verify

verify is a command for Claude Code from sumulige/sumulige-claude. It costs 12 tokens per session (1,633 once invoked), scanned A, original, MIT.

A pre-pull-request check that runs build, formatting, tests, coverage, and other quality checks in five stages. A pull request is a proposed change submitted for review before it is merged.

In plain words
What is it for?
Use it before opening a pull request, or use its quick option to skip coverage checks or its fix option to correct formatting automatically.
Why use it?
It finds problems that could block review or break the project before the change is submitted.

Command for Claude Code

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/sumulige/sumulige-claude/verify
Clone the repo
git clone --depth 1 https://github.com/sumulige/sumulige-claude

Made for: Claude Code.

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/sumulige/sumulige-claude/verify.svg)](https://agentmods.dev/commands/sumulige/sumulige-claude/verify)
Your own site
<a href="https://agentmods.dev/commands/sumulige/sumulige-claude/verify"><img src="https://agentmods.dev/badge/commands/sumulige/sumulige-claude/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,633 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 $0.00012 $0.01633
Opus 5 $0.00006 $0.00816
Sonnet 5 $0.00002 $0.00327
Haiku 4.5 $0.00001 $0.00163

Measured 4d ago against content hash 300f9c05cfbb, 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/commands/verify.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/verify - Pre-PR Verification Loop

Run all quality checks to ensure code is ready for PR submission.

Usage

/verify           # Run all 5 phases
/verify --quick   # Skip coverage check (faster)
/verify --fix     # Auto-fix formatting issues before check

Verification Phases

Execute each phase sequentially. If a blocking phase fails, stop and fix before continuing.


Phase 1: Sanity Check (Build)

Verify the CLI loads without errors:

node cli.js --version
Result Meaning
Version displayed PASS
Error thrown FAIL (blocking)

Phase 2: Format Check (Lint)

Check code formatting with Prettier:

npx prettier --check "**/*.{js,cjs,mjs,json,md}" --ignore-path .gitignore

If issues found (--fix mode):

npx prettier --write "**/*.{js,cjs,mjs,json,md}" --ignore-path .gitignore
Result Meaning
All files formatted PASS
Files need formatting WARN (non-blocking, fixable)

Phase 3: Test Suite

Run all tests with coverage:

npm run test:coverage

Coverage Requirements (from .claude/rules/testing.md):

Code Type Minimum
General business logic 80%
Financial/Auth/Security 100%
Result Meaning
Tests pass, coverage >= 80% PASS
Tests pass, coverage < 80% FAIL (blocking)
Tests fail FAIL (blocking)

For --quick mode, run without coverage:

npm test

Phase 4: Security Scan

Scan for hardcoded secrets and debugging statements:

4.1 Check for console.log in production code:

grep -rn "console\.log\|console\.debug\|console\.info" --include="*.js" --include="*.cjs" --exclude-dir=node_modules --exclude-dir=tests --exclude-dir=coverage lib/ cli.js 2>/dev/null || echo "No console logs found"

4.2 Check for hardcoded secrets:

grep -rn "sk-[a-zA-Z0-9]\{20,\}\|ghp_[a-zA-Z0-9]\{36\}\|AKIA[A-Z0-9]\{16\}" --include="*.js" --include="*.cjs" --exclude-dir=node_modules lib/ cli.js 2>/dev/null || echo "No secrets found"

Read the full file on GitHub · 283 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 · 283 lines · 12 tokens per session scan A 300f9c05cfbb

Subscribe to this mod's changes

verify is a command published in the GitHub repository sumulige/sumulige-claude (2 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 1,633 once invoked, about $0.0001 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.