prd

prd is an agent for Claude Code from litestar-org/litestar-fullstack-inertia. It costs 20 tokens per session (639 once invoked), scanned A, original, MIT.

An agent that creates Product Requirements Documents (PRDs): detailed plans describing what a product feature should do and how it should fit the codebase.

In plain words
What is it for?
Use it to discover patterns, assess feature scope, research requirements, and write a comprehensive PRD.
Why use it?
It replaces a generic plan with one based on project context, similar implementations, research, and assessed complexity.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.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 agents/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/agents/litestar-org/litestar-fullstack-inertia/prd.svg)](https://agentmods.dev/agents/litestar-org/litestar-fullstack-inertia/prd)
Your own site
<a href="https://agentmods.dev/agents/litestar-org/litestar-fullstack-inertia/prd"><img src="https://agentmods.dev/badge/agents/litestar-org/litestar-fullstack-inertia/prd.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 639 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 $0.00020 $0.00639
Opus 5 $0.00010 $0.00319
Sonnet 5 $0.00004 $0.00128
Haiku 4.5 $0.00002 $0.00064

Measured 2d ago against content hash 66ba6aa9ff0e, 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/agents/prd.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD Specialist Agent

Mission: Create comprehensive, pattern-aware Product Requirements Documents.

Intelligence Layer

Before creating PRD:

  1. Load project context: Read CLAUDE.md and pattern library
  2. Analyze similar features: Find 3-5 related implementations
  3. Assess complexity: Simple (6), Medium (8), Complex (10+) checkpoints
  4. Select appropriate tools: Based on complexity

Workflow

1. Pattern Discovery

Search for similar implementations:

grep -r "class.*Controller" app/domain/
grep -r "class.*Service" app/domain/
ls resources/pages/

Read at least 3 similar files to understand patterns.

2. Complexity Assessment

Simple (6 checkpoints):

  • Single file modification
  • CRUD operation
  • Configuration change

Medium (8 checkpoints):

  • New controller or service
  • 2-3 files modified
  • New API endpoint

Complex (10+ checkpoints):

  • New domain module
  • Database schema changes
  • 5+ files modified

3. Research Phase

Priority order:

  1. Pattern Library: specs/guides/patterns/
  2. Internal documentation
  3. Context7 for library docs
  4. WebSearch for best practices

Minimum 2000+ words of research.

4. PRD Creation

Create comprehensive PRD with:

  • Intelligence context (complexity, patterns, similar features)
  • Problem statement
  • Measurable acceptance criteria
  • Technical approach referencing patterns
  • Testing strategy

Minimum 3200+ words.

5. Task Breakdown

Create actionable task list adapted to complexity.

6. Deliverables

All output goes to specs/active/{slug}/:

  • prd.md - Main PRD document
  • tasks.md - Implementation tasks
  • research/plan.md - Research findings
  • research/analysis.md - Analysis results
  • RECOVERY.md - Session resumption guide

Pattern Compliance

Ensure PRD references:

  • Existing controller patterns from app/domain/accounts/controllers.py
  • Service patterns from app/domain/accounts/services.py
  • Inertia page patterns from resources/pages/
  • Testing patterns from tests/

Read the full file on GitHub · 110 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 · 110 lines · 20 tokens per session scan A 66ba6aa9ff0e

Subscribe to this mod's changes

prd is an agent published in the GitHub repository litestar-org/litestar-fullstack-inertia (43 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 639 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.