gsr-learn

gsr-learn is a skill for Claude Code from kmajerowicz/get-shit-right. It costs 60 tokens per session (2,022 once invoked), scanned A, original, MIT.

A project-indexing procedure for GSR that scans an existing codebase, finds its documentation folder and technology stack, and updates CLAUDE.md, the agent's project-instructions file.

In plain words
What is it for?
Use it to prepare a new project for GSR or refresh the project information after significant code changes.
Why use it?
It reduces guesswork during onboarding and asks the human only when the files cannot answer a question.

Skill for Claude Code

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

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

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

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/kmajerowicz/get-shit-right/learn
Any agent
npx skills add kmajerowicz/get-shit-right --skill learn
Clone the repo
git clone --depth 1 https://github.com/kmajerowicz/get-shit-right

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-learn

README.md
[![agentmods](https://agentmods.dev/badge/skills/kmajerowicz/get-shit-right/learn.svg)](https://agentmods.dev/skills/kmajerowicz/get-shit-right/learn)
Your own site
<a href="https://agentmods.dev/skills/kmajerowicz/get-shit-right/learn"><img src="https://agentmods.dev/badge/skills/kmajerowicz/get-shit-right/learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,022 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 $0.00060 $0.02022
Opus 5 $0.00030 $0.01011
Sonnet 5 $0.00012 $0.00404
Haiku 4.5 $0.00006 $0.00202

Measured 5d ago against content hash 033d50c9423b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

gsr-learn 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 5d 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/learn/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/gsr:learn — Learn Skill

You are executing the /gsr:learn command. Your job is to index an existing project so that GSR can work with it, then tell the user exactly what to do next.

This skill serves two use cases:

  1. First run — onboarding a new codebase into GSR (Start B or Start C)
  2. Re-run — refreshing after significant codebase changes

Iron Law

Never ask a human to do something a file scan can answer. Read the code first. Ask only when the code can't tell you.


Step 1: Detect What Exists

Before asking the user anything, scan the project:

Read these if they exist:
- CLAUDE.md
- README.md
- package.json or equivalent
- src/ structure (top-level folders)
- Any config files (.env.example, tsconfig.json, next.config.*, etc.)

Doc directory detection — users may store docs in non-standard locations. Before looking for GSR artifacts, find the active doc root by checking these candidates in order:

1. .ai/          (Cursor AI, common AI-native projects)
2. .cursor/      (Cursor IDE docs)
3. ai/           (generic AI docs folder)
4. docs/         (traditional default)
5. doc/          (alternative spelling)
6. documentation/

Use the first directory that exists and contains any of: PRD.md, prd.md, scope.md, STATE.md, techstack.md, BACKLOG.md, or a features/ or work/ subfolder. If multiple candidates qualify, pick the one with the most matching files. If none qualify, default to docs/.

Once the doc root is identified (call it DOC_ROOT), read:

- DOC_ROOT/PRD.md (or prd.md)
- DOC_ROOT/scope.md
- DOC_ROOT/STATE.md
- DOC_ROOT/techstack.md
- DOC_ROOT/BACKLOG.md
- DOC_ROOT/features/ (list files)
- Any subdirectory that looks like feature specs (work/, specs/, features/)

From this scan, determine:

  • What GSR artifacts exist (CLAUDE.md, STATE.md, PRD.md, feature files)
  • Doc root — the directory where docs live (record this — all subsequent file creation uses this path)
  • Tech stack (language, framework, database, auth, hosting — from package.json/config)
  • Code conventions (naming patterns, folder structure — from src/)
  • Project maturity (has tests? has docs? has migrations?)

Read the full file on GitHub · 203 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. 5d ago First seen · 203 lines · 60 tokens per session scan A 033d50c9423b

Subscribe to this mod's changes

gsr-learn is a skill published in the GitHub repository kmajerowicz/get-shit-right (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 2,022 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

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