What is SwarmAI session-identity-and-backend-isolation.md?

A set of instructions for keeping a conversation tied to one browser tab and one stable session identity. It also separates the application's session ID from the internal ID used by the AI software.

Use it when implementing session storage, message persistence, backend requests, tab state, or conversation resume behavior.

It prevents messages, saved history, and tab state from being mixed between conversations, including after a backend restart.

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/session-identity-and-backend-isolation.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/session-identity-and-backend-isolation/github.svg)](https://agentmods.dev/instructions/xg-gh-25/swarmai/session-identity-and-backend-isolation)

Your own site

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

Per session 1,314 This file is loaded in full into every session.

When invoked 1,314 The same file — it is already loaded in full.

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	$0.01314	$0.01314
Opus 5	$0.00657	$0.00657
Sonnet 5	$0.00263	$0.00263
Haiku 4.5	$0.00131	$0.00131

Measured 5d ago against content hash cf3fb195edce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

SwarmAI session-identity-and-backend-isolation.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.

.kiro/steering/session-identity-and-backend-isolation.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Identity and Backend Isolation Principles

Core Invariant: One Tab = One Session ID = One Conversation

A session ID is the permanent identity of a conversation. It is the key for all message persistence, backend API calls, and frontend tab state. Once assigned, it MUST NOT change for the lifetime of that conversation.

The Dual-ID Model

┌──────────────────────────────────────────────────────────────┐
│  app_session_id (frontend tab ID)                            │
│  ═══════════════════════════════                             │
│  Assigned by the frontend when a tab first sends a message.  │
│  Stable across backend restarts. This is the CANONICAL ID    │
│  for all persistence and SSE communication.                  │
│                                                              │
│  sdk_session_id (Claude SDK internal ID)                     │
│  ═══════════════════════════════                             │
│  Assigned by the Claude SDK subprocess. Changes on every     │
│  fresh client creation. This is an IMPLEMENTATION DETAIL     │
│  that MUST NOT leak into the app's session model.            │
│                                                              │
│  effective_session_id pattern:                               │
│    app_session_id ?? sdk_session_id                          │
│  Used in ~15 places for all persistence and keying.          │
└──────────────────────────────────────────────────────────────┘

Session ID Rules

session_start SSE event MUST always carry the app_session_id (original tab session ID), never the SDK's internal session ID
All messages (user + assistant) MUST be saved under app_session_id
The _active_sessions dict MUST be keyed by effective_session_id so resume finds the client under the original tab ID
Frontend tab's tabMapRef entry MUST NOT be overwritten with a different session ID after session_start

Resume-Fallback Path (Backend Restart Scenario)

When the backend restarts and loses its in-memory SDK client:

Read the full file on GitHub · 115 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 · 115 lines · 1,314 tokens per session scan A cf3fb195edce

Subscribe to this mod's changes

SwarmAI session-identity-and-backend-isolation.md is an instructions file published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed 4d ago), licensed MIT. It adds 1,314 tokens to every session, about $0.0066 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 2026-09-06.

Backend and APIs 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