curate-tests

curate-tests is a skill for Claude Code from theogbrand/yoink. It costs 34 tokens per session (693 once invoked), scanned A, original, MIT.

A testing workflow that finds relevant tests from an original library and generates focused new tests for a selected function or feature. It is intended for projects that have already prepared a reference copy and the real library.

In plain words
What is it for?
Use it when curating tests for a package and target feature, either through the full yoink workflow or as a standalone step after setup.
Why use it?
It provides tests based on the library's actual behavior while avoiding tests that need network access, API keys, or complex fixtures. The discovered tests are study material and are not executed.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the yoink plugin — 4 skills, 4 agents, 3 hooks shipped together

Good fit Use it when curating tests for a package and target feature, either through the full yoink workflow or as a standalone step after setup.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add theogbrand/yoink
Claude Code
/plugin install yoink

Made for: Claude Code.

Or install yoink, the plugin that ships this one along with the rest of its 4 skills, 4 agents, 3 hooks.

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 curate-tests

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/theogbrand/yoink/curate-tests"><img src="https://agentmods.dev/badge/skills/theogbrand/yoink/curate-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 693 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 $0.00034 $0.00693
Opus 5 $0.00017 $0.00347
Sonnet 5 $0.00007 $0.00139
Haiku 4.5 $0.00003 $0.00069

Measured 9d ago against content hash 39b9d69a8b3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

curate-tests 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/yoink/skills/curate-tests/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Curate Tests

Do not invoke this skill unless explicitly requested. It is called by /yoink:yoink or run standalone by the user.

Prerequisite: /yoink:setup must have been run first (reference dir and real library must exist).

Parse your prompt to identify:

  • Package name: from the Package: line or --package argument
  • Target function/feature: from the Task: line or prompt body

Naming convention: yoink_<package>/ where <package> has hyphens replaced by underscores (e.g., package litellm -> yoink_litellm/).


1. Discover relevant tests

  • If --skip-test-discoverer is present then skip to step 2.

Use the yoink:test-discoverer agent to search for relevant tests from the original library's test suite.

Pass input as JSON:

{
  "package_name": "<PACKAGE>",
  "target_function": "<TARGET_FUNCTION>"
}

Discovered tests are reference material only. They exist so the test-generator can study real-world patterns and assertions. They are never executed during validation or any later step -- only generated tests are run.

2. Generate focused tests

Use the yoink:test-generator agent to write original pytest tests for the target function.

Pass input as JSON:

{
  "package_name": "<PACKAGE>",
  "target_function": "<TARGET_FUNCTION>"
}

3. Validate generated tests against the real library

Run only the generated tests using the script below against the installed real library. Do NOT run discovered tests -- they are reference only and may depend on API keys, network access, or fixtures that are not available.

uv run ${CLAUDE_PLUGIN_ROOT}/scripts/run_tests.py --project-dir . 2>&1
  • If all tests pass then proceed to the next step.
  • If any tests fail or error then investigate and fix the generated tests. Do NOT proceed to the next step until all generated tests pass against the real library.

4. Rewrite imports

After validation passes, rewrite imports in generated tests so they target yoink_<package>/:

Read the full file on GitHub · 86 lines

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 · 86 lines · 34 tokens per session scan A 39b9d69a8b3b

Subscribe to this mod's changes

curate-tests is a skill published in the GitHub repository theogbrand/yoink (36 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 693 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.

Related

Other skills, from other repositories

test-native-extension

Validate a third-party control repo across four automated layers plus one printed manual recipe. Layer 1 asserts native-source structure (Android getName() and iOS +moduleName to manifest nativeModule; @ReactMethod / RCTEXPORTMETHOD to methods; no @ReactModule) plus load/init readiness (ReactPackage public no-arg…

microsoft/power-platform-skills · 211 tokens

test-site

Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.

microsoft/power-platform-skills · 46 tokens

phx-work

Execute Elixir/Phoenix plan tasks with progress tracking. Use after phx-plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.

oliver-kriska/claude-elixir-phoenix · 43 tokens

lab:autoresearch

Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs.

oliver-kriska/claude-elixir-phoenix · 52 tokens

codex-loop

Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.

oliver-kriska/claude-elixir-phoenix · 52 tokens

verify

Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.

oliver-kriska/claude-elixir-phoenix · 33 tokens