Borrowing it
Nothing to install: this file belongs to metabase/repro-bot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/metabase/repro-bot/main/.claude/skills/write-test/SKILL.mdgit clone --depth 1 https://github.com/metabase/repro-botWrote 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/metabase/repro-bot/write-test)<a href="https://agentmods.dev/skills/metabase/repro-bot/write-test"><img src="https://agentmods.dev/badge/skills/metabase/repro-bot/write-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/metabase/repro-bot/write-test"><img src="https://agentmods.dev/badge/skills/metabase/repro-bot/write-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 | $0.00062 | $0.01314 |
| Opus 5.5 | $0.00025 | $0.00526 |
| Sonnet 5.5 | $0.00012 | $0.00263 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
write-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 1mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Failing Test
This skill is invoked from the /repro workflow. The issue ID, repro dir, reproduction status, and root cause are in conversation context from prior phases.
Determine Test Type
| Bug Type | Test Type | Location |
|---|---|---|
| Backend logic, query processor, API | Clojure unit test | test/metabase/... |
| Frontend UI behavior, rendering | Jest unit/component test | frontend/test/... or co-located *.unit.spec.ts/*.unit.spec.tsx |
| End-to-end user workflow, UI interaction | Cypress acceptance test | e2e/test/scenarios/... |
| Mixed (backend + frontend) | Both — Clojure test for data + frontend/e2e test for UI |
Find Relevant Test File
Use the root cause to identify source file(s), then locate the corresponding test file:
Backend: src/metabase/foo/bar.clj → test/metabase/foo/bar_test.clj
Frontend: frontend/src/metabase/foo/Bar.tsx → frontend/src/metabase/foo/Bar.unit.spec.tsx or frontend/test/metabase/foo/Bar.unit.spec.tsx
E2E: UI workflow → e2e/test/scenarios/<category>/foo.cy.spec.ts
Use Grep to search for existing tests related to the buggy function/component. Consult CLAUDE.md in the source worktree for test conventions.
Choose Test Approach
Backend (Clojure):
| Root Cause Type | Test Approach |
|---|---|
| Query processor bug | mt/process-query or qp/process-query |
| API endpoint bug | mt/user-http-request |
| Model / data bug | mt/with-temp + t2/select |
| Pure logic / edge case | Direct function call with specific inputs |
Frontend (TypeScript):
| Root Cause Type | Test Approach |
|---|---|
| Component rendering bug | Jest + React Testing Library — render component, assert DOM |
| User interaction bug | Cypress — visit page, interact, assert visible result |
| Data display / formatting | Jest unit test on the formatting/transform function |
| State management bug | Jest — test reducer/action/selector with specific inputs |
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.
- 1mo ago First seen · 93 lines · 62 tokens per session scan A 89a650bb44fb
write-test is a skill published in the GitHub repository metabase/repro-bot (11 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,314 once invoked, about $0.0002 per session on Opus 5.5. 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.