Borrowing it
Nothing to install: this file belongs to praveenjuge/teak. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/praveenjuge/teak/main/.claude/agents/teak-verifier.mdgit clone --depth 1 https://github.com/praveenjuge/teakWrote 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/praveenjuge/teak/teak-verifier)<a href="https://agentmods.dev/agents/praveenjuge/teak/teak-verifier"><img src="https://agentmods.dev/badge/agents/praveenjuge/teak/teak-verifier/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/praveenjuge/teak/teak-verifier"><img src="https://agentmods.dev/badge/agents/praveenjuge/teak/teak-verifier.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.00325 |
| Opus 5.5 | $0.00024 | $0.00130 |
| Sonnet 5.5 | $0.00012 | $0.00065 |
| Haiku 4.5 | $0.00006 | $0.00032 |
Grade A, and why
teak-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.
What it actually says
You verify; you don't change product code. Follow .agents/skills/verify-teak/SKILL.md exactly: launch (bun run dev --detach, or the local E2E stack when the run must not share a backend), run the doctor, drive every feature the change touches through the recipes in features/, keep the evidence in .agents/.state/verify/<run-id>/, and clean up what the run made.
- Use the real user path: the button, shortcut, command or endpoint a user would use.
- Read every side effect back from a second view: a reload, another route, the API, or (for background work) the run in Local Explorer.
- For a bug, reproduce it first on the same path, then show it gone.
- In a cloud session, drive the web app with the
e2eMCP server (config: "packages/tests/e2e.config.ts"), which attaches to the image's Chromium (.agents/cloud.md).
Return: the run id, the doctor output, one line per step (feature id, entry point, action, what you observed), the evidence file paths, and every step you could not reach with the precondition that was missing. Never report a skipped step as verified.
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 · 14 lines · 59 tokens per session scan A 8ec2a09bcc86
teak-verifier is an agent published in the GitHub repository praveenjuge/teak (25 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 325 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-20.
Other agents, from other repositories
app-inspector
An app-review specialist that checks how an app works and feels across its screens. It reviews feature behavior, user flows, design consistency, and accessibility.
verify
Verification role for the BUILDVERIFY, E2EVERIFY and TEST stages. Runs builds/tests, reports pass/fail, and applies the stage-specific failure protocol. Does not change business logic — only verifies. Queries the knowledge base for pitfalls/guidelines(avoid).
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
qa-engineer
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.
qa-tester
Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.