context-isolation

context-isolation is an agent for Claude Code from thapaliyabikendra/ai-artifacts. It costs 0 tokens per session (1,070 once invoked), scanned A, original, Apache-2.0.

A way for helper agents to work in separate conversation spaces from the main coding session. Each helper returns its result without bringing all of its intermediate work into the main conversation.

In plain words
What is it for?
Use it when delegating research, analysis, or other lengthy tasks to helper agents while keeping the main conversation smaller and easier to follow.
Why use it?
Long investigations can fill the main conversation with temporary details and slow later work. Separate spaces keep the main session focused and allow several helpers to work at once.

Agent for Claude Code

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 agents/thapaliyabikendra/ai-artifacts/context-isolation
Clone the repo
git clone --depth 1 https://github.com/thapaliyabikendra/ai-artifacts

Made for: Claude Code.

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 context-isolation

README.md
[![agentmods](https://agentmods.dev/badge/agents/thapaliyabikendra/ai-artifacts/context-isolation.svg)](https://agentmods.dev/agents/thapaliyabikendra/ai-artifacts/context-isolation)
Your own site
<a href="https://agentmods.dev/agents/thapaliyabikendra/ai-artifacts/context-isolation"><img src="https://agentmods.dev/badge/agents/thapaliyabikendra/ai-artifacts/context-isolation.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,070 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01070
Opus 5 $0.00000 $0.00535
Sonnet 5 $0.00000 $0.00214
Haiku 4.5 $0.00000 $0.00107

Measured 5d ago against content hash b548ba841dda, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-isolation 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.

.claude/skills/claude-artifact-creator/references/agents/context-isolation.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Isolation in Sub-Agents

What is Context Isolation?

Sub-agents operate in their own context window, completely separate from the main conversation. This architectural decision provides significant benefits for performance and cost optimization.

Key Benefits

1. Prevents Context Pollution

When a sub-agent performs extensive exploration or analysis, all that intermediate work stays in its own context. The main session only receives the final result, keeping the main context clean and focused.

2. Faster Responses

With a smaller, focused context window, the main session processes requests more quickly without being slowed down by irrelevant information from sub-agent operations.

3. Lower Costs

Context windows consume tokens. By isolating complex operations to sub-agents, you only pay for the relevant results that get passed back to the main session, not all the intermediate steps.

4. Parallel Efficiency

Multiple sub-agents can work simultaneously in their own contexts without interfering with each other or bloating the main context.

How It Works

┌─────────────────────────────────────┐
│     Main Session Context            │
│  • User conversation                │
│  • High-level task coordination     │
│  • Final results from sub-agents    │
└──────────────┬──────────────────────┘
               │ spawns
               ▼
    ┌──────────────────┐      ┌──────────────────┐      ┌──────────────────┐
    │  Sub-Agent 1     │      │  Sub-Agent 2     │      │  Sub-Agent 3     │
    │  Context         │      │  Context         │      │  Context         │
    │                  │      │                  │      │                  │
    │ • Tool calls     │      │ • Tool calls     │      │ • Tool calls     │
    │ • File reads     │      │ • Analysis       │      │ • Code changes   │
    │ • Exploration    │      │ • Searches       │      │ • Testing        │
    └──────────────────┘      └──────────────────┘      └──────────────────┘
         │ returns                  │ returns                  │ returns
         └──────────────────────────┴──────────────────────────┘
                           Only final results

Read the full file on GitHub · 116 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.

  1. 5d ago First seen · 116 lines · 0 tokens per session scan A b548ba841dda

Subscribe to this mod's changes

context-isolation is an agent published in the GitHub repository thapaliyabikendra/ai-artifacts (24 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,070 tokens. 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.