canary: Skill for Claude Code

.agents/skills/canary-preview/SKILL.md

canary-preview is a skill for Claude Code from osauer/canary. It costs 84 tokens per session (437 once invoked), scanned A, original, MIT.

A preview helper for opening the Canary single-page app, a web app that loads its interface in one browser page, on a local address.

In plain words
What is it for?
Use it to start or reuse the Canary preview at the specified local address and open it in a Codex browser panel.
Why use it?
It provides a safe isolated preview without using the shared network host or exposing write actions to an unpaired browser.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is osauer/canary's own configuration. It tells Claude Code how to work on canary 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 canary configures →

Part of the canary plugin — 3 skills, 2 hooks, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to osauer/canary. 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/osauer/canary/main/.agents/skills/canary-preview/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/osauer/canary

Made for: Claude Code.

Or install canary, the plugin that ships this one along with the rest of its 3 skills, 2 hooks, 1 MCP server.

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 canary-preview

README.md
[![agentmods](https://agentmods.dev/badge/skills/osauer/canary/canary-preview.svg)](https://agentmods.dev/skills/osauer/canary/canary-preview)
Your own site
<a href="https://agentmods.dev/skills/osauer/canary/canary-preview"><img src="https://agentmods.dev/badge/skills/osauer/canary/canary-preview.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 437 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00084 $0.00437
Opus 5 $0.00042 $0.00218
Sonnet 5 $0.00017 $0.00087
Haiku 4.5 $0.00008 $0.00044

Measured 8d ago against content hash 5fa990bfd2eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

canary-preview 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 8d 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/skills/canary-preview/SKILL.md · 34 lines

What it actually says

Canary preview

Open the isolated Canary SPA at http://127.0.0.1:8766/. Never adopt, kill, restart, or bind the shared LAN host on 0.0.0.0:8765; it belongs to the phone-paired app.

  1. Reuse an already-open tab or preview process for that exact URL. Do not launch a duplicate.

  2. Otherwise start this direct command in a long-running terminal session and keep it alive:

    canary app --addr 127.0.0.1:8766 --public-url http://127.0.0.1:8766 --state-dir /tmp/ibkr-codex-preview-app-state-8766 --preview-read-grant
    
  3. Open http://127.0.0.1:8766/ in a Codex browser panel. Prefer the Codex app open-panel tool; do not load browser automation merely to show the page.

  4. Stop when the panel is open. No pairing, navigation beyond /, page reads, screenshots, or console inspection. Report success in one line.

The --preview-read-grant flag exposes only read routes to an unpaired loopback browser. Never submit broker writes from a browser.

The preview serves the installed binary, not loose source. After editing web/app, run make install, stop only this skill's long-running preview session, and launch it again. A blank page with no console errors usually means the isolated server is no longer running; restart this preview session before debugging the SPA.

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. 8d ago First seen · 34 lines · 84 tokens per session scan A 5fa990bfd2eb

Subscribe to this mod's changes

canary-preview is a skill published in the GitHub repository osauer/canary (8 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 437 once invoked, about $0.0004 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 skills, from other repositories

ibkr

Interactive Brokers — global stocks/forex/futures via a LOCAL TWS/IB Gateway, not cloud. Covers stocks, ETFs, forex, futures; account, positions, orders, quotes, history, order placement. Use when the user wants to check or trade an Interactive Brokers account (e.g. "IBKR positions", "buy 10 AAPL on IBKR paper", "my…

Starchild-ai-agent/official-skills · 102 tokens

x402

Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…

browser-use/browser-use · 175 tokens

pinchtab

Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…

pinchtab/pinchtab · 94 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

tradingview-mcp

AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and multi-market screener. Supports stocks, crypto, ETFs, indices, Turkish (BIST), and Egyptian (EGX) markets.

atilaahmettaner/tradingview-mcp · 73 tokens

stock-api

Fetch real-time stock quotes, K-line (candlestick) history, and search symbols for China A-shares, Hong Kong, and US markets. Use when the user asks for a stock price, a quote, market data, candlestick/K-line data, or to look up a stock code by company name.

zhangxiangliang/stock-api · 66 tokens