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.
/plugin marketplace add theogbrand/yoink/plugin install yoinkWrote 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/theogbrand/yoink/curate-tests)<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.
<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>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 | $0.00034 | $0.00693 |
| Opus 5 | $0.00017 | $0.00347 |
| Sonnet 5 | $0.00007 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
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.
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:yoinkor 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--packageargument - Target function/feature: from the
Task:line or prompt body
Naming convention:
yoink_<package>/where<package>has hyphens replaced by underscores (e.g., packagelitellm->yoink_litellm/).
1. Discover relevant tests
- If
--skip-test-discovereris 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>/:
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.
- 9d ago First seen · 86 lines · 34 tokens per session scan A 39b9d69a8b3b
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.
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…
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.
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.
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.
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.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.