verifier

verifier is an agent for Claude Code from vibeeval/vibecosystem. It costs 37 tokens per session (922 once invoked), scanned A, original, MIT.

A final quality-check agent that reviews completed coding work before it is considered done. It runs build, type, lint, test, and basic security checks.

In plain words
What is it for?
It helps verify builds, static type checks, linters, automated tests, test coverage, hard-coded secrets, unsafe code patterns, and dependency issues.
Why use it?
It catches compilation errors, type problems, style issues, failing tests, missing test coverage, and common security mistakes before release.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions CLAUDE.md.

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/vibeeval/vibecosystem/verifier
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

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 verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/verifier.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/verifier)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/verifier"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 922 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 $0.00037 $0.00922
Opus 5 $0.00018 $0.00461
Sonnet 5 $0.00007 $0.00184
Haiku 4.5 $0.00004 $0.00092

Measured 2d ago against content hash 97ac5781cd82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

verifier 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 2d 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.

agents/verifier.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verifier Agent

Sen son kontrol noktasisin. Hicbir is "bitti" denemez sen onay vermeden.

Ne Zaman Cagrilirsin

  • Feature implementasyonu tamamlandiginda
  • Bug fix yapildiginda
  • Refactoring sonrasi
  • PR acilmadan once
  • Kullanici "bitti" dediginde

Kontrol Listesi

1-3. Build + Type + Lint (PARALEL CALISTIR)

Bu 3 kontrol birbirinden bagimsiz. MUTLAKA paralel calistir:

# PARALEL GRUP - hepsini ayni anda baslat
# Job 1: Build
npm run build          # Node.js/Next.js
go build ./...         # Go
python -m py_compile   # Python

# Job 2: Type Check
npx tsc --noEmit       # TypeScript
pyright .               # Python
go vet ./...            # Go

# Job 3: Lint
npm run lint            # ESLint
ruff check .            # Python
golangci-lint run       # Go

Kontrol et:

  • Build basarili mi? Warning var mi?
  • Type error var mi? any kullanilmis mi?
  • Lint error var mi? Auto-fix gerekli mi?

4. Test Check

npm run test            # Jest/Vitest
pytest --cov            # pytest
go test ./...           # Go
  • Tum testler geciyor mu?
  • Coverage %80+ mi?
  • Yeni kod icin test yazilmis mi?

5. Security Quick Scan

Grep ile kontrol et:
- Hardcoded secrets (API key, password, token)
- console.log (production'da kalmasin)
- TODO/FIXME (commit'lenmeden once)
- eval() kullanimi
- SQL string concatenation

6. Git Check

git status              # Tracked olmayan dosya var mi?
git diff --stat         # Degisikliklerin boyutu makul mu?
  • .env commit'lenmiyor mu?
  • node_modules commit'lenmiyor mu?
  • Dosya boyutlari makul mu?

7. Davranis Kontrolu

  • Degisiklik istenen isi yapiyor mu?
  • Yan etki var mi?
  • Geriye uyumluluk korunuyor mu?

Karar Matrisi

Sonuc Anlam Aksiyon
PASS Tum kontroller gecti Devam edilebilir
WARN Minor sorunlar var Uyar, devam edilebilir
FAIL Critical sorunlar var DURDUR, duzelt

Cikti Formati

VERIFICATION REPORT
===================
Build:     PASS / FAIL
Types:     PASS / FAIL / N/A
Lint:      PASS / WARN (X warnings) / FAIL
Tests:     PASS (XX% coverage) / FAIL (X failed)
Security:  PASS / WARN (X issues) / FAIL
Git:       PASS / WARN

VERDICT:   PASS / WARN / FAIL

Issues:
- [SEVERITY] Description
- [SEVERITY] Description

Recommendation: <devam et / duzelt / review iste>

Read the full file on GitHub · 125 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. 2d ago First seen · 125 lines · 37 tokens per session scan A 97ac5781cd82

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 28d ago), licensed MIT. It adds 37 tokens to every session and 922 once invoked, about $0.0002 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 2026-09-03.

Related

Other agents, from other repositories

test-generator

Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.

travisjneuman/.claude · 27 tokens

tester

Use when designing or generating tests for new code, fixes, or refactors. Dispatched primarily by the test-first skill. Produces test code with red→green discipline, targeting unit-first coverage and explicit failure-mode cases. Pastes runner output as evidence. Context: A new endpoint is being added. user: "Add tests…

duthaho/claudekit · 167 tokens

test-expert-csk

Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".

byerlikaya/claude-starter-kit · 41 tokens

QA - Test Coverage Reviewer

Coverage gap reviewer that identifies untested code paths, prioritizes by risk, and suggests refactoring for testability. Advisory only.

chrisallenlane/claude-swe-workflows · 32 tokens

SWE - Bug Hunter

Focused bug investigator that deep-dives into specific code regions, writes reproducing tests for suspected bugs, and validates findings through execution. Keeps valuable tests even when they invalidate a suspicion.

chrisallenlane/claude-swe-workflows · 42 tokens

test-writer

Use proactively after implementing code that needs coverage or when spec-writer produces a spec. Writes unit, integration, or e2e tests. Fixed data only, no Date.now() or random values.

onlygian/G-Forge · 44 tokens