turns an idea or ticket into a shared written definition before implementation begins. An optional interview helps collect missing product details, while a Jira option can seed information from an existing ticket.

Command

Part of the orc plugin — 13 skills, 30 commands, 14 agents, 5 hooks shipped together

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 commands/higoralves/orc/prd
Clone the repo
git clone --depth 1 https://github.com/HigorAlves/orc

Or install orc, the plugin that ships this one along with the rest of its 13 skills, 30 commands, 14 agents, 5 hooks.

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,243 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 $0.00043 $0.01243
Opus 5 $0.00022 $0.00622
Sonnet 5 $0.00009 $0.00249
Haiku 4.5 $0.00004 $0.00124

Measured 3d ago against content hash 6ba99c209eb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

orc/commands/prd.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/orc:prd

Author a new PRD following orc:prd-writing. Lives at docs/prds/NNNN-<kebab-title>.md.

Arguments

  • <title> — optional. Short noun phrase describing the feature (e.g. "report CSV export"). If omitted, prompts via AskUserQuestion.
  • --interview — optional. Walk the user through the seven-question PRD interview (Problem, Audience, Success metric, In/Out scope, Open questions, Dependencies) before drafting. Default is to draft from existing context only.
  • --from-jira <KEY> — optional. Pre-seed the PRD's Problem, Linked tickets, and (if available) Audience sections from a Jira ticket via orc:jira-cli.

Workflow

Phase 1 — Confirm a PRD is warranted

Invoke orc:prd-writing. Apply its "all of these are true" test:

  • user-facing outcome
  • non-obvious intent (real product question)
  • non-trivial work (multi-day or coordinated)

If borderline, print the Gate headline (**⛔ Gate — is this PRD-worthy?**, per orc:callouts), then AskUserQuestion:

  • "Yes, write the PRD"
  • "Smaller — issue or design note instead"
  • "Skip — this is implementation-only; reach for a plan"
  • "Refocus — this is technical contract, write a TRD with /orc:trd"

Phase 2 — Locate docs/prds/

If the directory doesn't exist, create it and add a one-line docs/prds/README.md linking to orc:prd-writing. Find the next sequence:

ls docs/prds 2>/dev/null | grep -E '^[0-9]{4}-' | sort | tail -1

Increment to get the new four-digit sequence (0001 if first).

Phase 3 — Gather inputs

If --from-jira <KEY> was passed, fetch the ticket:

acli jira workitem view "$KEY" --fields "key,summary,description,assignee,priority,status,labels" --json

Use the response to seed:

  • Problem (from summary + description)
  • Linked tickets (the key itself)
  • Audience (if labels indicate persona — heuristic; user confirms)

If --interview was passed, walk the seven-question interview from orc:prd-writing (skip questions answered by --from-jira or by conversation context). Batch into 2–3 AskUserQuestion calls; don't drip one at a time.

Read the full file on GitHub · 109 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. 3d ago First seen · 109 lines · 43 tokens per session scan A 6ba99c209eb6

Subscribe to this mod's changes

prd is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 6d ago), licensed MIT. It adds 43 tokens to every session and 1,243 once invoked, about $0.0002 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.