verify

verify is a command for coding agents from kmajerowicz/get-shit-right. It costs 16 tokens per session (305 once invoked), scanned A, a copy of learn, MIT.

A verification command for checking a feature or project phase with evidence such as a successful build, search results, and required human checks. It also confirms that the agent is working in the intended project directory.

In plain words
What is it for?
Use it after implementation to run the project’s verification process and confirm whether the relevant phases have passed.
Why use it?
It catches wrong-directory work and makes completion claims depend on observable checks instead of assumption.

Command

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 commands/kmajerowicz/get-shit-right/verify
Clone the repo
git clone --depth 1 https://github.com/kmajerowicz/get-shit-right

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 verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/kmajerowicz/get-shit-right/verify.svg)](https://agentmods.dev/commands/kmajerowicz/get-shit-right/verify)
Your own site
<a href="https://agentmods.dev/commands/kmajerowicz/get-shit-right/verify"><img src="https://agentmods.dev/badge/commands/kmajerowicz/get-shit-right/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 305 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00016 $0.00305
Opus 5 $0.00008 $0.00152
Sonnet 5 $0.00003 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured 5d ago against content hash a62b66c9a2cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

Origin

This is a copy

86% identical to learn — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

gsr/commands/verify.md · 19 lines

What it actually says

You are running the /gsr:verify command.

Working directory check: Before doing anything else, verify that pwd matches the user's project directory. If CLAUDE.md exists, check that the project name matches. If something looks wrong (you're in a different project's folder, or in a system directory), check .gsr-session.json in the current directory — it records the last known project directory. If it exists and points elsewhere, cd there. Otherwise, stop and ask the user to confirm the correct directory before proceeding.

Session manifest: After confirming the working directory, write .gsr-session.json in the project root:

{ "project_dir": "<absolute path>", "project_name": "<from CLAUDE.md or scope>", "last_command": "gsr:verify", "timestamp": "<ISO 8601>" }

Update this file (don't recreate) if it already exists — preserve project_dir and project_name, update last_command and timestamp.

Load and execute the verification skill: read ${CLAUDE_PLUGIN_ROOT}/skills/verification/SKILL.md in full, then follow its instructions exactly.

When verification is complete, tell the user:

Verification complete. If all phases PASS and backlog is triaged, the project is done. Otherwise, run /gsr:build to continue.

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 · 19 lines · 16 tokens per session scan A a62b66c9a2cd

Subscribe to this mod's changes

verify is a command published in the GitHub repository kmajerowicz/get-shit-right (5 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 305 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to learn, differing in 14 lines, and is treated as a copy.