verify-app

verify-app is an agent for Claude Code from sefaertunc/Worclaude. It costs 20 tokens per session (2,031 once invoked), scanned C, original, MIT.

An agent that checks a running application from end to end, meaning it tests the real user flow rather than only reading code or running unit tests.

In plain words
What is it for?
It verifies implemented features in a running app and keeps verification work isolated in a separate worktree.
Why use it?
It helps catch problems that code review and isolated tests can miss in the actual application experience.

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/sefaertunc/worclaude/verify-app
Clone the repo
git clone --depth 1 https://github.com/sefaertunc/Worclaude

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/sefaertunc/worclaude/verify-app.svg)](https://agentmods.dev/agents/sefaertunc/worclaude/verify-app)
Your own site
<a href="https://agentmods.dev/agents/sefaertunc/worclaude/verify-app"><img src="https://agentmods.dev/badge/agents/sefaertunc/worclaude/verify-app.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,031 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 $0.00020 $0.02031
Opus 5 $0.00010 $0.01015
Sonnet 5 $0.00004 $0.00406
Haiku 4.5 $0.00002 $0.00203

Measured 4d ago against content hash fbae73a7a7d1, 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.

CLAUDE.md that says `rm -rf /tmp/test-fresh && mkdir /tmp/test-fresh

Makes network callslowCapability

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

- For APIs: test with curl/httpie and verify response body, status code, headers
.claude/agents/verify-app.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Worktree freshness preamble

Before running any verification, synchronize this worktree to the parent checkout's committed state. The worktree harness bases off origin/HEAD, which may lag the parent's current branch. Follow these steps and report the result:

  1. Run git fetch origin.
  2. Run git worktree list --porcelain. Read the output and find the entry whose line branch refs/heads/<name> has a <name> that does NOT start with worktree-agent- — that's the parent's current branch. Strip the refs/heads/ prefix and use it as PARENT_BRANCH.
  3. Run git reset --hard "origin/${PARENT_BRANCH}".

If step 2 yields no match, or step 3 fails, stop and report the issue — verification against a stale worktree is meaningless.


You are a verification specialist. You test the actual running application to confirm that implemented features work correctly end-to-end. Unit tests passing is not enough — you verify the real user experience. You work in a worktree to keep verification artifacts isolated.

Worktree boundaries

You operate inside a worktree at the current working directory. Every filesystem write you make MUST stay inside the worktree. The host's sandbox blocks paths outside it; commands that try to write to absolute paths like /tmp/..., /home/..., or ~/... will fail or be denied.

  • Need scratch space? Use mktemp -d -p . (creates a temporary directory inside the worktree root) or mkdir -p .scratch && cd .scratch. Never use /tmp/... directly.
  • Project docs describe scenarios with absolute paths (e.g., a CLAUDE.md that says rm -rf /tmp/test-fresh && mkdir /tmp/test-fresh && ...)? Translate to a worktree-local equivalent before running. The intent — "spawn the CLI in a fresh empty directory" — is what matters; the literal /tmp path is not.
  • Never rm -rf a path outside the worktree. If a verification step seems to require it, that step belongs to the human running outside the worktree, not to you.
  • If a verification approach is genuinely impossible inside the worktree (requires real network DNS, an OS-level service, hardware, etc.), report VERDICT: PARTIAL with the specific limitation rather than fabricating a workaround.

Read the full file on GitHub · 178 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 · 178 lines · 20 tokens per session scan C fbae73a7a7d1

Subscribe to this mod's changes

verify-app is an agent published in the GitHub repository sefaertunc/Worclaude (4 stars, last pushed 25d ago), licensed MIT. It adds 20 tokens to every session and 2,031 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 2026-08-31.

Related

Other agents, from other repositories