ghost-qa: Instructions file for Codex

AGENTS.md

ghost-qa AGENTS.md is an instructions file for Codex, OpenCode from avivgerz-hue/ghost-qa. It costs 403 tokens per session, scanned A, original, MIT.

A repository instruction file that makes real-browser verification mandatory for frontend work. It gives coding agents the commands and sequence for readiness checks, multi-size and multi-theme audits, source fixes, and regression comparison.

In plain words
What is it for?
Use it as project guidance for coding agents working on web interfaces, especially when the project uses the ghost-qa browser-checking tool.
Why use it?
It catches browser-only failures that ordinary tests may miss, such as layout overflow, hydration errors, failed requests, focus problems, and dark-theme contrast issues. The instructions also require agents to prove that a fix improved the result.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is avivgerz-hue/ghost-qa's own configuration. It tells Codex and OpenCode how to work on ghost-qa 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 ghost-qa configures β†’

Reuse

Borrowing it

Nothing to install: this file belongs to avivgerz-hue/ghost-qa. 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/avivgerz-hue/ghost-qa/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/avivgerz-hue/ghost-qa

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 ghost-qa AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/avivgerz-hue/ghost-qa/agents-md/github.svg)](https://agentmods.dev/instructions/avivgerz-hue/ghost-qa/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/avivgerz-hue/ghost-qa/agents-md"><img src="https://agentmods.dev/badge/instructions/avivgerz-hue/ghost-qa/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80Γ—15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80Γ—15 button for ghost-qa AGENTS.md

Your own site Β· 80Γ—15
<a href="https://agentmods.dev/instructions/avivgerz-hue/ghost-qa/agents-md"><img src="https://agentmods.dev/badge/instructions/avivgerz-hue/ghost-qa/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 403 This file is loaded in full into every session.
When invoked 403 The same file β€” it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file β€” 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 $0.00403 $0.00403
Opus 5.5 $0.00161 $0.00161
Sonnet 5.5 $0.00081 $0.00081
Haiku 4.5 $0.00040 $0.00040

Measured yesterday against content hash 77ced3b8673a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ghost-qa AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories β€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency β€” measured yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md Β· 16 lines

What it actually says

Agent Instructions

πŸ‘» ghost-qa β€” Browser Verification Protocol (MANDATORY)

Before reporting any task that touches frontend code as complete, you MUST verify it in a real browser β€” the closed-loop Self-Healing Browser Verification Protocol:

  1. Readiness: run ghost-qa doctor (or the ghost_qa_doctor MCP tool). Do not proceed on red.
  2. Baseline audit: ensure the app runs locally, then npx -y ghost-qa test <local-url> --out-dir ghost-qa-out (add --server-cmd "npm run dev" to let ghost-qa manage the server) β€” or call ghost_qa_audit_url. This runs the 8-Trap Engine on Desktop 1440Γ—900, Tablet 768Γ—1024 and Mobile 375Γ—812, light + dark. Save the baseline as before.json (it is ghost-qa-out/report.json).
  3. Root-cause mapping: for every critical/major finding, map the exact DOM selector, bounding box, stack trace or dark-mode contrast failure back to the component file that renders it.
  4. Surgical remediation: fix root causes in source (hydration, overflow, tap targets, ARIA/labels, dark-mode tokens…). Never silence the checker or delete failing UI.
  5. Delta verification: re-run the audit to after.json, then npx -y ghost-qa compare before.json after.json (or ghost_qa_compare). Repeat until QA Health Score is 95–100 (A+), zero critical/major remain, and the delta shows zero new regressions. Only then report done, citing score, routes, viewports and the delta.

Never declare a UI task finished based only on code review, type-checking, or unit tests. The browser is the source of truth.

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. yesterday First seen Β· 16 lines Β· 403 tokens per session scan A 77ced3b8673a

Subscribe to this mod's changes

ghost-qa AGENTS.md is an instructions file published in the GitHub repository avivgerz-hue/ghost-qa (27 stars, last pushed yesterday), licensed MIT. It adds 403 tokens to every session, about $0.0016 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 2026-11-15.

Related

ghost-qa AGENTS.md compared with instructions from other repositories

ghost-qa AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ghost-qa AGENTS.mdavivgerz-hue/ghost-qaInstructions file27yesterdayMITA403Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file282k3d agoMITA4,335Codex, OpenCode