Borrowing it
Nothing to install: this file belongs to allenhutchison/obsidian-gemini. 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/allenhutchison/obsidian-gemini/master/.agents/skills/plugin-test/SKILL.mdgit clone --depth 1 https://github.com/allenhutchison/obsidian-geminiWrote 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/allenhutchison/obsidian-gemini/plugin-test)<a href="https://agentmods.dev/skills/allenhutchison/obsidian-gemini/plugin-test"><img src="https://agentmods.dev/badge/skills/allenhutchison/obsidian-gemini/plugin-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/allenhutchison/obsidian-gemini/plugin-test"><img src="https://agentmods.dev/badge/skills/allenhutchison/obsidian-gemini/plugin-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 156 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 348 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00174 | $0.07103 |
| Opus 5.5 | $0.00070 | $0.02841 |
| Sonnet 5.5 | $0.00035 | $0.01421 |
| Haiku 4.5 | $0.00017 | $0.00710 |
Grade A, and why
plugin-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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin acceptance test (three passes, agent as judge)
This skill is the deterministic counterpart to a human pre-release run-through. It tests the plugin in three escalating passes — cheapest first, most expensive last — and the agent decides between each pass whether it makes sense to continue. The test list comes from the user-facing docs (so anything documented stays honest), with extra weight on functionality merged since the last release tag (so the most likely regressions get the most attention).
The skill is conservative on cost and side effects. Pass 1 spends nothing. Pass 2 takes screenshots and clicks through UI but never makes a Gemini API call. Pass 3 is the only pass that spends real API tokens, and it only runs after the agent has reported pass-2 results to the user and the user has explicitly said to proceed.
When to use this skill
- The user is preparing a release and wants the plugin smoke-tested first
- The user asks "act as a judge on the plugin" / "test what's new" / "verify before I tag"
- A maintainer wants a regression sweep after a large refactor
- Don't use this skill for normal development debugging — for that, use the
obsidian-cliskill directly. This skill is heavyweight; reach for it when you need a top-to-bottom check.
Inputs
The user usually invokes this with no arguments. They may optionally specify:
- A vault name to target (defaults to
Test Vault— see vault guard below) - A focus area ("just test the scheduler", "skip pass 3") — if specified, narrow the relevant pass
Vault guard (mandatory preflight, before any other action)
This skill performs destructive actions: plugin reloads, opening modals, planting fake state, taking screenshots, and (in Pass 3) generating files via the API. Running it against the wrong vault — particularly the user's production vault — is unacceptable.
The Obsidian CLI has a critical footgun: vault=<name> is effectively decorative — empirically it does not route by name. The CLI always targets the focused Obsidian window regardless of what's passed. So you cannot redirect the skill to a non-focused vault by passing a flag; the user has to make the test vault the active window themselves. And because focus can drift (a click into another window) or the user may Cmd-Tab without realizing it, the safest posture is: only the test vault should be open at all for the duration of the run.
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 Changed · +26 lines 08aaba00297a
- 2mo ago First seen · 353 lines · 174 tokens per session scan A c486d726a3e5
plugin-test is a skill published in the GitHub repository allenhutchison/obsidian-gemini (533 stars, last pushed today), licensed MIT. It adds 174 tokens to every session and 7,103 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
axiom-testing
Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest. Covers unit tests, UI tests, async testing, test architecture.
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
test-automation-expert
Comprehensive test automation specialist covering unit, integration, and E2E testing strategies. Expert in Jest, Vitest, Playwright, Cypress, pytest, and modern testing frameworks. Guides test pyramid design, coverage optimization, flaky test detection, and CI/CD integration. Activate on 'test strategy', 'unit tests'…
JMeter Load Testing
Load and performance testing skill using Apache JMeter, covering test plans, thread groups, assertions, listeners, timers, and distributed testing.