AI-Watch-Tester: Instructions file for Codex

AGENTS.md

AI-Watch-Tester AGENTS.md is an instructions file for Codex, OpenCode from ksgisang/AI-Watch-Tester. It costs 483 tokens per session, scanned A, original, MIT.

Project instructions for using AWT, a tool that scans web pages and runs UI tests. The required process has separate stages for scanning, writing and showing a test scenario, getting approval, running it, and reporting results.

In plain words
What is it for?
Use it when testing a web application with AWT, especially to inspect page controls, create YAML test scenarios, run approved tests, and report failures.
Why use it?
It prevents tests from running before the user has reviewed and approved them. It also requires the agent to stop when a test step fails and protects the approval mechanism from being bypassed.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions Codex.

This is ksgisang/AI-Watch-Tester's own configuration. It tells Codex and OpenCode how to work on AI-Watch-Tester itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AI-Watch-Tester configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ksgisang/AI-Watch-Tester. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ksgisang/AI-Watch-Tester/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ksgisang/AI-Watch-Tester

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for AI-Watch-Tester AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ksgisang/ai-watch-tester/agents-md/github.svg)](https://agentmods.dev/instructions/ksgisang/ai-watch-tester/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ksgisang/ai-watch-tester/agents-md"><img src="https://agentmods.dev/badge/instructions/ksgisang/ai-watch-tester/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.

agentmods 80×15 button for AI-Watch-Tester AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ksgisang/ai-watch-tester/agents-md"><img src="https://agentmods.dev/badge/instructions/ksgisang/ai-watch-tester/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 483 This file is loaded in full into every session.
When invoked 483 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00483 $0.00483
Opus 5 $0.00242 $0.00242
Sonnet 5 $0.00097 $0.00097
Haiku 4.5 $0.00048 $0.00048

Measured 10d ago against content hash 268d2bdab94a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

AI-Watch-Tester 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 10d 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.md · 49 lines

What it actually says

AWT (AI Watch Tester) — AI Agent Rules

This file is for AI coding assistants (Gemini, Copilot, Codex, Cursor, Claude Code, etc.). Follow these rules when the user asks you to use AWT for testing.

⛔ MANDATORY WORKFLOW — 4 Steps, No Exceptions

When the user asks you to test a web application with AWT, you MUST follow these 4 steps in order. Do NOT skip, combine, or automate any step.

Step 1: SCAN

aat scan --url <URL>

Read .aat/scan_result.json and present a summary to the user:

  • How many elements were found (inputs, buttons, links)
  • Ask: "Should I create a test scenario based on these elements?"
  • WAIT for user response.

Step 2: GENERATE + PRESENT

Write a YAML scenario using data from scan_result.json. Show the full scenario to the user in a readable format. Ask: "Should I run this test? Or do you want me to change anything?"

  • WAIT for user approval.
  • If user requests changes → modify and show again.

Step 3: EXECUTE (only after user says "go ahead")

aat run --skill-mode --fast <scenario_file>

If a step fails → STOP immediately. Report:

  • Which step failed and why
  • What the possible cause is
  • Ask: "Should I fix the scenario, or fix the source code?"
  • WAIT for user instruction. Do NOT auto-fix.

Step 4: REPORT

When all steps pass, summarize the results to the user.

⛔ BANNED — Never Do These

Banned Why
aat devqa Runs entire pipeline without user checkpoints
-y / --auto-approve Bypasses user approval gate
Auto-fixing code without asking User must approve all changes
Auto-retrying failed tests User must decide what to fix first
headless: true User must see the browser
Guessing element names Always scan first, use real data
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. 10d ago First seen · 49 lines · 483 tokens per session scan A 268d2bdab94a

Subscribe to this mod's changes

AI-Watch-Tester AGENTS.md is an instructions file published in the GitHub repository ksgisang/AI-Watch-Tester (7 stars, last pushed 4mo ago), licensed MIT. It adds 483 tokens to every session, about $0.0024 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 2026-08-31.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens