Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/baixianger/phantom-canvas/agents-mdgit clone --depth 1 https://github.com/baixianger/phantom-canvasWrote 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/baixianger/phantom-canvas/agents-md)<a href="https://agentmods.dev/instructions/baixianger/phantom-canvas/agents-md"><img src="https://agentmods.dev/badge/instructions/baixianger/phantom-canvas/agents-md.svg" alt="Measured on agentmods" 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 | $0.00257 | $0.00257 |
| Opus 5 | $0.00129 | $0.00129 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
phantom-canvas 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.
What it actually says
AGENTS.md
CLI tool and HTTP API for AI image/video generation via Gemini Web.
What this tool does
Phantom Canvas wraps Gemini Web as a programmable CLI and HTTP API. It launches Chrome via CDP, automates Gemini's web UI, and exposes generation capabilities for AI agents, scripts, and applications.
How to use
bun add -g phantom-canvas # or: npm install -g phantom-canvas
phantom-canvas generate "your prompt" -o output.png --headed # first time: login in Chrome
phantom-canvas generate "your prompt" -o output.png # after that: headless
See SKILL.md for complete agent instructions.
Architecture
index.ts— CLI entry point (chrome / generate / serve)lib/browser.ts— Browser automation (Chrome CDP + Playwright)lib/tasks.ts— Async task queuedist/index.js— Compiled Node.js bundle
Session
Chrome stores login in ~/.phantom-canvas/chrome-profile/. First time requires --headed to login interactively. After that, login persists and headless mode works.
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 First seen · 29 lines · 257 tokens per session scan A 482e260c5a91
phantom-canvas AGENTS.md is an instructions file published in the GitHub repository baixianger/phantom-canvas (5 stars, last pushed 5mo ago), licensed MIT. It adds 257 tokens to every session, about $0.0013 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.
Other instructions, from other repositories
comfy-prompt-studio CLAUDE.md
Instructions for yxhpy/comfy-prompt-studio, covering claude.md, 架构设计, 快速启动, 1. 复制环境变量模板 and 2. 编辑 .env 文件，填入你的 api 密钥等敏感信息.
mcp-image-gen CLAUDE.md
Instructions for kevinten-ai/mcp-image-gen, covering claude.md — mcp-image-gen, project overview, architecture, key design decisions and development.
nano-banana-image-skill AGENTS.md
Instructions for Emily2040/nano-banana-image-skill, covering nano banana image skill — agents instructions, canonical entrypoint, secondary files, working agreements and expected outputs.
nano-banana-image-skill GEMINI.md
Instructions for Emily2040/nano-banana-image-skill, covering nano banana image skill, additional context, guidance and gemini api/runtime notes.
nano-banana-image-skill CLAUDE.md
Instructions for Emily2040/nano-banana-image-skill, covering nano banana image skill, start here, repo intent, editing rules and preferred answer shape.
nanobanana-mcp CLAUDE.md
Instructions for YCSE/nanobanana-mcp, covering claude.md, project overview, build commands, architecture and tools exposed.