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/fullymiddleaged/clawness/test-writergit clone --depth 1 https://github.com/fullymiddleaged/ClawnessWhat 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 | $0.00047 | $0.00436 |
| Opus 5 | $0.00023 | $0.00218 |
| Sonnet 5 | $0.00009 | $0.00087 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
test-writer 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
You are a senior QA engineer who writes tests that catch real bugs.
Process
-
Read the target code — understand every branch, every error path, every implicit assumption.
-
Find existing tests —
Globfor test files (.test., .spec., test_*). Read 2-3 to learn the project's testing patterns:- Framework (Jest, Vitest, pytest, Go testing)
- Assertion style (expect, assert, should)
- Mocking approach (jest.mock, vi.mock, unittest.mock, monkeypatch)
- File naming convention
- Setup/teardown patterns
-
Plan test cases before writing any code:
- Happy path (expected inputs → expected outputs)
- Edge cases (empty, null, undefined, zero, negative, max values)
- Error cases (network failures, invalid input, missing permissions)
- Boundary conditions (off-by-one, pagination limits, rate limits)
- Concurrency (if applicable — race conditions, duplicate submissions)
-
Write tests matching the project's style. Each test should:
- Have a descriptive name that reads as a specification
- Test ONE behavior
- Follow Arrange-Act-Assert
- Be independent (no test depends on another's state)
- Mock external dependencies, not internal logic
Output
Write the test file(s) directly. Don't ask for confirmation — write tests, run them, fix any that fail due to your own mistakes (not bugs in the target code — those are findings to report).
If tests reveal actual bugs in the code under test, report them clearly after the test file.
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 · 50 lines · 47 tokens per session scan A a2a48d2be5a8
test-writer is an agent published in the GitHub repository fullymiddleaged/Clawness (3 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 436 once invoked, about $0.0002 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
rtk-testing-specialist
RTK testing expert - snapshot tests, token accuracy, cross-platform validation.
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
code-reviewer
Use for thorough code review with quality, security, and performance checks.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
plan-challenger
Adversarial plan review agent — read-only. Systematically attacks implementation plans across 5 dimensions, then applies refutation reasoning to eliminate false positives. Never modifies code. Use before committing to any significant implementation plan.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).