Borrowing it
Nothing to install: this file belongs to matanrak/agent-meet. 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/matanrak/agent-meet/main/.agents/skills/testing-agentmeet/SKILL.mdgit clone --depth 1 https://github.com/matanrak/agent-meetWrote 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/skills/matanrak/agent-meet/testing-agentmeet)<a href="https://agentmods.dev/skills/matanrak/agent-meet/testing-agentmeet"><img src="https://agentmods.dev/badge/skills/matanrak/agent-meet/testing-agentmeet/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/skills/matanrak/agent-meet/testing-agentmeet"><img src="https://agentmods.dev/badge/skills/matanrak/agent-meet/testing-agentmeet.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 | $0.00029 | $0.01021 |
| Opus 5.5 | $0.00012 | $0.00408 |
| Sonnet 5.5 | $0.00006 | $0.00204 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
testing-agentmeet 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 2mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentMeet E2E Testing
Use this skill when validating AgentMeet runtime behavior, especially PRs that touch frontend/src/app/api/v1, room creation, agent registration, message polling, or read receipts.
Devin Secrets Needed
- None required for the local fallback flow.
- Optional for protected deployed preview testing, if available:
VERCEL_ACCESS_TOKENor browser login/session that can bypass Vercel preview protection.- One database URL env var for the deployed project:
DATABASE_URL,POSTGRES_URL,POSTGRES_PRISMA_URL, orSUPABASE_DB_URL. NEXT_PUBLIC_SUPABASE_URLandNEXT_PUBLIC_SUPABASE_ANON_KEYfor browser Realtime testing.
Local fallback environment
If the Vercel preview is protected or project secrets are unavailable, test locally with Docker PostgreSQL:
docker run --name agentmeet-test-postgres \
-e POSTGRES_PASSWORD=agentmeet_test \
-e POSTGRES_DB=agentmeet_test \
-p 127.0.0.1:55432:5432 \
-d postgres:16-alpine
Wait until Postgres is ready:
docker exec agentmeet-test-postgres pg_isready -U postgres -d agentmeet_test
Run Next.js from the repo root:
DATABASE_URL='postgresql://postgres:[email protected]:55432/agentmeet_test' \
PGSSLMODE=disable \
FRONTEND_URL='http://localhost:3000' \
NEXT_PUBLIC_SUPABASE_URL='https://example.supabase.co' \
NEXT_PUBLIC_SUPABASE_ANON_KEY='dummy-anon-key-for-local-e2e' \
npm --prefix frontend run dev -- --hostname 0.0.0.0
The dummy Supabase values allow the UI bundle to load. This local fallback verifies persisted data and read receipt rendering after page load/refresh, but does not verify live Supabase Realtime delivery.
Browser checks to record
- Open
http://localhost:3000. - Click Start an agent call.
- Assert the room page opens with No agents here yet, Copy invite prompt, and Invite Agent, with no visible
API error 500. - Click Invite Agent and then the popover Copy action.
- Assert the invite UI describes API credentials/endpoints and does not show the old
/waitflow. - After API assertions create messages and read receipts, open the test room URL and assert the transcript shows the message plus
✓✓checkmarks.
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.
- 2mo ago First seen · 85 lines · 29 tokens per session scan A 6f96bc802f51
testing-agentmeet is a skill published in the GitHub repository matanrak/agent-meet (29 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 1,021 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
pod-e2e
ONLY for developing Kiro Crew itself -- if the project you are working on is anything else, ignore this skill: it drives Kiro Crew's own pod tooling, which does not exist in another repository. Boots a Kiro Crew feature worktree's full stack as an ISOLATED throwaway pod and proves it boots, authenticates and renders…
relay-80-100-workflow
Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, review-depth fresh-eyes review/fix loops with test hardening, PGlite…
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.
user-test
Test an app, API or CLI like a real user: launch it, try every feature or named ones, log bugs, perf and UX issues, auto-fix simple ones, report. Don't use for unit tests, E2E suite code, or design audits.
bmad-qa-generate-e2e-tests
Generate automated API and end-to-end tests for implemented features. Use when the user says "create qa automated tests for [feature]".
web-system-tests
The web realization of the system-tests contract — browser-driven system tests with Playwright against a running frontend. Owns the project layout (tests/), the Playwright configuration (baseURL plus webServer, cross-engine projects), the role- and label-based selector policy, code coverage as an opt-in second run…