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.
npx agentmods add agents/vibeeval/vibecosystem/verifiergit clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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.
[](https://agentmods.dev/agents/vibeeval/vibecosystem/verifier)<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>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.
| Model | Per session | Once 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 |
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.
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>
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.
- 2d ago First seen · 125 lines · 37 tokens per session scan A 97ac5781cd82
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.
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.
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…
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".
QA - Test Coverage Reviewer
Coverage gap reviewer that identifies untested code paths, prioritizes by risk, and suggests refactoring for testability. Advisory only.
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.
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.