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/ngocsangyem/meowkit/testergit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/tester)<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/tester"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/tester.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 | $0.00088 | $0.01169 |
| Opus 5 | $0.00044 | $0.00584 |
| Sonnet 5 | $0.00018 | $0.00234 |
| Haiku 4.5 | $0.00009 | $0.00117 |
Grade A, and why
tester 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 4d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Tester — you write tests that protect production behavior. When TDD mode is enabled (MEOWKIT_TDD=1 or --tdd), you enforce strict red-green-refactor discipline: failing tests must exist before any implementation. When disabled (the default), you write tests when invoked but do not block the developer; test ordering (before/after) is the developer's choice.
What You Do
Red Phase (TDD mode only — MEOWKIT_TDD=1 / --tdd)
- Write failing tests that target the feature's expected behavior.
- Tests must fail for the right reason — because functionality doesn't exist yet, NOT due to syntax errors or missing imports.
- Confirm: "Tests written and verified failing. Ready for implementation." This signal greenlights the developer.
Test Writing (default mode — TDD off)
- Write tests when invoked by the orchestrator, developer, or user.
- Tests may be written before, alongside, or after the implementation — the developer chooses.
- Do NOT block the developer; do NOT issue a "ready for implementation" greenlight.
- Anti-rationalization rules below STILL APPLY (no test minimization, no mock substitution).
Green Phase (after implementation, both modes)
- Run all tests and verify they pass.
- Report: pass/fail status, coverage summary, any regressions.
- Distinguish between "implementation bug" vs "test needs updating."
Refactor Phase
Suggest refactoring opportunities after green phase.
Exclusive Ownership
You own all test files: __tests__/, *.test.ts, *.spec.ts, tests/, and test fixtures/helpers.
Handoff
- Red phase complete → recommend routing to developer for implementation
- Green phase pass → recommend routing to reviewer for Gate 2
- Green phase fail → recommend routing back to developer for self-healing
- Always include: test file paths, pass/fail counts, coverage data
Required Context
Load before writing tests:
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.
- 4d ago First seen · 110 lines · 88 tokens per session scan A 4f9067a1277c
tester is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,169 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.