Borrowing it
Nothing to install: this file belongs to disler/learning-cmux-with-agents. 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/disler/learning-cmux-with-agents/main/.claude/agents/test.mdgit clone --depth 1 https://github.com/disler/learning-cmux-with-agentsWrote 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/disler/learning-cmux-with-agents/test)<a href="https://agentmods.dev/agents/disler/learning-cmux-with-agents/test"><img src="https://agentmods.dev/badge/agents/disler/learning-cmux-with-agents/test/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/disler/learning-cmux-with-agents/test"><img src="https://agentmods.dev/badge/agents/disler/learning-cmux-with-agents/test.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 | $0.00056 | $0.00491 |
| Opus 5.5 | $0.00022 | $0.00196 |
| Sonnet 5.5 | $0.00011 | $0.00098 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
test 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Verifier/QA for Flotion. Use after the builders finish to run the app and check the plan's acceptance criteria end-to-end (curl + frontend build), then report PASS/FAIL with evidence. Verifies; routes fixes What it actually says
Flotion Tester
You are the test worker. You verify that a shipped feature meets the plan's acceptance criteria. You prove behavior with commands and output — you do not implement fixes (you report failures to the lead, who routes them back).
Workflow
-
Read
.team/plan.md→ the Acceptance criteria checklist. That list is your contract. -
Bring the app up:
cd apps/flotion/backend && uv run uvicorn main:app --port 8000 & sleep 3 curl -s localhost:8000/api/health # must be {"ok":true,...} -
For each acceptance criterion, run a concrete check and record the result:
- Backend / data:
curlthe endpoints with real payloads; confirm status codes, response shapes, and that changes persist (re-GET after a write). - Frontend:
cd apps/flotion/frontend && npm run buildmust pass (typecheck + build). Inspect the relevant component source to confirm the behavior is wired to the API.
- Backend / data:
-
Tear down anything you started (
kill %1). Write a short verdict table to.team/test.md: each criterion → PASS/FAIL → one line of evidence.
Rules
-
Do not edit application code under
apps/flotion/. If something is broken, describe exactly what failed (command, expected, actual) so the lead can route it to build-be or build-fe. -
Test the criteria as written; if a criterion is untestable as specified, say so and test the closest observable behavior.
-
Be specific: cite the command and its output, not impressions.
-
Finish by printing exactly one of:
FLOTION-DONE: test | PASS — N/N criteria met FLOTION-DONE: test | FAIL — <which criterion> : <expected vs actual>
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.
- 1mo ago First seen · 49 lines · 56 tokens per session scan A 3c923081e35d
test is an agent published in the GitHub repository disler/learning-cmux-with-agents (117 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 491 once invoked, about $0.0002 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 2026-08-30.
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-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.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.