Borrowing it
Nothing to install: this file belongs to arjitj2/skillindex. 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/arjitj2/skillindex/main/.agents/skills/skillindex-testing/SKILL.mdgit clone --depth 1 https://github.com/arjitj2/skillindexWrote 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/arjitj2/skillindex/skillindex-testing)<a href="https://agentmods.dev/skills/arjitj2/skillindex/skillindex-testing"><img src="https://agentmods.dev/badge/skills/arjitj2/skillindex/skillindex-testing/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/arjitj2/skillindex/skillindex-testing"><img src="https://agentmods.dev/badge/skills/arjitj2/skillindex/skillindex-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Rogue Agent · line 97 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00041 | $0.01996 |
| Opus 5.5 | $0.00016 | $0.00798 |
| Sonnet 5.5 | $0.00008 | $0.00399 |
| Haiku 4.5 | $0.00004 | $0.00200 |
Grade A, and why
skillindex-testing 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 2mo 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Index Testing
Use this skill whenever you modify this repo. Pick the smallest test set that gives real confidence, then report exactly what you ran and what you did not run.
For any visual/UI change, the final response to the user must attach a screenshot proving the rendered result. Attach it as a Markdown image using an absolute local path, for example . Do not only describe the visual result or only list a screenshot path.
Testing Ladder
Run these from lowest cost to highest confidence:
pnpm typecheck- Focused Vitest for the files or layer you changed
- Computer Use against the Electron app with Sandbox enabled when available
- Playwright against the live app for UI changes, layout checks, or when Computer Use is unavailable
- Broader suite only when the change crosses boundaries or the focused checks are not enough
What To Run
Logic, contracts, and filesystem behavior
Use focused Vitest for src/main, src/preload, and src/shared.
Examples:
pnpm typecheck
pnpm test -- src/main/skill-inventory.test.ts
pnpm test -- src/shared/renderer-dev-config.test.ts
Renderer component behavior
Use focused Vitest for isolated component and view behavior in src/renderer/src/**.
Examples:
pnpm typecheck
pnpm test -- src/renderer/src/views/AgentsWorkspaceView.test.tsx
pnpm test -- src/renderer/src/components/ui.test.tsx
Use this for:
- conditional rendering
- filtering and search behavior
- section grouping
- button states
- text/content changes
Do not treat these tests as proof of layout correctness. JSDOM can verify structure, not actual rendered alignment.
Cross-view renderer behavior
Use broader renderer tests like src/renderer/src/app-shell.test.tsx when a change affects:
- tab switching
- shared app state
- navigation between panes
- interactions spanning multiple views
If there are known unrelated failures, do not hide that. Run the most relevant focused tests, then clearly report the unrelated failing suite.
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.
- 2mo ago First seen · 206 lines · 41 tokens per session scan A 05f7d5428fa3
skillindex-testing is a skill published in the GitHub repository arjitj2/skillindex (18 stars, last pushed 3d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,996 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 2026-08-30.
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.