agentmods.dev

gsr-prd

gsr-prd is a skill for Claude Code from kmajerowicz/get-shit-right. It costs 61 tokens per session (3,287 once invoked), scanned A, original, MIT.

A process for turning a project scope document into a product requirements document (PRD), feature files, and basic project documentation. A PRD explains what a product should do without describing its technical implementation.

In plain words
What is it for?
Use it after shaping scope to create docs/PRD.md, feature documents, and files such as project state, backlog, and technology notes. Each build phase also gets a sentence describing what the user can do afterward.
Why use it?
It gives a raw idea a structured, checkable plan before development begins. It also keeps product decisions separate from technical details such as code, database designs, and routes.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the gsr plugin — 8 skills, 10 commands, 4 agents, 4 hooks shipped together

not rated 5repo 1mo ago A scan 61 tokens original MIT

Good fit Use it after shaping scope to create docs/PRD.md, feature documents, and files such as project state, backlog, and technology notes. Each build phase also gets a sentence describing what the user can do afterward.

Compare 6 skills from other repositories ↓
View source ↗ kmajerowicz/get-shit-right
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add kmajerowicz/get-shit-right
Claude Code
/plugin install gsr

Made for: Claude Code.

Or install gsr, the plugin that ships this one along with the rest of its 8 skills, 10 commands, 4 agents, 4 hooks.

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 gsr-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/kmajerowicz/get-shit-right/prd-generation.svg)](https://agentmods.dev/skills/kmajerowicz/get-shit-right/prd-generation)
Your own site
<a href="https://agentmods.dev/skills/kmajerowicz/get-shit-right/prd-generation"><img src="https://agentmods.dev/badge/skills/kmajerowicz/get-shit-right/prd-generation.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,287 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 $0.00061 $0.03287
Opus 5 $0.00030 $0.01643
Sonnet 5 $0.00012 $0.00657
Haiku 4.5 $0.00006 $0.00329

Measured 8d ago against content hash 6cb65e8214fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gsr-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 8d 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.

gsr/skills/prd-generation/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/gsr:prd — PRD Generation Skill

You are executing the /gsr:prd command. Your job is to generate docs/PRD.md, docs/features/*.md, and the full project infrastructure from docs/scope.md.

This skill runs Phase 1 (PRD generation) + Phase 2 (project init) in one flow.

Iron Laws

  1. PRD is purely product. No tech stack, no schemas, no routes, no design tokens. Those live in code and CLAUDE.md. If you catch yourself writing a column name or route path in PRD.md — stop. Move it to code. [invariant]
  2. Every build phase must have a demo sentence. "User can [do X] after this phase." If you can't write it, the phase is too abstract. Restructure. [invariant]
  3. Skills are boosters, not blockers. The PRD is complete whether or not skills are installed. Skills enhance quality, not enable completion. [invariant]

Model Recommendation (show first, once)

Before any detection or action, show this one-liner to the user (exact text):

💡 This step is reasoning-heavy (PRD and feature files shape the entire implementation). It works best on Opus — if you're not on Opus, consider /model opus now and come back. Otherwise, let's keep going.

Do not wait for a response. Proceed immediately to "Step 0: Detect Mode" below. Show this reminder only once per session.

Step 0: Detect Mode

Read **Weight:** from docs/STATE.md (default standard if absent). Weight-scaled behaviors below reference ${CLAUDE_PLUGIN_ROOT}/docs/patterns/weight.md.

Before doing anything, check if docs/PRD.md already exists.

If PRD.md exists → Update mode:

  • Read docs/PRD.md and docs/scope.md
  • Do NOT re-run research. Research was already done for the existing PRD.
  • Identify what changed: compare scope with what's reflected in the PRD. List the deltas.
  • Update only the sections that need to change. Leave the rest untouched.
  • Skip straight to the self-verification pass (Step 1), then present changes to user.

If PRD.md does not exist → Full generation mode:

  • Read docs/scope.md and any design references the user mentions
  • Resolve research areas from scope.md marked "blocking PRD" before writing — dispatch researcher agents in parallel for independent research questions. Dispatch via the Agent tool with subagent_type: "gsr:researcher" — model and role come from the agent definition.
  • Proceed through Step 1 in full

Read the full file on GitHub · 265 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. 8d ago First seen · 265 lines · 61 tokens per session scan A 6cb65e8214fb

Subscribe to this mod's changes

gsr-prd is a skill published in the GitHub repository kmajerowicz/get-shit-right (5 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 3,287 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.

PlanningWriting and docs
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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens