prd

A tool that turns a plain-language description of an app or feature into a Product Requirements Document, a written plan describing what to build and how it should work. It asks questions, researches similar apps, and documents the scope, technology choices, and architecture.

In plain words
What is it for?
Use it before building a new app or planning a substantial feature. For an existing project, it reads the current code and describes how the feature should fit into that project.
Why use it?
It turns an idea into a structured brief before implementation begins, helping define boundaries and important decisions. It also prepares the work for later breakdown into an implementation campaign.

Skill for Claude CodeCodex

Part of the Citadel plugin — 48 skills, 7 agents, 2 MCP servers 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 skills/sethgammon/citadel/prd
Any agent
npx skills add SethGammon/Citadel --skill prd
Clone the repo
git clone --depth 1 https://github.com/SethGammon/Citadel

Made for: Claude Code, Codex.

Or install Citadel, the plugin that ships this one along with the rest of its 48 skills, 7 agents, 2 MCP servers.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,591 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 $0.00048 $0.01591
Opus 5 $0.00024 $0.00796
Sonnet 5 $0.00010 $0.00318
Haiku 4.5 $0.00005 $0.00159

Measured 3d ago against content hash a83976ae5708, 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.

skills/prd/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prd — Product Requirements Document Generator

When to Use

Don't use when: architecture is already defined and you need implementation (use /architect then /archon); adding a small feature to an existing app (use /marshal directly).

  • User describes an app or feature to build (greenfield or feature mode)
  • Before any Archon campaign for a new project or feature

Mode Detection

Before starting, determine the mode:

Greenfield mode: No existing source files, or user explicitly says "new app" / "from scratch." Produces a full PRD as described below.

Feature mode: The project already has source files (check for src/, app/, lib/, package.json with dependencies, or similar). The user describes a feature to add, not a whole app ("add auth", "add a dashboard", "add payment processing").

In feature mode:

  • Read the existing file tree and package.json/equivalent before asking questions
  • The existing stack is a given — don't recommend alternatives
  • "Architecture" section describes integration points with existing code, not standalone shape
  • End conditions MUST include regression checks: "existing tests still pass", "typecheck has no new errors"
  • "Out of Scope" is relative to the feature, not the whole app
  • Technical Decisions only covers decisions the feature introduces (new dependencies, new patterns)

The PRD template below works for both modes. Feature mode just scopes it tighter.

Protocol

Step 1: UNDERSTAND

Determine mode (greenfield vs feature). Identify core functionality, target user, and success criteria (greenfield) or integration points and existing stack (feature). Ask up to 3 questions — only those that would change the architecture. Do not ask about tech stack in greenfield mode; in feature mode, the stack is already decided.

Step 2: RESEARCH (Optional)

If the concept has well-known implementations, run /research to identify 2-3 reference apps and common expected features. Skip for simple concepts (landing page, personal tool, CRUD).

Read the full file on GitHub · 173 lines

Files

What ships with it

2 files 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.

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 · 173 lines · 48 tokens per session scan A a83976ae5708

Subscribe to this mod's changes

prd is a skill published in the GitHub repository SethGammon/Citadel (914 stars, last pushed 6d ago), licensed MIT. It adds 48 tokens to every session and 1,591 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 2026-08-30.

Related

Other skills, from other repositories

debrief

This skill should be used when the user asks to "debrief", "record what happened", "session summary", "write a debrief", or wants to capture session activity (commits, task state changes, decisions, issues) into a structured record for the next session.

spacedock-dev/spacedock · 59 tokens

refit

This skill should be used when the user asks to "refit a workflow", "upgrade a workflow", "update workflow scaffolding", or wants to bring an existing workflow's scaffolding files up to date with the current Spacedock version.

spacedock-dev/spacedock · 52 tokens

fo-dispatch-recovery

Claude dispatch failure recovery — Break-Glass Manual Dispatch (the manual Agent() template) and Context Budget Failure/Dead Ensign Handling (the budget-unavailable stderr conditions, the recovery clause, dead-ensign bookkeeping). Read ONLY at its resident triggers inside claude-fo-dispatch.md — a non-zero or…

spacedock-dev/spacedock · 137 tokens

fo-status-viewer

First-officer status query/mutate/display surface — the status command flag docs, --set field docs, canonical captain-facing invocations, the Captain-Facing State Display rendering, and the GitHub-issue-filing approval gate. Invoke at the first ad-hoc status question, --set mutation, --next-id/--resolve lookup, or…

spacedock-dev/spacedock · 87 tokens

present-gate

First-officer gate-presentation rendering — the captain-facing gate-review template and assembly rules, including workflow-owned finding labels. Invoke at the gate point after the FO has decided a stage must be presented.

spacedock-dev/spacedock · 44 tokens

agent-workflow-playbook

AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4…

Gingiris-1031/gingiris-skills · 83 tokens