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 skills add bgmacris/quimera-ai --skill tandemgit clone --depth 1 https://github.com/bgmacris/quimera-aiWrote 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/skills/bgmacris/quimera-ai/tandem)<a href="https://agentmods.dev/skills/bgmacris/quimera-ai/tandem"><img src="https://agentmods.dev/badge/skills/bgmacris/quimera-ai/tandem/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.
<a href="https://agentmods.dev/skills/bgmacris/quimera-ai/tandem"><img src="https://agentmods.dev/badge/skills/bgmacris/quimera-ai/tandem.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00068 | $0.02710 |
| Opus 5 | $0.00034 | $0.01355 |
| Sonnet 5 | $0.00014 | $0.00542 |
| Haiku 4.5 | $0.00007 | $0.00271 |
Grade A, and why
tandem 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 10d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tandem — shared browser, human + Claude
The human and you share ONE SAME Chrome in real time. The human sees it and drives it with the mouse;
you operate it with the browser_* tools of the tandem MCP (Playwright over CDP). What one does,
the other sees: state, cookies, and session are the same.
Startup
- The browser does NOT start on its own. If the
browser_*tools giveECONNREFUSED 127.0.0.1:9222, Chrome isn't running: ask the human to run/tandem:browser-start(or run it yourself if you have the command available). Check state with/tandem:browser-status.
Division of labor
- The human does what requires being human: solving captchas, getting past anti-bot checkpoints (e.g. Vercel Security Checkpoint), 2FA logins, visual decisions.
- You do the analysis:
browser_snapshot(accessibility tree, better than a screenshot for reasoning and acting),browser_evaluate(JS),browser_network_requests, data extraction, filling forms, clicking by snapshot ref. - Typical unblocking pattern: the human clears the wall → you read the already-rendered DOM and analyze.
Two modes: live vs delegated (don't pollute the context)
There are two ways to navigate; choose by the task, not one by default:
- Live (in this context): when there's handoff with the human (walls they clear: captcha, checkpoint, login), interactive navigation, or on-the-fly decisions. The human is in the loop.
- Delegated to the
web-navigatorsubagent: when it's HEAVY read/extraction without walls (large snapshots, scraping, walking many pages). The subagent swallows the DOM/snapshots in ITS context and returns to you only the distilled data → this context isn't polluted. You share the SAME Chrome (global state), so the human keeps seeing the window. - Rule: if the task will generate a lot of noise (snapshots of hundreds of KB, multi-page) and does NOT need the human live → delegate. If it needs human handoff or iterating with you → live.
- Limit of delegation: the subagent doesn't talk to the human. If it hits a wall, it returns which and where; you tell the human, they clear it, and you relaunch the subagent to continue.
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.
- 10d ago First seen · 153 lines · 68 tokens per session scan A e9eb87f7e94c
tandem is a skill published in the GitHub repository bgmacris/quimera-ai (11 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 2,710 once invoked, about $0.0003 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.
Other skills, from other repositories
owb
Open Web Bridge (OWB) — drive the user's own real browser with the owb command. Read pages behind their existing logins, gather and cross-check information, fill forms, walk multi-step flows, debug their site, audit responsive/accessibility behavior, and capture or reverse-engineer network traffic. Use this whenever…
chrome-agent
Local browser automation with structured, verified outcomes. Use for web navigation, scraping and extraction, form interaction, screenshots and downloads, network or console checks, responsive testing, or page-scoped device emulation.
scrape-structured-data
Get the repeating records off a web page (product grids, search results, job listings, news feeds, tables) as JSON, without writing CSS selectors and without spending a model call to read the HTML. Works on sites with no API, including ones behind a login or bot protection. Runs locally, one binary, no API key. Use…
browser
Use this skill when the user says browser, /browser, test in Chrome, inspect a webpage, verify a localhost app, capture screenshots, check console/network errors, run browser QA, or automate browser flows with the Mochi browser MCP.
control-chrome-bridge
Drive the user's real Chrome browser — their own profile, tabs, cookies and logged-in sessions — through the chrome-bridge MCP server. Use for tasks that need existing browser state: reading a page behind a login, filling a form on a site the user is signed into, testing a local app in a real browser, or inspecting…
chrome-cdp-ex
Your EYES into the user's live Chrome browser and Electron apps. This skill lets you SEE and INTERACT with the user's actual browser or Electron app — their open tabs, logged-in sessions, and live page state. You MUST use this whenever the user's request involves browser content or Electron app inspection in ANY way.…