verify

verify is a skill for Claude Code, Codex from lukas-grigis/ralphctl. It costs 54 tokens per session (468 once invoked), scanned A, original, MIT.

A single project check that runs type checking, linting, and tests in sequence. Type checking catches incorrect code types, linting checks code rules, and tests check behavior.

In plain words
What is it for?
Use it after code changes or when checking whether a project is ready to ship.
Why use it?
It provides one repeatable command for finding common problems before committing changes or shipping code, stopping at the first failed check.

Skill for Claude CodeCodex

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/lukas-grigis/ralphctl/verify
Any agent
npx skills add lukas-grigis/ralphctl --skill verify
Clone the repo
git clone --depth 1 https://github.com/lukas-grigis/ralphctl

Made for: Claude Code, Codex.

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/skills/lukas-grigis/ralphctl/verify.svg)](https://agentmods.dev/skills/lukas-grigis/ralphctl/verify)
Your own site
<a href="https://agentmods.dev/skills/lukas-grigis/ralphctl/verify"><img src="https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 468 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 $0.00054 $0.00468
Opus 5 $0.00027 $0.00234
Sonnet 5 $0.00011 $0.00094
Haiku 4.5 $0.00005 $0.00047

Measured 4d ago against content hash 3028bc493c7f, 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 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.

.claude/skills/verify/SKILL.md · 37 lines

What it actually says

Verify

Run the project's verification gate as a single command:

pnpm typecheck && pnpm lint && pnpm test

All three MUST pass. If any step fails, report which one, show the error, and stop — don't move on until the failure is addressed.

Why these three, in this order

  1. pnpm typechecktsc (noEmit set in tsconfig.json). Fastest feedback; catches most issues.
  2. pnpm lint — ESLint. Includes the Clean Architecture layer fence ( domain → business → integration → application), the no-class fence (outside domain/value/error/), the no-barrels fence, and the sibling-isolation rules under integration/ai/<concept>/. A layer violation shows up here.
  3. pnpm test — vitest (vitest run). The full suite, including flow step-order integration tests that lock the architectural shape.

Running them chained with && short-circuits on the first failure, which is what we want.

Not a replacement for

  • pnpm format:check / pnpm format — Prettier. The pre-commit hook handles staged files; run format:check manually for a full sweep before opening a PR.
  • pnpm deadcode — knip. One-off audit; symbols intentionally exported are whitelisted via @public JSDoc tag + knip.json#tags: ["-public"].
  • pnpm buildtsup + tsx scripts/build-assets.ts. Only needed before publishing to npm; CI verifies the bundle from arbitrary cwd.
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 · 37 lines · 54 tokens per session scan A 3028bc493c7f

Subscribe to this mod's changes

verify is a skill published in the GitHub repository lukas-grigis/ralphctl (23 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 468 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 2026-08-30.