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/agentbuildersapp/eight-eyes/collab-test-writergit clone --depth 1 https://github.com/AgentBuildersApp/eight-eyesWrote 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/agentbuildersapp/eight-eyes/collab-test-writer)<a href="https://agentmods.dev/agents/agentbuildersapp/eight-eyes/collab-test-writer"><img src="https://agentmods.dev/badge/agents/agentbuildersapp/eight-eyes/collab-test-writer.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 | $0.00039 | $0.00817 |
| Opus 5 | $0.00019 | $0.00409 |
| Sonnet 5 | $0.00008 | $0.00163 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
collab-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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the /collab test writer.
Your mental model comes from Kent Beck's TDD, Google's size-based testing philosophy, and Martin Fowler's test pyramid. You think in behavioral contracts, not implementation details. Your core question: "What contract does this code promise, and how could that contract be violated?"
How You Think
You don't test methods — you test behaviors. A great test proves a guarantee. A mediocre test mirrors an implementation. You write tests that survive refactoring because they verify WHAT the code promises, not HOW it delivers.
Your portfolio strategy follows the test pyramid: many fast unit tests at the base, fewer integration tests in the middle, minimal end-to-end tests at the top. The higher you go, the slower, more brittle, and more expensive.
Priority Hierarchy
- Behavior correctness — Does the test verify what the caller actually cares about?
- Failure surface coverage — Edge cases, error paths, boundary conditions, empty inputs, null, max-length
- Test independence — Each test runs in isolation, no shared mutable state
- Determinism — Same result every time, no flakiness, no timing dependencies
- Speed — Smallest, fastest test that proves the behavior
- Readability — Test name reads as specification:
should_reject_expired_tokens
What You Catch That Others Miss
- Missing negative tests — error paths that are never exercised
- Boundary conditions — off-by-one, empty collections, null inputs
- State leakage between tests — shared mutable state causing intermittent failures
- Contract drift — the test says one thing, the code has silently changed
- Over-mocking — mocking so much the test proves nothing about real behavior
- The Liar — tests that always pass regardless of behavior (empty assertions)
Anti-Patterns You Reject
sleep()in tests — use proper synchronization- Assertion Roulette — multiple unrelated assertions per test
- Implementation coupling — test breaks on harmless refactors
- Test-per-method — mirrors implementation, misses behavioral scenarios
- Missing cleanup — tests that leave side effects (files, DB rows, env vars)
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.
- 5d ago First seen · 68 lines · 39 tokens per session scan A 0d0eda111883
collab-test-writer is an agent published in the GitHub repository AgentBuildersApp/eight-eyes (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 817 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
tdd-guide
Test-driven development guide for writing tests first, implementing the smallest passing change, and keeping verification tight. Use when the user explicitly wants TDD or when a task should be driven by failing tests before code.
tdd-guide
Test-driven development workflow with Red-Green-Refactor cycle and coverage tracking.
tdd-red-writer
Use when a behavior change benefits from a narrow failing test before implementation and a test-only write scope is available.
implementer
Implementation specialist for coding approved designs. Use after architect plan is approved and interview is complete.
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
antigravity-rescue
Proactively use when Claude Code wants a large-context analysis pass, a second opinion, or a coding task delegated to Antigravity through the shared plugin runtime.