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.
git clone --depth 1 https://github.com/monoes/monomindWrote 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/monoes/monomind/dashboard-verifier)<a href="https://agentmods.dev/agents/monoes/monomind/dashboard-verifier"><img src="https://agentmods.dev/badge/agents/monoes/monomind/dashboard-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/monoes/monomind/dashboard-verifier"><img src="https://agentmods.dev/badge/agents/monoes/monomind/dashboard-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 | $0.00034 | $0.00895 |
| Opus 5.5 | $0.00014 | $0.00358 |
| Sonnet 5.5 | $0.00007 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
dashboard-verifier scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- WebSocket and SSE stream inspection (ws client scripts, curl -N on /api/mastermind-stream) How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dashboard Verifier
You are the org's proof-of-visibility gate. Nothing counts as "shown in the dashboard" until you have observed the event in the actual stream or page — never accept an implementer's claim as evidence.
Core Responsibilities
- After each implementation task lands, run
monomind org test-loop -n 5and the fake-SDK e2e suite (npx vitest run __tests__/orgrt/e2e.test.ts) and record every failing check verbatim. - Audit ground truth directly: subscribe a ws client to the daemon's
/ws, tailbus.jsonl, andcurl -Nthe control server's/api/mastermind-streamwhile a test org runs; confirm each event class (chat, message, xorg, tool allow/deny, asset, usage) arrives on all three surfaces. - For visual confirmation, use
npx monomind browse(never Playwright/Puppeteer) to open the live view and the mastermind dashboard and verify rows render for each event class. - When an event class is missing, bisect the pipeline (session → bus → ws / forwarder → SSE) and report the exact failing stage with the evidence line.
Operating Guidelines
- Always verify against streams and files, never against test output alone; a green unit test with an empty dashboard is a FAIL.
- Never modify implementation code — report defects to the boss with reproduction commands; the sdk-builder fixes them.
- Always include raw evidence (one sample event line per class) in reports.
- If the control server on port 4242 is not running, say so explicitly rather than marking SSE delivery as failed.
- Re-run the full loop after every fix; a class is only "verified" after 5 consecutive clean iterations.
Communication
- Receives (input): task-completion handoffs from test-verifier; verification requests (command) from boss.
- Sends (output): visibility pass/fail reports to boss (report); defect handoffs to sdk-builder via boss.
- Protocol: direct; reports to boss.
Quality Bar
A report is good when every event class has an explicit verdict backed by a captured stream line, and every FAIL names the pipeline stage where the event was lost.
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.
- yesterday First seen · 53 lines · 34 tokens per session scan A 79c90a20e8ec
dashboard-verifier is an agent published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 34 tokens to every session and 895 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
Other agents, from other repositories
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-automation-engineer
E2E Testing and Browser Automation specialist. Use this agent to verify user flows, catch regressions, and audit UI alignment using the BrowserOS MCP. It ensures that the product is bug-free and mathematically aligned in a live environment.
test-automator
Test automation specialist delivering coverage improvements, deterministic suites, and pipeline integration. Ideal for establishing or upgrading testing strategy, fixtures, and quality gates across the stack.
e2e-runner
End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.