gsr-quick

gsr-quick is a skill for Claude Code, Codex from kmajerowicz/get-shit-right. It costs 56 tokens per session (613 once invoked), scanned A, original, MIT.

A GSR procedure for completing one small, clearly bounded coding task with evidence, human control over product decisions, and an atomic commit, a commit containing one focused change.

In plain words
What is it for?
Use it for small fixes or changes that do not need a scope document, product requirements document, or full workflow.
Why use it?
It avoids the planning ceremony used for larger work while preserving checks that prevent unsupported completion claims, missing assets, and unclear user-facing decisions.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

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-quick

README.md
[![agentmods](https://agentmods.dev/badge/skills/kmajerowicz/get-shit-right/quick.svg)](https://agentmods.dev/skills/kmajerowicz/get-shit-right/quick)
Your own site
<a href="https://agentmods.dev/skills/kmajerowicz/get-shit-right/quick"><img src="https://agentmods.dev/badge/skills/kmajerowicz/get-shit-right/quick.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 613 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 $0.00056 $0.00613
Opus 5 $0.00028 $0.00307
Sonnet 5 $0.00011 $0.00123
Haiku 4.5 $0.00006 $0.00061

Measured 4d ago against content hash 26640455f377, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsr-quick 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 4d 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/quick/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/gsr:quick — Quick Task Skill

One bounded task, GSR invariants, zero ceremony. No scope, no PRD, no feature file, no mode selection, no skills-matching gate.

Iron Laws (all invariants — no exceptions at any project weight)

  1. Evidence before "done". Run the gate function; use the evidence format. Banned phrases: "should work", "seems correct", "looks good".
  2. Human owns product decisions. If the task hides a product decision (user-visible behavior, limits, formats), surface it via the decision gate pattern — or record a D-pin if the user defers and a ledger exists.
  3. Corrections compound. On user correction: implement, then ask "Add to CLAUDE.md Learned Rules?"
  4. Atomic commit with evidence in the message.
  5. Never reference assets that don't exist.

Flow

  1. Read CLAUDE.md if it exists (conventions + Learned Rules). Read nothing else upfront.
  2. Restate the task in one line; if scope is genuinely ambiguous, ask ONE clarifying question, else proceed.
  3. Implement in the smallest reasonable diff.
  4. Run the gate per ${CLAUDE_PLUGIN_ROOT}/skills/gate/SKILL.md (single source of truth).
  5. Report with the evidence format: ✅ <command> → <output summary> → "<claim>"
  6. Commit: <type>: <task> — <evidence summary>.
  7. If docs/STATE.md exists, append one line under a ## Quick Tasks section (create it at the end of the file if missing): - [<date>] <task> — <commit sha>. If it doesn't exist, skip silently — quick works without GSR structure.

Escalation

If the task turns out to touch >5 files, need a product decision the user won't make inline, or break existing behavior: stop and say "This outgrew quick — recommend /gsr:build (or /gsr:scope if the product is undefined)." Never soldier on past the boundary.

Red Flags

Thought Reality
"It's quick mode, I'll skip the gate function" Invariant. Evidence or it didn't happen.
"I'll expand scope while I'm in here" Quick = the asked task. Note extras, don't do them.
"No STATE.md, so I can't work" Quick needs nothing. Work.

Read the full file on GitHub · 52 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. 4d ago First seen · 52 lines · 56 tokens per session scan A 26640455f377

Subscribe to this mod's changes

gsr-quick is a skill published in the GitHub repository kmajerowicz/get-shit-right (5 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 613 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

contributing

How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…

HugoRCD/evlog · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

git-commit

Creates git commits following Conventional Commits format with type/scope/subject and detailed markdown body. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md. Each change type gets its own markdown heading (# emoji + type), with…

redai-infra/Relax · 73 tokens

writing-commit-messages

Write clear, conventional commit messages with proper type prefixes, scopes, and body content.

spencerpauly/awesome-cursor-skills · 23 tokens

git-mastery

Advanced Git: rebase, bisect, reflog, cherry-pick, worktrees, LFS. Triggers: rebase, bisect, cherry-pick, reflog, force push, merge conflict, worktree.

softspark/ai-toolkit · 51 tokens

doc-sync

Synchronize each repo's .docs/ and README.md with recently succeeded plans/issues/benchmarks by diffing git history against the last documented entry. Use after landing a GOAT-passing plan, closing a batch of issues, or quarterly as a doc-hygiene gate. Covers every workspace repo and knows each repo's doc layout +…

katopz/katgpt-rs · 97 tokens