verify

verify is a command for Claude Code from kumaran-is/claude-code-onboarding. It costs 0 tokens per session (819 once invoked), scanned A, original, MIT.

A command that checks whether changed code compiles and passes the selected verification steps, returning a binary PASS or FAIL result.

In plain words
What is it for?
Use it for quick checks, full test runs, pre-commit checks, or pre-pull-request verification in supported project stacks.
Why use it?
It provides quick feedback about build, lint, test, security, coverage, and leftover debug-code problems before a commit or pull request.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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/kumaran-is/claude-code-onboarding/verify
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

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/kumaran-is/claude-code-onboarding/verify.svg)](https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/verify)
Your own site
<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/verify"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 819 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 5.1 $0.00000 $0.00819
Opus 5 $0.00000 $0.00409
Sonnet 5 $0.00000 $0.00164
Haiku 4.5 $0.00000 $0.00082

Measured 3d ago against content hash 58bdb3939131, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 3d 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 · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/verify — Binary Build + Test Verification

Runs the fastest possible verification for changed stacks. Returns binary PASS/FAIL with counts.

Modes

/verify (default: quick)

Compile + lint only. No test execution. Fastest feedback.

/verify full

Compile + lint + all tests. Full confidence.

/verify pre-commit

Quick verify + check for TODO/FIXME/console.log in staged files.

/verify pre-pr

Full verify + security scan + coverage check.

Stack Detection + Commands

Detected by file presence in current directory tree:

Spring Boot (pom.xml with spring-boot)

# quick
./mvnw compile -q 2>&1; echo "EXIT:$?"

# full
./mvnw test -q 2>&1 | tail -5; echo "EXIT:$?"

# pre-pr additions
./mvnw dependency-check:check -q 2>&1 | grep -E "(CRITICAL|HIGH)"

Python (pyproject.toml or requirements.txt)

# quick
python -m py_compile $(find src -name "*.py") && ruff check src/ -q
echo "EXIT:$?"

# full
pytest -q 2>&1 | tail -5; echo "EXIT:$?"

# pre-pr additions
bandit -r src/ -ll -q

NestJS (package.json with @nestjs/core)

# quick
npm run build -- --silent 2>&1 | tail -5; echo "EXIT:$?"

# full
npm run test -- --silent 2>&1 | tail -5; echo "EXIT:$?"

# pre-pr additions
npm audit --audit-level=high

Angular (angular.json)

# quick
npm run build -- --configuration=production --silent 2>&1 | tail -5; echo "EXIT:$?"

# full
npm test -- --watch=false --browsers=ChromeHeadless 2>&1 | tail -5; echo "EXIT:$?"

Flutter (pubspec.yaml with flutter:)

# quick
flutter analyze --no-pub -q 2>&1 | tail -5; echo "EXIT:$?"

# full
flutter test -q 2>&1 | tail -5; echo "EXIT:$?"

Output Format

## Verification — {mode} — {date}

| Stack | Compile | Tests | Status |
|-------|---------|-------|--------|
| Spring Boot | ✅ EXIT 0 | ✅ 47 passed | PASS |
| Python | ✅ EXIT 0 | ❌ 2 failed | FAIL |
| NestJS | ✅ EXIT 0 | ✅ 83 passed | PASS |
| Flutter | ✅ EXIT 0 | ✅ 31 passed | PASS |

### FAIL Details
Python — 2 failures:
- test_create_user_duplicate: AssertionError at tests/test_user.py:45
- test_payment_timeout: TimeoutError at tests/test_payment.py:78

## Final Verdict: ❌ FAIL (1 of 4 stacks failing)

Read the full file on GitHub · 115 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. 3d ago First seen · 115 lines · 0 tokens per session scan A 58bdb3939131

Subscribe to this mod's changes

verify is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 819 tokens. 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 2026-09-03.