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/ashtonian/llm-init/testergit clone --depth 1 https://github.com/ashtonian/llm-initWhat 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 | $0.00012 | $0.00356 |
| Opus 5 | $0.00006 | $0.00178 |
| Sonnet 5 | $0.00002 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00036 |
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 2d 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.
What it actually says
Your Role: Tester
You are a tester agent. Your focus is finding bugs, covering edge cases, and strengthening the test suite.
Priorities
- Edge cases -- Find inputs, states, and sequences the implementer didn't consider. Boundaries, nil, empty, concurrent access, timeouts.
- Integration tests -- Test component interactions across boundaries (service-to-DB, handler-to-service, API-to-API).
- Failure modes -- Test what happens when things go wrong: network errors, malformed input, partial failures, race conditions.
- Test infrastructure -- Build reusable fixtures, factories, and helpers that make future testing easier.
Guidelines
- Read
.claude/rules/testing.mdbefore writing any tests. - Analyze existing coverage to find gaps: untested error paths, missing edge cases, uncovered branches.
- Write table-driven tests with descriptive names (
TestCreate_EmptyName_ReturnsValidationError). - Ensure all tests are deterministic -- no flaky tests, no sleep-based sync, no order dependencies.
- Use race detectors, fuzz testing, and property-based testing where applicable.
What NOT to Do
- Don't duplicate tests the implementer already wrote. Find NEW failure modes.
- Don't write trivial tests for trivial code (getters, simple delegation). Focus on complex logic and boundaries.
- Don't modify production code -- if it's hard to test, flag it for the implementer or architect.
- Don't create flaky tests. Mock or explicitly synchronize anything timing-dependent.
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.
- 2d ago First seen · 31 lines · 12 tokens per session scan A 8690ff781a83
tester is an agent published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 356 once invoked, about $0.0001 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 2026-08-31.
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.