prd-03-rule-modeler

prd-03-rule-modeler is a skill for Claude Code, Codex from baobao2333/prd-agent-kit. It costs 64 tokens per session (816 once invoked), scanned A, original, MIT.

A method for turning product descriptions into precise rules that engineers and testers can implement. It defines objects, states, permissions, conditions, limits, timing, exceptions, and outcomes.

In plain words
What is it for?
Use it when converting a product requirements document into rules for engineering and quality assurance.
Why use it?
It replaces vague product language with clear behavior and records unknown details instead of guessing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when converting a product requirements document into rules for engineering and quality assurance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/baobao2333/prd-agent-kit/prd-03-rule-modeler
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.

Any agent
npx skills add baobao2333/prd-agent-kit --skill prd-03-rule-modeler
Clone the repo
git clone --depth 1 https://github.com/baobao2333/prd-agent-kit

Made for: Claude Code, Codex.

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-03-rule-modeler

README.md
[![agentmods](https://agentmods.dev/badge/skills/baobao2333/prd-agent-kit/prd-03-rule-modeler/github.svg)](https://agentmods.dev/skills/baobao2333/prd-agent-kit/prd-03-rule-modeler)
Your own site
<a href="https://agentmods.dev/skills/baobao2333/prd-agent-kit/prd-03-rule-modeler"><img src="https://agentmods.dev/badge/skills/baobao2333/prd-agent-kit/prd-03-rule-modeler/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prd-03-rule-modeler

Your own site · 80×15
<a href="https://agentmods.dev/skills/baobao2333/prd-agent-kit/prd-03-rule-modeler"><img src="https://agentmods.dev/badge/skills/baobao2333/prd-agent-kit/prd-03-rule-modeler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00064 $0.00816
Opus 5 $0.00032 $0.00408
Sonnet 5 $0.00013 $0.00163
Haiku 4.5 $0.00006 $0.00082

Measured 10d ago against content hash 08782904b3c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prd-03-rule-modeler 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 10d 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-03-rule-modeler/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.

PRD Rule Modeler

Purpose

Turn natural-language feature descriptions into rule language that engineering and QA can execute.

This skill is the heart of PRD quality. It removes vague phrases and replaces them with objects, states, conditions, actions, and exceptions.

Inputs

  • Business boundary document.
  • Any known product rules.
  • Any numerical thresholds or eligibility criteria.
  • Any known roles, permissions, or timing constraints.

Process

  1. Identify rule objects.
  2. Define states for each object.
  3. Define state transitions.
  4. Define permissions by role.
  5. Define triggering conditions.
  6. Define success and failure outcomes.
  7. Define time boundaries.
  8. Define repeat, reversal, deletion, expiration, and concurrency handling.
  9. Write a functional rule narrative that explains the rule set in continuous prose.
  10. Mark unknowns instead of filling them with fake certainty, then resolve any unknown that blocks engineering or QA before handoff.

Rule writing rules

  • Replace “support” with exact operation and result.
  • Replace “eligible user” with eligibility conditions.
  • Replace “high value” with threshold and time window.
  • Replace “system determines” with inputs and output states.
  • Replace “backend configurable” with actual config item, default value, and failure handling.
  • Replace “optimized later” with explicit non-goal or follow-up trigger.
  • If a threshold is not provided, choose a conservative initial default when product context supports it and mark the rationale.
  • If no responsible default can be chosen, ask the user before handing off instead of passing the gap downstream.
  • Do not let the output be only tables. Add a short prose narrative that connects objects, triggers, inputs, decisions, outputs, user-visible behavior, feedback, failure, and rollback.

Output format

# 02 Rule Model: {Feature Name}

## 1. Rule objects
| Object | Definition | Key fields / attributes | Notes |
|---|---|---|---|

## 2. States
| Object | State | Definition | Entry condition | Exit condition |
|---|---|---|---|---|

## 3. Permissions
| Role | Can view | Can operate | Cannot operate | Notes |
|---|---|---|---|---|

## 4. Core rules
| Rule ID | Rule | Trigger | Conditions | Result | User-facing response | Unknowns |
|---|---|---|---|---|---|---|

## 5. Time rules
| Rule | Start | End | Timezone / cycle | Boundary behavior |
|---|---|---|---|---|

## 6. Conflict and exception rules
| Case | System behavior | User-facing behavior | Needs confirmation? |
|---|---|---|---|
| Repeated operation |  |  |  |
| Concurrent operation |  |  |  |
| Expired resource |  |  |  |
| Deleted resource |  |  |  |
| Permission revoked |  |  |  |
| Old client version |  |  |  |

## 7. Functional rule narrative
{Continuous prose explaining how the feature works end to end using the rules above. Include trigger, inputs, system judgment, output, user-visible behavior, feedback, failure, and rollback.}

## 8. Handoff to next stage
Recommended next skill: `prd-04-flow-modeler`

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. 10d ago First seen · 91 lines · 64 tokens per session scan A 08782904b3c0

Subscribe to this mod's changes

prd-03-rule-modeler is a skill published in the GitHub repository baobao2333/prd-agent-kit (5 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 816 once invoked, about $0.0003 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 2026-08-31.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens