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.
npx agentmods add agents/thapaliyabikendra/ai-artifacts/context-isolationgit clone --depth 1 https://github.com/thapaliyabikendra/ai-artifactsWrote 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.
[](https://agentmods.dev/agents/thapaliyabikendra/ai-artifacts/context-isolation)<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>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 | $0.00000 | $0.01070 |
| Opus 5 | $0.00000 | $0.00535 |
| Sonnet 5 | $0.00000 | $0.00214 |
| Haiku 4.5 | $0.00000 | $0.00107 |
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.
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
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 · 116 lines · 0 tokens per session scan A b548ba841dda
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.