trove-tdd

trove-tdd is a skill for Claude Code from bravew/trove. It costs 62 tokens per session (424 once invoked), scanned A, original, MIT.

A test-first workflow called test-driven development, or TDD, in which a test describing the desired behavior is written before the code change.

In plain words
What is it for?
Use it to write a small regression test for a bug, confirm it fails for the right reason, make the fix, and check nearby tests.
Why use it?
It checks that a bug is really reproduced before fixing it and prevents the same problem from returning later.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents).

Part of the trove-dev plugin — 15 skills, 1 agent shipped together

Good fit Use it to write a small regression test for a bug, confirm it fails for the right reason, make the fix, and check nearby tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bravew/trove/trove-tdd
View source ↗ bravew/trove
Install

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.

Any agent
npx skills add bravew/trove --skill trove-tdd
Clone the repo
git clone --depth 1 https://github.com/bravew/trove

Made for: Claude Code.

Or install trove-dev, the plugin that ships this one along with the rest of its 15 skills, 1 agent.

Wrote 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.

agentmods badge for trove-tdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/bravew/trove/trove-tdd/github.svg)](https://agentmods.dev/skills/bravew/trove/trove-tdd)
Your own site
<a href="https://agentmods.dev/skills/bravew/trove/trove-tdd"><img src="https://agentmods.dev/badge/skills/bravew/trove/trove-tdd/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.

agentmods 80×15 button for trove-tdd

Your own site · 80×15
<a href="https://agentmods.dev/skills/bravew/trove/trove-tdd"><img src="https://agentmods.dev/badge/skills/bravew/trove/trove-tdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 424 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.00424
Opus 5 $0.00031 $0.00212
Sonnet 5 $0.00012 $0.00085
Haiku 4.5 $0.00006 $0.00042

Measured 9d ago against content hash 582aee056938, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

trove-tdd 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 9d 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.

plugins/trove-dev/.agents/skills/trove-tdd/SKILL.md · 41 lines

What it actually says

Trove · v2026.7.4

Session Init

This skill ships Trove conventions. Prefer existing project patterns over generic best practices when they conflict.

trove-tdd

Write the test that fails for the right reason before you change the code. The test encodes intended behavior, not the current implementation.

Workflow

  1. Understand the intended behavior — what should be true that currently isn't.
  2. Choose the narrowest check that exercises it (unit over integration over E2E).
  3. Write a test that fails before the fix, for the reason you expect.
  4. Run it and confirm it fails on that reason — not a typo or a missing import.
  5. Make the smallest fix.
  6. Re-run; confirm it passes.
  7. Run nearby tests to catch fallout.

When to skip (escape hatch)

Prefer no new test over a bad test. Skip — and say why — when:

  • The only path is a slow E2E flow or a broad harness with heavy setup.
  • Reproducing it needs brittle mocks that would assert implementation detail, not behavior.
  • The test target is genuinely unclear.

A bad test is one that passes when the bug is present, asserts on incidental implementation, or is so slow/flaky it gets disabled. Don't write it to look thorough.

Output

Report the evidence, not just the outcome: name the run that failed before the fix and the run that passed after (e.g. pnpm test reducer.test.ts red → green). If you skipped the test, state the reason in one line.

Changes

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.

  1. 9d ago First seen · 41 lines · 62 tokens per session scan A 582aee056938

Subscribe to this mod's changes

trove-tdd is a skill published in the GitHub repository bravew/trove (10 stars, last pushed 10d ago), licensed MIT. It adds 62 tokens to every session and 424 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.