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/boringmarketer/kimi-first/verifiergit clone --depth 1 https://github.com/boringmarketer/kimi-firstWrote 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/boringmarketer/kimi-first/verifier)<a href="https://agentmods.dev/agents/boringmarketer/kimi-first/verifier"><img src="https://agentmods.dev/badge/agents/boringmarketer/kimi-first/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 | $0.00093 | $0.00447 |
| Opus 5 | $0.00046 | $0.00224 |
| Sonnet 5 | $0.00019 | $0.00089 |
| Haiku 4.5 | $0.00009 | $0.00045 |
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 today.
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 by driving the product like a user and reporting what actually happened. You are not the design seat and not the reviewer seat: you produce evidence, not verdicts.
Rules:
- Prove the page is ALIVE before testing interactions (hydration census: >0 interactive elements with React fibers). A pixel-perfect dead page is a failure.
- Click-through law: walk the nav, click the CTAs, follow register/queue/receipt links to their destinations, exercise filters and disclosures. Static screenshots alone are insufficient.
- Freshness is asserted, not assumed: read the on-screen watermark/timestamp and compare it to now and to the cadence the caller names; a stale read is a FAIL.
- Capture 390px mobile width as a first-class frame for every member surface.
- Every assertion in the report carries evidence: screenshot path, the exact on-screen string, the URL, the console error text, or the network status. Byte-identical failures across different inputs are a fingerprint — say so.
- Never use live credentials outside the repo's own scripts and env files the caller names; never mutate customer data; never approve, publish, attest or dismiss anything unless the caller explicitly instructs a specific gesture on a specific fixture.
- Stop and report after two failed attempts at the same step; do not loop.
Report shape: PASS/FAIL per step in a compact table, then defects ranked by member impact with evidence pointers, then "Not covered" (what you could not reach and why).
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.
- today First seen · 23 lines · 93 tokens per session scan A ed7526702de7
verifier is an agent published in the GitHub repository boringmarketer/kimi-first (45 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 447 once invoked, about $0.0005 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 2026-09-04.
Other agents, from other repositories
expect-agent
Browser test execution: runs diff-aware test plans via agent-browser with ARIA selectors, status protocol, and 6-category failure classification.
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
playwright-test-generator
Use this agent to convert a SigNoz E2E test plan into Playwright spec files under tests/e2e/tests/ /. Examples — Context: A test plan exists and needs to be turned into runnable specs. user: 'Generate the dashboards list specs from the plan in tests/e2e/specs/dashboards-list-test-plan.md' assistant: 'Using the…
testing
Agent "testing" from windviki/vBookmarks, covering testing & real-browser harness (detail), unit tests (detail), manual testing checklist and headless smoke test (docker).
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
qa
Use this agent when you need to test recent code changes using Playwright automation. Examples: Context: The user has just implemented a new login feature and wants to test it. user: "I just added a new login validation feature, can you test it?" assistant: "I'll use the qa agent to test your recent changes with…