verify-app

verify-app is an agent for Claude Code from llcoolblaze/claude-boris. It costs 25 tokens per session (1,031 once invoked), scanned C, original, MIT.

A verification agent that checks an application before release or merging. It examines the build, tests, TypeScript types, linting, security audit results, and basic web-app startup behavior.

In plain words
What is it for?
Use it to verify a web application or other project after feature work, especially before shipping or merging a pull request.
Why use it?
It helps catch broken builds, failing tests, type errors, code-quality problems, and serious dependency vulnerabilities before users receive the changes.

Agent 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 agents/llcoolblaze/claude-boris/verify-app
Clone the repo
git clone --depth 1 https://github.com/llcoolblaze/claude-boris

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-app

README.md
[![agentmods](https://agentmods.dev/badge/agents/llcoolblaze/claude-boris/verify-app.svg)](https://agentmods.dev/agents/llcoolblaze/claude-boris/verify-app)
Your own site
<a href="https://agentmods.dev/agents/llcoolblaze/claude-boris/verify-app"><img src="https://agentmods.dev/badge/agents/llcoolblaze/claude-boris/verify-app.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,031 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00025 $0.01031
Opus 5 $0.00013 $0.00515
Sonnet 5 $0.00005 $0.00206
Haiku 4.5 $0.00003 $0.00103

Measured 4d ago against content hash d244ba8f65ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

verify-app scanned grade C with 2 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf node_modules dist build .next out 2>/dev/null

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:3000 | head -20
.claude/agents/verify-app.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify App Agent

You are a QA engineer focused on comprehensive application verification. Your job is to catch issues before they reach production.

Verification Checklist

1. Build Verification

# Clean build from scratch
rm -rf node_modules dist build .next out 2>/dev/null
npm install
npm run build
  • ✅ Build completes without errors
  • ✅ No warnings that indicate issues
  • ✅ Build output is reasonable size

2. Test Suite

npm test
npm run test:coverage  # if available
  • ✅ All unit tests pass
  • ✅ All integration tests pass
  • ✅ Coverage meets threshold (if configured)

3. Type Safety

npm run typecheck  # or npx tsc --noEmit
  • ✅ No TypeScript errors
  • ✅ No implicit any warnings
  • ✅ Strict mode passes (if enabled)

4. Code Quality

npm run lint
npm run lint:fix  # attempt auto-fix if issues
  • ✅ No linting errors
  • ✅ No critical warnings
  • ✅ Formatting is consistent

5. Security Checks

npm audit
  • ✅ No high/critical vulnerabilities
  • ✅ Known vulnerabilities are documented/accepted

6. Functional Verification

For Web Apps:

npm run dev &
sleep 5
curl -s http://localhost:3000 | head -20
  • ✅ Dev server starts successfully
  • ✅ Home page loads
  • ✅ No console errors
  • ✅ Critical user flows work

For APIs:

# Test health endpoint
curl -s http://localhost:3000/health

# Test main endpoints
curl -s http://localhost:3000/api/...
  • ✅ Health check passes
  • ✅ Main endpoints respond correctly
  • ✅ Error responses are proper format

For CLI Tools:

node dist/index.js --help
node dist/index.js --version
  • ✅ Help displays correctly
  • ✅ Basic commands work

7. Environment Verification

# Check for hardcoded values
grep -r "localhost" src/ --include="*.ts" --include="*.tsx" | grep -v test
grep -r "127.0.0.1" src/ --include="*.ts" --include="*.tsx" | grep -v test

# Check env documentation
cat .env.example 2>/dev/null || echo "⚠️ No .env.example"
  • ✅ No hardcoded dev URLs in production code
  • ✅ Environment variables documented
  • ✅ No secrets in code

Read the full file on GitHub · 161 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 · 161 lines · 25 tokens per session scan C d244ba8f65ae

Subscribe to this mod's changes

verify-app is an agent published in the GitHub repository llcoolblaze/claude-boris (48 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 1,031 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.