generate-prp

A command that creates a PRP, or detailed implementation blueprint, from a feature file. It researches the project's documentation and records the findings for another agent to use when building the feature.

In plain words
What is it for?
Use it to prepare feature implementation plans, collect documentation references, and define how an agent should validate the finished work.
Why use it?
It turns a short feature request into a researched plan with enough project context to guide implementation and checking. This reduces guesswork about the tools and requirements involved.

Command for Claude Code

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/steppied/context-engineering/generate-prp
Clone the repo
git clone --depth 1 https://github.com/SteppieD/context-engineering

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 936 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 $0.00000 $0.00936
Opus 5 $0.00000 $0.00468
Sonnet 5 $0.00000 $0.00187
Haiku 4.5 $0.00000 $0.00094

Measured yesterday against content hash 921d952e2155, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generate-prp 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 yesterday.

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/generate-prp.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create PRP

YOU MUST DO IN-DEPTH RESEARCH, FOLLOW THE

  • Don't only research one page, and don't use your own webscraping tool - instead scrape many relevant pages from all documentation links mentioned in the initial.md file
  • Take my tech as sacred truth, for example if I say a model name then research that model name for LLM usage - don't assume from your own knowledge at any point
  • When I say don't just research one page, I mean do incredibly in-depth research, like to the ponit where it's just absolutely ridiculous how much research you've actually done, then when you creat the PRD document you need to put absolutely everything into that including references to the .md files you put inside the /research/ directory so any AI can pick up your PRD and generate WORKING and COMPLETE production ready code.

</RESEARCH PROCESS>

Feature file: $ARGUMENTS

Generate a complete PRP for general feature implementation with thorough research. Ensure context is passed to the AI agent to enable self-validation and iterative refinement. Read the feature file first to understand what needs to be created, how the examples provided help, and any other considerations.

The AI agent only gets the context you are appending to the PRP and training data. Assuma the AI agent has access to the codebase and the same knowledge cutoff as you, so its important that your research findings are included or referenced in the PRP. The Agent has Websearch capabilities, so pass urls to documentation and examples.

Research Process

  1. Codebase Analysis

    • Search for similar features/patterns in the codebase
    • Identify files to reference in PRP
    • Note existing conventions to follow
    • Check test patterns for validation approach
  2. External Research

    • Search for similar features/patterns online
    • Library documentation (include specific URLs)
    • Implementation examples (GitHub/StackOverflow/blogs)
    • Best practices and common pitfalls
    • Don't only research one page, and don't use your own webscraping tool - instead scrape many relevant pages from all documentation links mentioned in the initial.md file
    • Take my tech as sacred truth, for example if I say a model name then research that model name for LLM usage - don't assume from your own knowledge at any point
    • When I say don't just research one page, I mean do incredibly in-depth research, like to the ponit where it's just absolutely ridiculous how much research you've actually done, then when you creat the PRD document you need to put absolutely everything into that including INCREDIBLY IN DEPTH CODE EXMAPLES so any AI can pick up your PRD and generate WORKING and COMPLETE production ready code.

Read the full file on GitHub · 86 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. yesterday First seen · 86 lines · 0 tokens per session scan A 921d952e2155

Subscribe to this mod's changes

generate-prp is a command published in the GitHub repository SteppieD/context-engineering (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 936 tokens. 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.