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/algopian/chromeclaw/indexgit clone --depth 1 https://github.com/algopian/chromeclawWhat 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 | $0.00844 |
| Opus 5 | $0.00000 | $0.00422 |
| Sonnet 5 | $0.00000 | $0.00169 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
index 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 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.
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
ChromeClaw supports multiple named agents, each with their own model, tools, workspace files, memory, and personality. Switch between agents to get different behaviors for different tasks.
What is an agent?
An agent is a named AI persona with its own configuration:
- Identity — Name, description, avatar/emoji
- Model — Which LLM to use (can differ per agent)
- Tools — Which tools are enabled (can override global settings)
- Workspace files — Per-agent SOUL.md, AGENTS.md, USER.md, etc.
- Custom tools — Agent-specific JS tools registered via
@toolmetadata - Memory — Separate memory scope per agent
Creating agents
- Open the Options page → Agent tab group → Agents
- Click Add Agent
- Configure the agent's name, emoji, and description
- Optionally set a per-agent model
- Optionally override tool availability
- Customize workspace files for this agent
Switching agents
Switch between agents from the chat interface. Each agent maintains its own:
- Workspace file contents (SOUL.md, AGENTS.md, etc.)
- Custom tool registrations
- Memory scope
Chat history is shared across agents, but the agent context (system prompt, tools, workspace) changes.
Agent loop
The agent loop processes each conversation turn:
- Build system prompt from workspace files, tool descriptions, and agent config
- Stream LLM response with text, reasoning, and tool calls
- Execute tool calls with schema validation and timeout management
- Process follow-ups — Handle multi-turn tool interactions
- Handle steering — Process user corrections mid-turn
Steering messages
If you send a message while the agent is still processing, it's queued as a "steering message" and applied at the next opportunity. This lets you correct the agent's direction mid-task.
Follow-up mode
After tool execution, the agent may need additional turns to complete a task. Follow-up messages are auto-generated to keep the agent loop running until the task is done.
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 · 101 lines · 0 tokens per session scan A 046d7f345ab1
index is an agent published in the GitHub repository algopian/chromeclaw (197 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 844 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.