What is qiankun AGENTS.md?

A project knowledge base for qiankun, a micro-frontend framework, covering its code structure, architecture, commands, and build process. A monorepo is one repository that contains several related packages.

Use it when developing, building, or debugging qiankun and its packages, especially when a task touches the sandbox, loader, shared code, or UI bindings.

It gives coding agents the repository rules and package relationships they need before making changes, including which tools and runtime versions to use.

qiankun AGENTS.md — Instructions file for Codex and OpenCode by umijs: A project knowledge base for qiankun, a micro-frontend framework…

About the project

qiankun is a JavaScript framework for building web applications from independently developed micro frontends, allowing multiple teams to combine apps made with different frameworks. It addresses integration, isolation, deployment independence, runtime sandboxing, performance, and shared dependencies between those smaller applications. Catalogue add-ons provide workflows for using qiankun.

umijs/qiankun · 16,679 stars · on GitHub

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.

agentmods

npx agentmods add instructions/umijs/qiankun/agents-md

Clone the repo

git clone --depth 1 https://github.com/umijs/qiankun

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/umijs/qiankun/agents-md.svg)](https://agentmods.dev/instructions/umijs/qiankun/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/umijs/qiankun/agents-md"><img src="https://agentmods.dev/badge/instructions/umijs/qiankun/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,000 This file is loaded in full into every session.

When invoked 3,000 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.03000	$0.03000
Opus 5	$0.01500	$0.01500
Sonnet 5	$0.00600	$0.00600
Haiku 4.5	$0.00300	$0.00300

Measured 5d ago against content hash ed8b327cfa39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qiankun 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 5d 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.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QIANKUN PROJECT KNOWLEDGE BASE

Updated: 2026-07-06 · Commit: dcc42ae4 · Branch: next (qiankun 3.0, active dev)

Qiankun is a micro-frontend framework built on single-spa. v3 rewrites the runtime around streaming HTML-entry loading, a Proxy-membrane JS sandbox, and native ESM-sandbox execution. It is a pnpm monorepo built with Vite 8; tsc emits package declarations.

Requires Node ^22.15 || >=24, [email protected] (see packageManager). Never use npm/yarn at the root.

STRUCTURE

qiankun/
├── packages/
│   ├── qiankun/         # Facade: public APIs (register/loadMicroApp, start, prefetch) + loadApp orchestration
│   ├── sandbox/         # JS isolation: Proxy membrane + Compartment  → packages/sandbox/AGENTS.md
│   ├── loader/          # Streaming HTML-entry loader (writable-dom)  → packages/loader/AGENTS.md
│   ├── shared/          # Transpilers, fetch-utils, module-resolver, ESM-sandbox engine → packages/shared/AGENTS.md
│   ├── single-spa/      # Vendored single-spa fork (@qiankunjs/single-spa, upstream 7.0 @ ce0f925a) → packages/single-spa/README.md
│   ├── ui-bindings/     # <MicroApp> components: react/ vue/ shared/ (dogfooded by examples/{main,vue-host})
│   └── bundler-plugin/  # Webpack(4/5) + Vite plugins: mark entry script, fix output library
├── skills/              # Agent skills (installed by users via `npx skills add umijs/qiankun`) — content, not code: no build/publish
├── e2e/                 # Playwright, runs against BUILT dist → e2e/README.md
├── examples/            # Runnable demos: two hosts (main = @qiankunjs/react, vue-host = @qiankunjs/vue) + react/vue/purehtml/webpack
└── docs/                # VitePress site (docs/rfcs holds design RFCs)

PROGRESSIVE DISCLOSURE — read the scoped doc before editing a package

Working in…	Read first
`packages/sandbox/**`	`packages/sandbox/AGENTS.md` — membrane, compartment, patchers, ESM globals
`packages/loader/**`	`packages/loader/AGENTS.md` — streaming pipeline, head virtualization
`packages/shared/**`	`packages/shared/AGENTS.md` — transpilers, fetch decorators, esm-sandbox
`e2e/**`	`e2e/README.md` — Playwright layout, fixtures, anti-flake rules

Read the full file on GitHub · 135 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.

5d ago First seen · 135 lines · 3,000 tokens per session scan A ed8b327cfa39

Subscribe to this mod's changes

qiankun AGENTS.md is an instructions file published in the GitHub repository umijs/qiankun (16,679 stars, last pushed 5d ago), licensed MIT. It adds 3,000 tokens to every session, about $0.0150 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 2026-08-30.

javascript micro-frontend micro-frontends microfrontend microfrontends microservices

qiankun AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

QIANKUN PROJECT KNOWLEDGE BASE

STRUCTURE

PROGRESSIVE DISCLOSURE — read the scoped doc before editing a package

What this file has done since we first saw it

Other instructions, from other repositories

microfrontends AGENTS.md

microfrontends CLAUDE.md

appwrite AGENTS.md

orm AGENTS.md

joint CLAUDE.md

ai AGENTS.md