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 skills/aisa-group/skill-inject/write-unit-testsnpx skills add aisa-group/skill-inject --skill write-unit-testsgit clone --depth 1 https://github.com/aisa-group/skill-injectWrote 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/aisa-group/skill-inject/write-unit-tests)<a href="https://agentmods.dev/skills/aisa-group/skill-inject/write-unit-tests"><img src="https://agentmods.dev/badge/skills/aisa-group/skill-inject/write-unit-tests.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.02444 |
| Opus 5 | $0.00026 | $0.01222 |
| Sonnet 5 | $0.00011 | $0.00489 |
| Haiku 4.5 | $0.00005 | $0.00244 |
Grade A, and why
write-unit-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 4d 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 — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing tests
Unit and integration tests use Vitest. Tests run from workspace directories, not the repo root.
Test file locations
Unit tests - alongside source files:
packages/editor/src/lib/primitives/Vec.ts
packages/editor/src/lib/primitives/Vec.test.ts # Same directory
Integration tests - in src/test/ directory:
packages/tldraw/src/test/SelectTool.test.ts
packages/tldraw/src/test/commands/createShape.test.ts
Shape/tool tests - alongside the implementation:
packages/tldraw/src/lib/shapes/arrow/ArrowShapeUtil.test.ts
packages/tldraw/src/lib/shapes/arrow/ArrowShapeTool.test.ts
Which workspace to test in
- packages/editor: Core primitives, geometry, managers, base editor functionality
- packages/tldraw: Anything needing default shapes/tools (most integration tests)
cd packages/tldraw && yarn test run
cd packages/tldraw && yarn test run --grep "SelectTool"
TestEditor vs Editor
Use TestEditor for integration tests (includes default shapes/tools):
import { createShapeId } from '@tldraw/editor'
import { TestEditor } from './TestEditor'
let editor: TestEditor
beforeEach(() => {
editor = new TestEditor()
editor.selectAll().deleteShapes(editor.getSelectedShapeIds())
})
afterEach(() => {
editor?.dispose()
})
Use raw Editor when testing editor setup or custom configurations:
import { Editor, createTLStore } from '@tldraw/editor'
beforeEach(() => {
editor = new Editor({
shapeUtils: [CustomShape],
bindingUtils: [],
tools: [CustomTool],
store: createTLStore({ shapeUtils: [CustomShape], bindingUtils: [] }),
getContainer: () => document.body,
})
})
Common TestEditor methods
// Pointer simulation
editor.pointerDown(x, y, options?)
editor.pointerMove(x, y, options?)
editor.pointerUp(x, y, options?)
editor.click(x, y, shapeId?)
editor.doubleClick(x, y, shapeId?)
// Keyboard simulation
editor.keyDown(key, options?)
editor.keyUp(key, options?)
// State assertions
editor.expectToBeIn('select.idle')
editor.expectToBeIn('select.crop.idle')
// Shape assertions
editor.expectShapeToMatch({ id, x, y, props: { ... } })
// Shape operations
editor.createShapes([{ id, type, x, y, props }])
editor.updateShapes([{ id, type, props }])
editor.getShape(id)
editor.select(id1, id2)
editor.selectAll()
editor.selectNone()
editor.getSelectedShapeIds()
editor.getOnlySelectedShape()
// Tool operations
editor.setCurrentTool('arrow')
editor.getCurrentToolId()
// Undo/redo
editor.undo()
editor.redo()
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.
- 4d ago First seen · 400 lines · 53 tokens per session scan A a7235d28eafe
write-unit-tests is a skill published in the GitHub repository aisa-group/skill-inject (94 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 2,444 once invoked, about $0.0003 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
add-a-rule
Add security coverage to Guardana the way this repository requires — as a rule, evaluator or target, never by patching the engine — with the fixtures, the framework mapping and the documentation that make it shippable. Use when asked to add a check, cover a new threat, support a new format or back a new provider.
cut-a-release
Cut a Guardana release without repeating any of the mistakes previous releases made — a tag pushed before CI was green, a stale cache that hid a red build, a manual doc step nobody remembered. Use when asked to release, tag, publish or bump a version.
harness
End-to-end workflow orchestrator. Walks the 11-phase pipeline, invoking each phase skill in order inside an internal loop, yielding at consent gates (/approve-direction, /approve-swarm, /grant-commit), and exiting cleanly on yield/failure/done. Decides swarm-vs-solo at Phase 6. Auto-loops /tdd on integrate failures…
code-structure
MANDATORY skill for ALL code generation. Enforces top-down composition, consistent abstraction layers, and proper module hierarchy. Apply every time you write or modify code — in any language — no exceptions.
memory-sync
Review the auto-extracted candidates in .claude/memory/pending.md and commit keepers to the canonical memory files (landmarks.md, libraries.md, decisions.md, landmines.md, conventions.md, pending-questions.md, backlog.md). Invoke at session start when the SessionStart hook reports pending candidates, or any time…
chore
Workflow track for tasks that need no TDD — documentation edits, governance count bumps, vendored-skill content updates, configuration tweaks, formatting, typo fixes, dependency bumps where no project code changes. Skips /scenario and /implement (no failing test to drive) and runs the work directly. archive…