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.
npx agentmods add instructions/williamisnotdefined/rubiks-cube-solver/frontend-testinggit clone --depth 1 https://github.com/williamisnotdefined/rubiks-cube-solverWhat 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 | $0.03436 | $0.03436 |
| Opus 5 | $0.01718 | $0.01718 |
| Sonnet 5 | $0.00687 | $0.00687 |
| Haiku 4.5 | $0.00344 | $0.00344 |
Grade A, and why
rubiks-cube-solver frontend-testing.instructions.md 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 2d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated from ai/registry.json. Do not edit manually.
Canonical skill: ../../ai/skills/frontend-testing.md.
Referenced context:
../../ai/rules/frontend-rules.md../../ai/rules/testing-rules.md../../ai/rules/frontend-quality-rules.md../../ai/architecture/web-architecture.md
This file is compiled from canonical AI knowledge files. Edit canonical files under ai, then run npm run ai:sync.
Compiled AI Skill: frontend-testing
Canonical Skill: ai/skills/frontend-testing.md
Frontend Testing
Use for Vitest, Testing Library, API-domain tests, coverage, Storybook, and Playwright E2E.
Read First
ai/rules/frontend-rules.mdai/rules/testing-rules.mdai/rules/frontend-quality-rules.mdai/architecture/web-architecture.md
Workflow
- Test observable behavior at the narrowest public boundary and place it in the nearest established
__tests__folder. - Use accessible queries and shared API/E2E helpers; cover cancellation and recoverable failures where relevant.
- Keep global statements, branches, functions, and lines thresholds at 90%.
- Run the targeted test first, then coverage, Storybook, or the relevant E2E split for the changed surface.
Referenced Context
Reference: ai/rules/frontend-rules.md
Frontend Rules
Boundaries
- Keep solving, notation semantics, puzzle validity, and replay verification in Rust. React renders and coordinates typed product workflows.
- Keep HTTP mechanics and normalization in
apps/web/src/api; UI consumes domain hooks/adapters. - Typed scan-session contracts MAY contain reviewed stickers, confidence, and manual overrides. Notation solve UI MUST NOT expose facelet, Kociemba, or raw cube-state inputs.
- Keep API load, form, page workflow, solve result, scanner review, and visualization playback state separately owned unless a focused page owner coordinates them.
- Use the active
@rubiks-cube-solver/rubiks-cubepackage as a visualization adapter, never as canonical solver state.
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.
- 2d ago First seen · 220 lines · 3,436 tokens per session scan A d585b5aaa761
rubiks-cube-solver frontend-testing.instructions.md is an instructions file published in the GitHub repository williamisnotdefined/rubiks-cube-solver (4 stars, last pushed 9d ago), licensed MIT. It adds 3,436 tokens to every session, about $0.0172 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.
Other instructions, from other repositories
omnigent copilot-instructions.md
Copilot instructions for omnigent-ai/omnigent, covering copilot code review instructions, e2e test requirement, backend test coverage and frontend test coverage.
Math-To-Manim tests.instructions.md
Guidelines for writing and maintaining tests in Math-To-Manim.
instrMCP CLAUDE.md
Instructions for caidish/instrMCP, covering claude.md, development commands, always use conda environment instrmcpdev for testing, unit tests (fast, no hardware required - all mocked) and e2e tests (requires playwright and browser automation).
vite-ts-react-template tests.instructions.md
Instructions for bartstc/vite-ts-react-template, covering testing, tools, ai boundaries and test priorities.
copilot-instructions unit-and-integration-tests.instructions.md
Unit and integration testing best practices with pytest.
Chromanche CLAUDE.md
Claude Code instructions for marcobazzani/Chromanche, covering chromanche — engineering guardrails, testing is non-negotiable, unit tests (vitest), integration tests and red tests block merge.