prd

prd is a command for Claude Code from litestar-org/litestar-fullstack-inertia. It costs 10 tokens per session (2,093 once invoked), scanned A, original, MIT.

A planning command that creates a Product Requirements Document (PRD), a written specification for a product or feature, after studying similar code in the project.

In plain words
What is it for?
Use it to research a feature, define its requirements, and save a detailed implementation plan without changing application code.
Why use it?
It reduces guesswork by grounding the plan in existing project patterns and adjusting the amount of detail to the feature's complexity.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

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/litestar-org/litestar-fullstack-inertia/prd
Clone the repo
git clone --depth 1 https://github.com/litestar-org/litestar-fullstack-inertia

Made for: Claude Code.

Wrote 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.

agentmods badge for prd

README.md
[![agentmods](https://agentmods.dev/badge/commands/litestar-org/litestar-fullstack-inertia/prd.svg)](https://agentmods.dev/commands/litestar-org/litestar-fullstack-inertia/prd)
Your own site
<a href="https://agentmods.dev/commands/litestar-org/litestar-fullstack-inertia/prd"><img src="https://agentmods.dev/badge/commands/litestar-org/litestar-fullstack-inertia/prd.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,093 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 5.1 $0.00010 $0.02093
Opus 5 $0.00005 $0.01046
Sonnet 5 $0.00002 $0.00419
Haiku 4.5 $0.00001 $0.00209

Measured 2d ago against content hash c6acd1ebc95e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 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.

.claude/commands/prd.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intelligent PRD Creation Workflow

You are creating a Product Requirements Document for: $ARGUMENTS

Intelligence Layer (ACTIVATE FIRST)

Before starting checkpoints:

  1. Read MCP Strategy: Load .claude/mcp-strategy.md for tool selection
  2. Learn from Codebase: Read 3-5 similar implementations
  3. Assess Complexity: Determine simple/medium/complex
  4. Adapt Workflow: Adjust checkpoint depth

Critical Rules

  1. CONTEXT FIRST - Read existing patterns before planning
  2. NO CODE MODIFICATION - Planning only (specs/ directory only)
  3. PATTERN LEARNING - Identify 3-5 similar features
  4. ADAPTIVE DEPTH - Simple=6, Medium=8, Complex=10+ checkpoints
  5. RESEARCH GROUNDED - Minimum 2000+ words research
  6. COMPREHENSIVE PRD - Minimum 3200+ words

Checkpoint 0: Intelligence Bootstrap

Load project intelligence:

  1. Read CLAUDE.md (or AGENTS.md)
  2. Read specs/guides/patterns/README.md
  3. Read .claude/mcp-strategy.md

Learn from existing implementations:

For this Litestar project, search in:

  • app/domain/ for backend patterns
  • resources/pages/ for frontend patterns
  • app/db/models/ for data model patterns

Assess complexity:

  • Simple: Single file, CRUD, config change → 6 checkpoints
  • Medium: New controller/service, 2-3 files → 8 checkpoints
  • Complex: New domain module, schema changes, 5+ files → 10+ checkpoints

Output: "✓ Checkpoint 0 complete - Complexity: [level], Checkpoints: [count]"


Checkpoint 1: Pattern Recognition

Identify similar implementations:

# Search for related patterns in backend
grep -r "class.*Controller" app/domain/ | head -5
grep -r "class.*Service" app/domain/ | head -5

# Search for related patterns in frontend
ls resources/pages/

Read at least 3 similar files and document:

## Similar Implementations

1. `app/domain/{feature}/controllers.py` - Description
2. `app/domain/{feature}/services.py` - Description
3. `resources/pages/{feature}/` - Description

## Patterns Observed

- Controller structure: Litestar controller with route decorators
- Service pattern: Extends SQLAlchemyAsyncRepositoryService
- Inertia integration: Returns Inertia responses with typed props
- Repository pattern: advanced-alchemy repositories

Read the full file on GitHub · 336 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 · 336 lines · 10 tokens per session scan A c6acd1ebc95e

Subscribe to this mod's changes

prd is a command published in the GitHub repository litestar-org/litestar-fullstack-inertia (43 stars, last pushed 5d ago), licensed MIT. It adds 10 tokens to every session and 2,093 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 2026-09-03.