What is SwarmAI multi-tab-isolation-principles.md?

Architecture guidance for keeping several chat tabs independent. It defines where each tab's messages, session, streaming status, and other state belong.

It helps developers design and maintain multi-tab chat applications where several tasks run at the same time.

It prevents one chat tab from changing, displaying, or cancelling another tab's work.

How xg-gh-25/SwarmAI configures Kiro

Reuse

Borrowing it

Nothing to install: this file belongs to xg-gh-25/SwarmAI. 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/xg-gh-25/SwarmAI/main/.kiro/steering/multi-tab-isolation-principles.md

Clone the repo

git clone --depth 1 https://github.com/xg-gh-25/SwarmAI

Made for: Kiro.

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/xg-gh-25/swarmai/multi-tab-isolation-principles/github.svg)](https://agentmods.dev/instructions/xg-gh-25/swarmai/multi-tab-isolation-principles)

Your own site

<a href="https://agentmods.dev/instructions/xg-gh-25/swarmai/multi-tab-isolation-principles"><img src="https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/multi-tab-isolation-principles/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/instructions/xg-gh-25/swarmai/multi-tab-isolation-principles"><img src="https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/multi-tab-isolation-principles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,886 This file is loaded in full into every session.

When invoked 2,886 The same file — it is already loaded in full.

Security scan C 1 finding. 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	$0.02886	$0.02886
Opus 5	$0.01443	$0.01443
Sonnet 5	$0.00577	$0.00577
Haiku 4.5	$0.00289	$0.00289

Measured 2d ago against content hash a5532a3483e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

SwarmAI multi-tab-isolation-principles.md scanned grade C with 1 finding 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

**Per-tab permission request (ISOLATED)**: Each tab/session independently raises its own `cmd_permission_request` to the user. If Tab A asks to run `rm -rf build/` and Tab B asks to run `docker build`, these are separate

.kiro/steering/multi-tab-isolation-principles.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Tab Chat Isolation Principles

Architecture Overview

Each chat tab is a standalone session with its own end-to-end lifecycle. The system supports 1-4 concurrent tabs (RAM-adaptive) processing different tasks in parallel. Tabs MUST NOT interfere with each other at any layer.

State Ownership Model

┌─────────────────────────────────────────────────────────────┐
│  tabMapRef (useRef<Map<string, UnifiedTab>>)                │
│  ════════════════════════════════════════════                │
│  AUTHORITATIVE source of truth for ALL per-tab state:       │
│  • messages, sessionId, pendingQuestion                     │
│  • isStreaming, abortController, streamGen                  │
│  • status (idle/streaming/waiting_input/error/etc.)         │
│                                                             │
│  React useState (messages, sessionId, isStreaming, etc.)    │
│  ════════════════════════════════════════════                │
│  DISPLAY MIRROR — reflects ONLY the active tab's state.     │
│  Updated on tab switch via restore + bumpStreamingDerivation│
│                                                             │
│  pendingStreamTabs (useState<Set<string>>)                  │
│  ════════════════════════════════════════════                │
│  PENDING TRACKER — covers the gap between handleSendMessage │
│  and session_start SSE event. Keyed by tabId.               │
└─────────────────────────────────────────────────────────────┘

The 7 Isolation Principles

Principle 1: Tab-Scoped State Mutations

Every state mutation MUST target a specific tabId. Never mutate global/shared state that affects all tabs.

setIsStreaming(value, tabId) — always pass the originating tab's ID
updateTabStatus(tabId, status) — always scope to the specific tab
Stream handlers capture capturedTabId at creation time and use it for all mutations
pendingStreamTabs is keyed by tabId, not a single boolean

Anti-pattern: setIsStreaming(false) without tabId — this defaults to activeTabIdRef.current which may have changed if the user switched tabs during streaming.

Read the full file on GitHub · 192 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.

2d ago First seen · 192 lines · 2,886 tokens per session scan C a5532a3483e7

Subscribe to this mod's changes

SwarmAI multi-tab-isolation-principles.md is an instructions file published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed yesterday), licensed MIT. It adds 2,886 tokens to every session, about $0.0144 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.

Building agents agentic-ai ai-agent aws-bedrock claude claude-sdk context-engineering

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

SwarmAI: Instructions file for Kiro