Borrowing it
Nothing to install: this file belongs to ASDAlexey/vitest-auto-spy. 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/ASDAlexey/vitest-auto-spy/master/AGENTS.mdgit clone --depth 1 https://github.com/ASDAlexey/vitest-auto-spyWrote 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/instructions/asdalexey/vitest-auto-spy/agents-md)<a href="https://agentmods.dev/instructions/asdalexey/vitest-auto-spy/agents-md"><img src="https://agentmods.dev/badge/instructions/asdalexey/vitest-auto-spy/agents-md/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/instructions/asdalexey/vitest-auto-spy/agents-md"><img src="https://agentmods.dev/badge/instructions/asdalexey/vitest-auto-spy/agents-md.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 | $0.07847 | $0.07847 |
| Opus 5.5 | $0.03139 | $0.03139 |
| Sonnet 5.5 | $0.01569 | $0.01569 |
| Haiku 4.5 | $0.00785 | $0.00785 |
Grade A, and why
vitest-auto-spy AGENTS.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 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 — 603 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vitest-auto-spy — instructions for AI coding agents
Reference for an agent writing tests with vitest-auto-spy in someone else's project: typed
test spies generated from a class, a type, or nothing at all, on Vitest, bun:test, node:test and
Rstest. It ships in the npm package, so it works offline: node_modules/vitest-auto-spy/AGENTS.md.
Working on the library's own source? Read CONTRIBUTING.md in the repository instead.
The spec you will write most often, an Angular service with a spied store and HTTP (the full recipe is §3):
import { TestBed } from '@angular/core/testing';
import { type Spy, injectSpy, provideAutoSpy } from 'vitest-auto-spy/angular';
import { expectRequest, provideHttpTesting } from 'vitest-auto-spy/angular-http';
let store: Spy<CartStore>;
beforeEach(() => {
TestBed.configureTestingModule({ providers: [...provideHttpTesting(), provideAutoSpy(CartStore)] });
store = injectSpy(CartStore);
});
it('posts the order', async () => {
const order = TestBed.inject(OrderService).checkout(); // Promise<Order>, sent through HttpClient
await expectRequest('/api/orders', { method: 'POST' }).flush({ id: 1 });
await expect(order).resolves.toEqual({ id: 1 });
expect(store.clear).toHaveBeenCalled();
});
To point a team's agents at this file, run npx vitest-auto-spy init: it adds a pointer to
AGENTS.md, CLAUDE.md, GEMINI.md and the rule files of tools already set up, all or nothing.
--check is the CI form and fails on a stale hand-made skill copy (delete it, re-run init) or an
edited managed block. --only CLAUDE.md,.claude limits it to untracked files. Full table:
https://asdalexey.github.io/vitest-auto-spy/utilities/cli.
| Resource | Where |
|---|---|
| Spec patterns at scale | https://asdalexey.github.io/vitest-auto-spy/recipes |
| Task recipes | https://asdalexey.github.io/vitest-auto-spy/guides/mocking-classes · /guides/mocking-local-storage · /guides/mocking-prisma · /guides/storybook-angular |
| Docs index for LLMs | https://asdalexey.github.io/vitest-auto-spy/llms.txt |
| Entire docs as one file | https://asdalexey.github.io/vitest-auto-spy/llms-full.txt |
| Human docs | https://asdalexey.github.io/vitest-auto-spy/ |
| Source | https://github.com/ASDAlexey/vitest-auto-spy |
| Types | node_modules/vitest-auto-spy/dist/index.d.ts (and one per subpath) |
Read dist/*.d.ts before inventing a call. Every export is typed and documented there, and the
type is the authority when this file and the code disagree.
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 Changed · +9 lines · +130 tokens per session bea46e6df7d8
- 6d ago Changed · +3 lines · +7 tokens per session b29e47fe658d
- 20d ago Changed · +1 lines · +27 tokens per session f2f811551b1d
- 27d ago Changed · +3 lines · +61 tokens per session 41c92233956d
- 28d ago Changed · -3 lines · -376 tokens per session 3110b06273db
- 29d ago Changed · +45 tokens per session 683f9be23168
- 1mo ago Changed · +12 tokens per session bb1d061fcb5e
- 1mo ago Changed · -2,192 lines · -35,899 tokens per session a8303fdc03a4
- 1mo ago Changed · +525 lines · +10,323 tokens per session c62840edabbd
- 1mo ago First seen · 2,257 lines · 33,517 tokens per session scan A 6feb6044c4f8
vitest-auto-spy AGENTS.md is an instructions file published in the GitHub repository ASDAlexey/vitest-auto-spy (10 stars, last pushed yesterday), licensed MIT. It adds 7,847 tokens to every session, about $0.0314 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.