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.
curl -O https://raw.githubusercontent.com/avivgerz-hue/ghost-qa/main/AGENTS.mdgit clone --depth 1 https://github.com/avivgerz-hue/ghost-qaWrote 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/avivgerz-hue/ghost-qa/agents-md)<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 80Γ15 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/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>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 | $0.00403 | $0.00403 |
| Opus 5.5 | $0.00161 | $0.00161 |
| Sonnet 5.5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00040 | $0.00040 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ghost-qa CLAUDE.md β 100% identical, 0 lines differ
What it actually says
Agent Instructions
π» 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:
- Readiness: run
ghost-qa doctor(or theghost_qa_doctorMCP tool). Do not proceed on red. - 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 callghost_qa_audit_url. This runs the 8-Trap Engine on Desktop 1440Γ900, Tablet 768Γ1024 and Mobile 375Γ812, light + dark. Save the baseline asbefore.json(it isghost-qa-out/report.json). - 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.
- Surgical remediation: fix root causes in source (hydration, overflow, tap targets, ARIA/labels, dark-mode tokensβ¦). Never silence the checker or delete failing UI.
- Delta verification: re-run the audit to
after.json, thennpx -y ghost-qa compare before.json after.json(orghost_qa_compare). Repeat until QA Health Score is 95β100 (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.
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.
- yesterday First seen Β· 16 lines Β· 403 tokens per session scan A 77ced3b8673a
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.
ghost-qa AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ghost-qa AGENTS.mdavivgerz-hue/ghost-qa | Instructions file | 27 | yesterday | MIT | A | 403 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 282k | 3d ago | MIT | A | 4,335 | Codex, OpenCode |