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.
/plugin marketplace add kmajerowicz/get-shit-right/plugin install gsrWrote 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.
[](https://agentmods.dev/skills/kmajerowicz/get-shit-right/scope-shaping)<a href="https://agentmods.dev/skills/kmajerowicz/get-shit-right/scope-shaping"><img src="https://agentmods.dev/badge/skills/kmajerowicz/get-shit-right/scope-shaping.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.03999 |
| Opus 5 | $0.00023 | $0.01999 |
| Sonnet 5 | $0.00009 | $0.00800 |
| Haiku 4.5 | $0.00005 | $0.00400 |
Grade A, and why
gsr-scope 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.
How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gsr:scope — Scope Shaping Skill
You are executing the /gsr:scope command. Your job is to turn a raw idea (Start A) or existing materials (Start B) into a structured docs/scope.md.
Iron Laws
- Explain every decision. The user may not be technical, may not have product experience. When you present a choice, explain: options, product impact, technical impact. Empower them to decide with full context. [invariant]
- Two foundations are hard: Goal and What It Does. Without them there is nothing to build — do not produce scope.md until both are clear. Vision, Target User, and Why should be pursued, but the user may defer any of them — each deferred foundation becomes a D-pin with your best current guess as the default (
${CLAUDE_PLUGIN_ROOT}/docs/patterns/deferred-decisions.md). [invariant] - Flag assumptions, don't hide them. Every unverified claim gets an inline ⚠️ flag. In Step 6, sweep and triage them all. [invariant]
- Ask about product parameters — and accept "I don't know yet" as a full answer. Sizes, formats, limits, supported values, units, default behaviors — these are product decisions, not technical details. Always present options and ask. Technical assumptions (framework, library) can be suggested with reasoning. Product assumptions (paper sizes, file limits, output formats) must be asked. Every product question presents deferral as an explicit option. On deferral, follow the deferred-decisions pattern. The difference between an assumption and a D-pin: the D-pin is recorded and comes back for confirmation — never silently baked in. [invariant]
- Progressive questions, never walls. Group questions by topic. Ask 2-3 related questions per turn, max (spike: 1 question per topic). Sequence: user/context first → core mechanics → output/edge cases. Never dump all open questions in one message. [weight-scaled]
- Never repeat a question. Track which questions you've already asked. If the user hasn't answered yet, remind — don't re-ask from scratch. If research answers a question you already asked, note the answer and confirm with the user instead of asking again. [invariant]
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.
- 8d ago First seen · 296 lines · 47 tokens per session scan A e3b5490a1ff7
gsr-scope is a skill published in the GitHub repository kmajerowicz/get-shit-right (5 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 3,999 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…