prp

A format for turning a complex feature or project idea into requirements, phases, tasks, and checks. It is intended as a detailed implementation blueprint.

In plain words
What is it for?
Use it to plan a new project, design a feature, break work into phases, execute an existing plan, or check whether a phase is complete.
Why use it?
It clarifies what needs to be built and how to verify each phase before implementation begins, reducing ambiguity in larger changes.

Skill for Claude CodeCodex

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/ozmasterai/torus-framework/prp
Any agent
npx skills add OZmasterAI/Torus-Framework --skill prp
Clone the repo
git clone --depth 1 https://github.com/OZmasterAI/Torus-Framework

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,483 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 $0.01483
Opus 5 $0.00000 $0.00741
Sonnet 5 $0.00000 $0.00297
Haiku 4.5 $0.00000 $0.00148

Measured 3d ago against content hash cd436650f412, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

dormant/skills/specialty/prp/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prp — Product Requirements Prompts

When to use

When user says "prp", "create a prp", "blueprint", "structured plan", or wants a comprehensive implementation blueprint for a complex feature.

Commands

  • /prp new-project <description> — Create requirements, roadmap, and first phase PRP
  • /prp generate <feature-description> — Research and create a PRP for a single feature
  • /prp plan-phase <prp-name> <phase-N> — Generate tasks for a phase, verify against requirements
  • /prp execute <prp-file> — Implement a PRP (or use /loop for fresh-context execution)
  • /prp verify-phase <prp-name> — 3-level verification: exists, substantive, wired
  • /prp list — List existing PRPs
  • /prp status <prp-name> — Show task pass/fail status from tasks.json

New Project Flow

  1. MEMORY CHECK: search_knowledge for similar projects, past PRPs
  2. GATHER REQUIREMENTS: Ask user about goals, scope, constraints
  3. CREATE REQUIREMENTS.md: Read ~/.claude/PRPs/templates/requirements.md, fill with R1..RN
  4. CREATE ROADMAP.md: Read ~/.claude/PRPs/templates/roadmap.md, decompose into phases
  5. CREATE CONTEXT.md: Read ~/.claude/PRPs/templates/context.md, fill with locked architectural decisions, constraints, naming conventions. These are injected into every executor prompt and cannot be overridden by tasks.
  6. PLAN FIRST PHASE: Auto-run plan-phase flow for Phase 1
  7. SAVE: Write to ~/.claude/PRPs/{project-name}/ directory
  8. REMEMBER: remember_this() with project summary and tags

Generate Flow (single feature PRP)

  1. MEMORY CHECK: search_knowledge for similar features, past PRPs, known issues
  2. CODEBASE SCAN: Explore relevant files, identify patterns to follow
  3. EXTERNAL RESEARCH: WebSearch/WebFetch for library docs, API references (if needed)
  4. FILL TEMPLATE: Read ~/.claude/PRPs/templates/base.md and fill every section
  5. SAVE: Write to ~/.claude/PRPs/{feature-name}.md 5b. GENERATE TASKS.JSON: Extract tasks from ## Implementation Tasks, create ~/.claude/PRPs/{feature-name}.tasks.json with id, name, status, requirement_id, files, validate, done, depends_on per task
  6. REMEMBER: remember_this() with the PRP summary and tags
  7. PRESENT: Show the PRP to the user for review/adjustment

Read the full file on GitHub · 91 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 · 91 lines · 0 tokens per session scan A cd436650f412

Subscribe to this mod's changes

prp is a skill published in the GitHub repository OZmasterAI/Torus-Framework (5 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,483 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens