A connector for routing BB Codex or Claude Code conversations through a Magpie gateway, a service that manages access to models. It can inspect settings, check connectivity, configure accounts, and sync a Pi extension.

Use it to inspect or configure the gateway, validate its connection, sync Pi installations, and choose the provider and model used by supported coding threads.

It centralizes model routing and configuration while providing checks that do not send model requests.

magpie — Skill for Claude Code and Codex by vaayne/agent-kit

Install

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.

Any agent

npx skills add vaayne/agent-kit --skill magpie

Clone the repo

git clone --depth 1 https://github.com/vaayne/agent-kit

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vaayne/agent-kit/magpie/github.svg)](https://agentmods.dev/skills/vaayne/agent-kit/magpie)

Your own site

<a href="https://agentmods.dev/skills/vaayne/agent-kit/magpie"><img src="https://agentmods.dev/badge/skills/vaayne/agent-kit/magpie/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vaayne/agent-kit/magpie"><img src="https://agentmods.dev/badge/skills/vaayne/agent-kit/magpie.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 810 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00030	$0.00810
Opus 5.5	$0.00012	$0.00324
Sonnet 5.5	$0.00006	$0.00162
Haiku 4.5	$0.00003	$0.00081

Measured 8d ago against content hash aa617cd9ab47, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

magpie 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.

bb-extensions/magpie/skills/magpie/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BB Magpie connector

Use bb magpie to inspect and configure the connector. Use the separate magpie CLI or Magpie UI to manage gateway accounts and models.

Inspect

bb magpie status shows the gateway, routing settings, sync state, and host installations.
bb magpie check --native checks the gateway without requiring Pi configuration.
bb magpie check also validates the Pi model catalog on the BB server.
Checks do not send model requests.

Monitor

Open Magpie in the BB navigation rail for Gateway, Routing, and Usage. Visible pages refresh every 5 seconds; snapshots are shared for up to 5 seconds. Usage offers Today, 7 days, and 30 days, using the Magpie server's time zone. Costs are model-price estimates, not invoices.

Health and usage read the configured gateway. A restricted gateway key may be refused the global usage summary.
Subscriptions and provider status need webUrl and secret webKey in plugin settings. Optional webLink sets the browser URL for Open Magpie Web. webUrl is an HTTP(S) origin reached by the BB server. Use the fixed MAGPIE_WEB_KEY when available. Never print keys or put them in command arguments.
The Web UI must own the gateway for live routing traces. The page reports when another process owns it.
Monitoring is read-only. It does not expose Web UI credentials, request bodies, session IDs, or raw upstream errors to the browser.

Configure

gatewayUrl is the gateway origin as reached from the BB server. The default is http://127.0.0.1:3425.
Set gatewayKey through the plugin settings when the gateway requires authentication. Do not print keys.
piAgentDir selects the source Pi directory on the server. Each host uses its own PI_CODING_AGENT_DIR or ~/.pi/agent.
autoSync is off for new installations. When enabled, it syncs all persistent machines every 30 seconds and reloads Pi when its threads are idle.

Use bb plugin config magpie set <setting> <value> for non-secret settings.

Pi changes

Read the full file on GitHub · 48 lines

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.

8d ago Changed · +9 lines aa617cd9ab47
9d ago First seen · 39 lines · 30 tokens per session scan A 3202b455fe88

Subscribe to this mod's changes

magpie is a skill published in the GitHub repository vaayne/agent-kit (53 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 810 once invoked, about $0.0001 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 2026-10-12.

Building agents

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…

vercel/next.js · 123 tokens