Borrowing it
Nothing to install: this file belongs to testivai/testivai-oss. 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/testivai/testivai-oss/main/AGENTS.mdgit clone --depth 1 https://github.com/testivai/testivai-ossWrote 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/testivai/testivai-oss/agents-md)<a href="https://agentmods.dev/instructions/testivai/testivai-oss/agents-md"><img src="https://agentmods.dev/badge/instructions/testivai/testivai-oss/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/testivai/testivai-oss/agents-md"><img src="https://agentmods.dev/badge/instructions/testivai/testivai-oss/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 | $0.05913 | $0.05913 |
| Opus 5.5 | $0.02365 | $0.02365 |
| Sonnet 5.5 | $0.01183 | $0.01183 |
| Haiku 4.5 | $0.00591 | $0.00591 |
Grade A, and why
testivai-oss 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
testivai-oss — Agent Guide
Universal guide for AI coding assistants (Claude Code, Cursor, GitHub Copilot, Gemini, etc.) working inside this repository.
For Claude Code specifically, see CLAUDE.md.
For task recipes, see SKILLS.md.
What this repo is
The public open-source home for the TestivAI visual regression SDKs. Everything here runs fully locally — no account, no API key, no server.
Hard rules — never violate these
-
pnpm only. Never run
npm installoryarnin the workspace root or any package.action/is a workspace package too: add its dependencies withpnpm --filter testivai-action add. -
Local-first. The packages need no account or API key, send nothing anywhere and have no telemetry. Today there is no hosted product: never reference one, and never describe a feature as paid or gated. TestivAI is free to use (
docs/philosophy.md, "Free and open source"); keep wording consistent with it. AI explanation is bring-your-own-model via@testivai/mcp(explain_snapshot). Core vocabulary: pixel diff, DOM diff, noise hint, layered analysis, baselines, threshold. -
action/dist/must always be committed. After any change toaction/src/, rebuild withcd action && pnpm run buildand commit the updateddist/index.js,dist/review.cjsanddist/publish.cjs. CI enforces this. -
Every public API change needs a changeset. Run
pnpm changesetand commit the generated.changeset/*.mdfile with your PR. -
Do not push tags manually without understanding the action versioning scheme. Semver tags (
v1.x.y) roll thev1major tag automatically via CI. See the "Action versioning" section below.
Repo layout
packages/
witness/ @testivai/witness core SDK: CLI, diff engine, baselines, HTML report
playwright/ @testivai/witness-playwright Playwright reporter + capture adapter
webdriverio/ @testivai/witness-webdriverio WebdriverIO service + capture
selenium/ @testivai/witness-selenium Selenium adapter
mcp/ @testivai/mcp MCP server: results + diff images for AI agents
action/ testivai/testivai-oss@v1 GitHub Action: post PR comment + commit status
approve/ testivai/testivai-oss/approve@v1 GitHub Action: /testivai approve command handler
review/ testivai/testivai-oss/review@v1 GitHub Action: Claude triages each diff (advisory; enabled: false turns it off)
publish/ testivai/testivai-oss/publish@v1 GitHub Action: publishes reports to GitHub Pages (rebuilt from checked data) and links them in PR comments
examples/ minimal working examples per framework
docs/ public Markdown documentation
e2e/ OSS smoke E2E test suite
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 · +2 lines · +40 tokens per session fe60a09ff50b
- 8d ago Changed · +47 lines · +864 tokens per session fa3db343749d
- 10d ago Changed · +9 lines · +258 tokens per session d37aa5b17a3c
- 11d ago Changed · +82 lines · +1,752 tokens per session 7eed793007ca
- 13d ago Changed · +8 lines · +189 tokens per session 0fa7dbd58fd2
- 15d ago Changed · +29 lines · +492 tokens per session 8e7dec37afd3
- 17d ago Changed · +1 lines · +20 tokens per session b70ce91f2f2c
- 25d ago Changed · +8 lines · +122 tokens per session 7f7c3acc4c48
- 2mo ago First seen · 243 lines · 2,176 tokens per session scan A eeb8a9cf5ec4
testivai-oss AGENTS.md is an instructions file published in the GitHub repository testivai/testivai-oss (6 stars, last pushed 4d ago), licensed MIT. It adds 5,913 tokens to every session, about $0.0237 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.