gsr-verify

gsr-verify is a skill for Claude Code from kmajerowicz/get-shit-right. It costs 52 tokens per session (4,395 once invoked), scanned A, original, MIT.

A checklist for checking a completed software feature or build phase against its required outcomes. It uses build results, searches, visual checks, tests, and human review when needed.

In plain words
What is it for?
Use it to verify project state, builds, requirements, tests, visual behavior, and evidence before marking a feature complete. It can also review a product specification when no code has been built yet.
Why use it?
It prevents declaring work finished based only on a status claim. It identifies blockers that stop release and separates them from smaller issues that can wait.

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

Good fit Use it to verify project state, builds, requirements, tests, visual behavior, and…

Compare 6 skills from other repositories ↓
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-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/kmajerowicz/get-shit-right/verification.svg)](https://agentmods.dev/skills/kmajerowicz/get-shit-right/verification)
Your own site
<a href="https://agentmods.dev/skills/kmajerowicz/get-shit-right/verification"><img src="https://agentmods.dev/badge/skills/kmajerowicz/get-shit-right/verification.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,395 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 $0.00052 $0.04395
Opus 5 $0.00026 $0.02197
Sonnet 5 $0.00010 $0.00879
Haiku 4.5 $0.00005 $0.00439

Measured 6d ago against content hash b35b83b40abf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

gsr-verify 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 6d 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/verification/SKILL.md · 426 lines

How it starts

The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/gsr:verify — Verification Skill

You are executing the /gsr:verify command. Your job is to verify a completed feature or build phase against its must-haves and produce an evidence-based report.


Iron Laws

  1. "All tasks done" is not verification. Check actual outcomes. Run commands. Read output. Verify with evidence. [invariant]
  2. Always exhaust lower tiers before escalating to human. Never ask a human to verify something a grep or build command can answer. [invariant]
  3. Blockers block. Minors don't. A Blocker means the feature is not done. A Minor goes to BACKLOG.md and the phase can still PASS. [invariant]

Step 0: Detect Project State

Read docs/STATE.md. Check the phase progress table. Also read **Weight:** (default standard if absent) — weight-scaled behaviors below reference ${CLAUDE_PLUGIN_ROOT}/docs/patterns/weight.md.

If all phases are NOT STARTED → the project has no built code to verify. Switch to PRD Review Mode (see section below). Do not proceed with Steps 1–5.

Otherwise → continue to Step 1 (build verification).


PRD Review Mode

The project has no built phases yet. Instead of verifying code, verify the spec — catch problems now before they become expensive to fix mid-build.

Run all 5 checks below. For each: fix what you can directly in docs/PRD.md and docs/features/*.md, surface what needs a user decision as a decision gate.

Check 1: Cross-Phase Dependency

For every feature in every phase, ask: does this feature depend on something only delivered in a later phase?

Common traps:

  • UI component references a service built in a later phase
  • Phase N demo sentence requires data only available after Phase N+2
  • Shared infrastructure (auth, caching, service workers) used before it's scaffolded

For each conflict found: either move the dependency earlier, swap phase order, or add a "scaffold in Phase X, complete in Phase Y" note. Fix directly if unambiguous; use a decision gate if trade-offs exist.

Read the full file on GitHub · 426 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. 6d ago First seen · 426 lines · 52 tokens per session scan A b35b83b40abf

Subscribe to this mod's changes

gsr-verify is a skill published in the GitHub repository kmajerowicz/get-shit-right (5 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 4,395 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

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens