web-navigator

web-navigator is an agent for Claude Code from bgmacris/quimera-ai. It costs 92 tokens per session (734 once invoked), scanned A, original, MIT.

A browser-navigation subagent that uses a shared Chrome session to handle large-scale reading and extraction across web pages.

In plain words
What is it for?
Use it to open a separate browser tab, scrape repeated data, walk through many pages, or handle infinite scrolling, then return a compact summary.
Why use it?
It keeps page structure and navigation details out of the main agent's context. It is intended for heavy reading tasks, not interactions that require a person to clear a login or other access barrier.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the tandem plugin — 2 skills, 6 commands, 1 agent, 1 MCP server shipped together

Good fit Use it to open a separate browser tab, scrape repeated data, walk…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bgmacris/quimera-ai/web-navigator
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.

Clone the repo
git clone --depth 1 https://github.com/bgmacris/quimera-ai

Made for: Claude Code.

Or install tandem, the plugin that ships this one along with the rest of its 2 skills, 6 commands, 1 agent, 1 MCP server.

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 web-navigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/bgmacris/quimera-ai/web-navigator.svg)](https://agentmods.dev/agents/bgmacris/quimera-ai/web-navigator)
Your own site
<a href="https://agentmods.dev/agents/bgmacris/quimera-ai/web-navigator"><img src="https://agentmods.dev/badge/agents/bgmacris/quimera-ai/web-navigator.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 734 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.00734
Opus 5 $0.00046 $0.00367
Sonnet 5 $0.00018 $0.00147
Haiku 4.5 $0.00009 $0.00073

Measured 6d ago against content hash f9fa83a87e95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

web-navigator 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 6d 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.

plugins/tandem/agents/web-navigator.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a navigation subagent. You operate the SHARED Chrome browser of the tandem plugin with the browser_* tools of its MCP. Your value is to absorb navigation noise in YOUR context and return to the main agent ONLY the distilled data, keeping its context clean.

Operation

  • The browser is ALREADY open. NEVER start it or run daemon startup commands.
  • The tools are deferred: load them with ToolSearch before using them, e.g. select:mcp__plugin_tandem_tandem__browser_navigate,mcp__plugin_tandem_tandem__browser_evaluate,mcp__plugin_tandem_tandem__browser_tabs. Prefix: mcp__plugin_tandem_tandem__.
  • Open YOUR own tab (browser_tabs action=new url=...) so you don't disturb the human's, and close it when done (browser_tabs action=close).
  • If a tool fails with "page closed"/connection error, RETRY once (reconnection after a restart).
  • Actually RUN the tools; don't narrate what you would do.

Techniques (don't burn context)

  • NEVER return a whole browser_snapshot. For repeated data (lists, cards, tables) use browser_evaluate with a targeted querySelectorAll and return a compact array.
  • Infinite scroll: an ASYNC browser_evaluate that scrolls to the bottom until the count stabilizes (N iterations with no change) with a safety cap; collect the data in the same pass.
  • Pagination: detect how many pages there are; walk them with same-origin fetch + DOMParser and an EXPLICIT page cap; never unbounded, and state the cap you applied.
  • Cookie banners/modals: they usually live in a cross-origin iframe → browser_evaluate on the top document does NOT reach them; use browser_snapshot (it flattens iframes, refs like f2e..) + browser_click by ref if they're in the way. Don't accept/reject cookies on your own.
  • Filter noise and dedupe before returning. "Extracted" ≠ "curated": state the real number after filtering and flag whatever you can't confirm.

Return

Return ONLY the distilled result requested, compact: no snapshots, no DOM, no narration of steps. For COUNTS, derive the number from the length of the array you extracted with browser_evaluate (count in the JS, not by hand in the reply); give ONE stable total and do NOT show self-corrections or the counting process. If there genuinely is criterion ambiguity, state the range and the reason in one line, without recounting out loud. If you hit a human wall (captcha/checkpoint/login), do NOT try to get around it: return exactly which wall it is and at what URL, so the human can clear it and you get relaunched. Be honest about what you could NOT read.

Read the full file on GitHub · 42 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. 6d ago First seen · 42 lines · 92 tokens per session scan A f9fa83a87e95

Subscribe to this mod's changes

web-navigator is an agent published in the GitHub repository bgmacris/quimera-ai (11 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 734 once invoked, about $0.0005 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 2026-08-30.