fixtures

Guidance for creating and organizing fixture files, which are fixed inputs such as HTML, SVG, CSS, JSON, fonts, or images used by repeatable tests.

In plain words
What is it for?
Adding test inputs for supported features, file formats, edge cases, and visual or data-processing checks.
Why use it?
Fixtures make tests self-contained and reproducible, and help detect rendering or parsing regressions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gridaco/nothing/fixtures
Any agent
npx skills add gridaco/nothing --skill fixtures
Clone the repo
git clone --depth 1 https://github.com/gridaco/nothing

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,443 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.01443
Opus 5 $0.00020 $0.00722
Sonnet 5 $0.00008 $0.00289
Haiku 4.5 $0.00004 $0.00144

Measured 3d ago against content hash e78ce080b6b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fixtures 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 3d 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.

.agents/skills/fixtures/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fixtures

What fixtures are

Fixtures are static input files — HTML, SVG, CSS, JSON, .grida, font binaries, images, text samples — used as deterministic inputs to rendering, parsing, and I/O tests. They exist so that tests are reproducible, self-contained, and don't depend on external services or generated data.

Why we keep them

  • Regression detection — render the same input, compare the output.
  • Spec coverage — each fixture maps to a specific feature or property being tested (one concept per file).
  • Onboarding — new contributors can see exactly what the renderer handles by browsing fixtures.
  • Cross-pipeline validation — the same fixture can be consumed by unit tests, golden tests, reftests, probe tests, and visual inspection.

What should be covered

A fixture should exist for every rendering behavior, format variant, or edge case that the engine supports or intends to support. This includes:

  • Each CSS property / SVG element the htmlcss or SVG renderer handles
  • Format I/O round-trips (SVG → Grida, .grida decode)
  • Edge cases: zero-size, empty content, deeply nested, degenerate inputs
  • Unsupported-but-tracked features (the fixture documents the gap)

Best practices

  • One concept per file. Don't combine unrelated properties.
  • Self-contained. No external resources, network fetches, or scripts.
  • Minimal. Only enough structure to isolate the behavior under test.
  • Probe-friendly. High-contrast palette (prefer B/W), round pixel values, ≤ 3 colors. Designed for headless pixel probing, not human aesthetics.
  • Descriptive naming. <domain>-<property>[-<descriptor>].<ext> — the filename alone should tell you what's being tested.
  • Labeled specimens. Within a fixture, label each test case with the value being exercised so both humans and heuristics can identify regions. Keep labels short, and pin the dimensions of any container holding a label (flex item, grid cell, stretched block) so font-advance-width differences between engines can't leak into box geometry. When a test pipeline offers a text-neutralizing stylesheet (e.g. fixtures/test-html/_reftest/hide-text.css for the htmlcss reftests), prefer that over stripping the label — keeping the text helps the next reader understand the fixture.
  • Match the fixture's subject to the viewport policy. For refbrowser fixtures under fixtures/test-html/, paint / visual-property fixtures should size their root to a preset viewport (via min-height) so grida's cull and Chromium's screenshot have identical dimensions. Layout fixtures (box-model, flex, grid, intrinsic sizing) must NOT force a body size — the output dimensions are what the test measures; a min-height hack contaminates the result. See fixtures/test-html/README.md for the preset list, the paint-vs-layout rule, and the per-fixture viewport workflow for layout tests.
  • Don't duplicate. Before adding a fixture, check if an existing one already covers the behavior. Extend or split rather than duplicate.

Read the full file on GitHub · 126 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. 3d ago First seen · 126 lines · 40 tokens per session scan A e78ce080b6b7

Subscribe to this mod's changes

fixtures is a skill published in the GitHub repository gridaco/nothing (43 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,443 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

fixtures

Guides authoring, organizing, and referencing test fixtures in this repo. Use when creating new fixtures, writing tests that depend on fixtures, or deciding what should be checked into git. Engine fixtures (rendering corpora) live in the engine repo.

gridaco/grida · 53 tokens

spec-driven-tests

Rebuild a package's unit test suite around a behavior specification (SPEC.md) derived from the implementation, with every test citing a numbered rule ID. Use when asked to do a spec-driven test rebuild, write a SPEC.md for a package, repeat the state or store spec process (PRs.

tldraw/tldraw · 63 tokens

write-unit-tests

Writing unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages/tldraw. Covers Vitest patterns, TestEditor usage, and test file organization.

tldraw/tldraw · 53 tokens

docs-svg-kit

Author SVG figures for Grida docs — diff-able, version-controlled vector diagrams embedded in doc pages instead of screenshots. Provides reusable primitives (selection chrome, size badges, anchor pins, resize cursors, click ripples), color/typography tokens, a starter template, and finished examples to crib from.…

gridaco/grida · 145 tokens

editor-perf

Guides performance investigation, benchmarking, and optimization of the Grida Canvas web editor (TypeScript reducer, Immer, React hooks). Use when profiling reducer dispatch cost, diagnosing slow interactions (drag, resize, color change), writing or running editor benchmarks, instrumenting with PerfObserver, or…

gridaco/grida · 69 tokens

sdk-seam

Discipline for the seam between two SDKs (or two sides of one contract) that the same hand writes. The failure mode: "we own both sides" produces dirty contracts no foreign reviewer would accept. The exercise: pretend the other side is FFI, IPC, or a network protocol you cannot rewrite. Spawn an adversarial subagent…

gridaco/grida · 142 tokens