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 skills add arcasilesgroup/ai-engineering --skill ai-test-plannergit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote 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/arcasilesgroup/ai-engineering/ai-test-planner)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-test-planner"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-test-planner/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/arcasilesgroup/ai-engineering/ai-test-planner"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-test-planner.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00095 | $0.01605 |
| Opus 5.5 | $0.00038 | $0.00642 |
| Sonnet 5.5 | $0.00019 | $0.00321 |
| Haiku 4.5 | $0.00010 | $0.00161 |
Grade A, and why
ai-test-planner scanned grade A with 1 finding 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 19d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 3 | CLI / static | The app type-checks, lints and builds; smoke `curl`s against the running API | Project config → *Lint*, *Build*, *Health check* (commands only, no files) | How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test planner
If you're running as a subagent (for example, launched by /ai-orchestrator), you can't launch subagents. Do the steps marked "subagent" yourself, and do only the steps and checkpoint cases you were asked for.
Project specifics (test file locations, commands, frameworks, how to act as a role, e2e sign-in) come from the Project config section of AGENTS.md. Read it first. If a value you need is missing there, infer it from the existing tests and config files, and say so in your report.
Rule: push every check to the lowest layer that can prove it. A browser test is only for things that exist only in the browser. Layers run in order, and a layer runs only once the one below it passes:
| # | Layer | Proves | Where / Run |
|---|---|---|---|
| 1 | Unit | Pure logic: calculations, date math, state rules | Project config → Unit tests |
| 2 | API | Endpoints, role/permission checks, status codes, DB constraints surfacing as 409/422, state transitions | Project config → API tests |
| 3 | CLI / static | The app type-checks, lints and builds; smoke curls against the running API |
Project config → Lint, Build, Health check (commands only, no files) |
| 4 | UI (runs last) | Rendering, navigation, form wiring, role-based visibility, and the 375px layout | Project config → E2E tests |
Before putting a case in layer 4, ask: could layer 1 or 2 fail for the same bug? If yes, move the case down. For example, "a staff user can't refund an order" is a layer 2 case, never a UI one.
1. Map the feature with a subagent
Send an Explore subagent to return a compact map of the feature:
- the pure functions involved;
- the endpoints, with their auth dependencies and permission checks;
- the tables, with their constraints (unique, check, FK, partial indexes);
- the pages, forms and client code that call the endpoints;
- the existing tests and fixtures.
If .ai-engineering/workflow/checkpoints/<slug>.json exists, have it include that file too, so the tests line up with the checkpoints.
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.
- 19d ago First seen · 96 lines · 95 tokens per session scan A a4866d4902f4
ai-test-planner is a skill published in the GitHub repository arcasilesgroup/ai-engineering (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 95 tokens to every session and 1,605 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-27.
Other skills, from other repositories
dotnet-testing-advanced-tunit-advanced
A guide for advanced TUnit testing in .NET. TUnit is a testing framework; the guide covers tests driven by data, dependency injection, integration tests, retries, time limits, and filtering.
testing-strategies
Systematic testing for confidence without over-testing — the right test at the right level.
converter-qa
Test harness for validating converter outputs with 284 assertions across all converter muscles.
inventree-devcontainer-testing
Run the InvenTree Plugin AI Toolkit devcontainer and execute a plugin's test-all.sh. Covers Docker setup, postCreateCommand, server startup, and the lint/unit/integration/frontend-build/E2E layers.
test-generation
Generate a test strategy and starter test stubs for given modules across unit, integration, and e2e layers (pytest/jest/playwright). Trigger on: generate tests, test plan, test strategy, coverage plan, test scaffolding.
testing-patterns
Testing patterns and principles. Unit, integration, mocking strategies.