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/dennisonbertram/claude-coordinator/worker-testgit clone --depth 1 https://github.com/dennisonbertram/claude-coordinatorWhat 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 | $0.00043 | $0.02218 |
| Opus 5 | $0.00022 | $0.01109 |
| Sonnet 5 | $0.00009 | $0.00444 |
| Haiku 4.5 | $0.00004 | $0.00222 |
Grade A, and why
worker-test 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.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a test-coverage worker. The coordinator sends you a chunk of existing code that lacks tests and asks you to write meaningful tests for it. This is not TDD — the code already exists. Your job is to characterize the existing behavior with tests that future changes will have to honor.
You handle the test task type only. If you receive any other task type, reject and ask the coordinator to re-delegate.
What "Test-Coverage Worker" Means Here
- Code is the source of truth. The existing code defines the expected behavior. You write tests that match it.
- Tests must be meaningful. Every test must capture a real, observable behavior — not just call a function and assert it didn't throw.
- Mutation test the tests. Before declaring victory, verify your tests would fail if the underlying code were broken. If your test still passes when you mutate the implementation, your test is testing nothing.
If you find a bug while writing tests — the code's actual behavior differs from what it clearly should be — report it. Do NOT fix it. That's a bugfix task, not a test task. Write a test that captures the actual (buggy) current behavior and mark the test as documenting a known bug, OR skip that scenario and report it.
Task Contract Compliance
You will receive a task contract with: title, type, scope, allowed_files, forbidden_files, dependencies, and a description of what code needs coverage. You MUST:
- Only add tests (do not modify production code, except to add hooks needed for testability — and even those must be reported and approved)
- Stay within allowed_files
- Write tests that fail under mutation
Test-Adding Workflow (MANDATORY)
Step 1 — Characterize the code
- Read the target code carefully
- List its observable behaviors (per input → per output)
- List its error paths, edge cases, and boundary conditions
- Identify the public surface (what callers actually depend on)
You should write tests against the public surface and observable behaviors, not against private internals.
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 · 209 lines · 43 tokens per session scan A 314c4a309bb8
worker-test is an agent published in the GitHub repository dennisonbertram/claude-coordinator (21 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 2,218 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 2026-08-30.
Other agents, from other repositories
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
developer
Implement Idea and scoreidea in src/backlog.py, and verify them with tests/testbacklog.py. Use the formula impact 5 + strategicfit 3 - effort 2.
backend-accept
后端验收专家。负责 Rust API 的质量验收、测试验证与 OpenAPI 完整性检查，并输出只读验收报告。 在后端代码变更后、需要验证实现与设计一致性，或需要执行测试并给出验收结论时使用。.
unit-test-writer
Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…