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 skills add zacharygcook/agent-skills --skill good-test-bad-testgit clone --depth 1 https://github.com/zacharygcook/agent-skillsWrote 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/skills/zacharygcook/agent-skills/good-test-bad-test)<a href="https://agentmods.dev/skills/zacharygcook/agent-skills/good-test-bad-test"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/good-test-bad-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zacharygcook/agent-skills/good-test-bad-test"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/good-test-bad-test.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00052 | $0.00467 |
| Opus 5 | $0.00026 | $0.00234 |
| Sonnet 5 | $0.00010 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
good-test-bad-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 11d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Good Test, Bad Test
Optimize for production confidence and maintainability, not raw coverage.
Required Classification
Before adding a test:
- Name the behavior or branch.
- Name the real production workflow that reaches it.
- Classify the test as
good,bad, ortemporary proof/TDD. - Choose whether to test, simplify production code, delete dead code, or temporarily prove a hypothesis.
Good Tests
Good tests protect behavior users or operators depend on:
- public contracts, domain rules, and critical state transitions;
- realistic external data and failure modes;
- regressions for bugs likely to recur;
- auth, data integrity, idempotency, retry, and concurrency invariants;
- integration seams where a unit mock would conceal risk.
They should survive reasonable refactors because they assert outcomes rather than private choreography.
Bad Tests
Do not add tests whose main effect is to:
- pin private helper calls, internal ordering, or incidental object shape;
- exercise unreachable defensive branches;
- preserve stale exports, obsolete commands, placeholder providers, or speculative abstractions;
- mock so much that the behavior under test cannot fail realistically;
- restate framework or library behavior;
- inflate line or branch coverage without protecting an invariant.
If production cannot reach a branch, prefer deleting or simplifying it. If it is an intentional placeholder, keep it small and document why coverage is deferred.
Temporary Proof/TDD Tests
Temporary tests may recreate a bug, test a narrow hypothesis, or drive an unsettled implementation. Before handoff, either convert them into durable behavior tests or delete them. Keep one only when the user explicitly approves the maintenance cost and the reason is documented.
Coverage Triage
For each uncovered branch, ask in order:
- Can a real workflow reach it?
- Does it protect meaningful behavior?
- Can it be tested through a public boundary?
- Would deleting or simplifying the code be safer?
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 58 lines · 52 tokens per session scan A c7be7c4de962
good-test-bad-test is a skill published in the GitHub repository zacharygcook/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 467 once invoked, about $0.0003 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 skills, from other repositories
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
rudder
Use locally captured coding-session intent to resolve a device-local behavioral spec, generate focused tests from that spec, implement the smallest production changes through red-green TDD, and verify coverage with the repository's native tooling. Use when the user asks to run Rudder, create or regenerate tests for…
TDD 开发纪律助手
A development skill based on TDD, or test-driven development: write or update a test first, make it pass with the smallest code change, then improve the code and check for regressions.
ship
Enforces Law 1 (Research Before Executing), Law 3 (One Thing at a Time), and Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline. Fix one defect through TDD and one PR, isolate unrelated dirty checkouts in an owner-locked clean worktree, and return only eligible clean checkouts to the detected default…
debugging
Investigate failures whose root cause is still unknown — narrow the search space, instrument, and test falsifiable hypotheses. Use for intermittent or environment-dependent behavior, unexplained stack traces, regressions with no known trigger, or any symptom without a confirmed cause. Ends once the root cause is…
mutation-testing
Finds weak or missing tests by analyzing if code changes would be caught. Use when verifying test effectiveness, strengthening test suites, or validating TDD workflows.