Paperclip is a Node.js server and React application for coordinating AI agents as a business team, with goals, organizational roles, budgets, governance, and work tracking in one interface. It is used by people managing multiple agents or autonomous agent organizations across tools such as OpenClaw, Claude Code, Codex, and Cursor. The catalogue includes skills, agents, an MCP add-on, and an instruction for working with Paperclip.
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 paperclipai/paperclip --skill agent-browsergit clone --depth 1 https://github.com/paperclipai/paperclipWrote 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/paperclipai/paperclip/agent-browser)<a href="https://agentmods.dev/skills/paperclipai/paperclip/agent-browser"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/agent-browser/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/paperclipai/paperclip/agent-browser"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 79 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.00040 | $0.01103 |
| Opus 5.5 | $0.00016 | $0.00441 |
| Sonnet 5.5 | $0.00008 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
agent-browser scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- You need to read JavaScript-rendered content that `curl`/`wget` will not see. How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Browser
Use a controlled browser to verify behavior, capture evidence, or extract information from web pages that a static fetch cannot reach (SPAs, login-gated pages, dynamic content). This skill is about supervised verification, not unattended scraping.
When to use
- You need a screenshot of a deployed page or a local dev server to confirm a UI change.
- You need to read JavaScript-rendered content that
curl/wgetwill not see. - A user reports a UI bug and you need to reproduce it interactively to capture console errors, network requests, or layout state.
- You need to walk through a short flow (load page, click, observe) to verify acceptance criteria.
When not to use
- The page is reachable as static HTML. Use
curl/HTTP fetch — it is cheaper, faster, and more reliable. - The task is unattended large-scale scraping. That belongs to a dedicated scraper with rate limits, robots.txt handling, and a real user agent policy — not this skill.
- The site is behind authentication you do not own credentials for, or whose terms of service prohibit automation.
- The site involves sensitive accounts (banking, healthcare, government) where automation risks lockout or compliance issues.
Before launching the browser
- Confirm the URL and what state should be true after navigation.
- Decide what evidence is needed: full-page screenshot, viewport screenshot, console log, network trace, HTML snapshot, extracted text.
- Decide the viewport size that matters for the task (mobile vs desktop). Default to a desktop size unless the task is mobile-specific.
- For local dev servers, confirm the server is running and the port is what you expect.
Driving the browser
A typical verification session:
- Launch with a real-looking user agent when the target is the public internet; an unrealistic UA flags automation traffic.
- Set a sane viewport (e.g., 1366×768 desktop, 390×844 iPhone-ish).
- Navigate and wait for the right signal. Prefer waiting for a specific selector or network-idle over arbitrary sleeps.
- Capture evidence immediately after the wait condition succeeds, before any interaction perturbs the state.
- Interact deliberately. One click at a time, with a wait between actions; re-screenshot after each meaningful state change.
- Read the console and network panels for unexpected errors, 4xx/5xx responses, or slow requests.
- Close the browser cleanly when done. Long-running browser sessions leak memory and hold ports.
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.
- 1mo ago First seen · 94 lines · 40 tokens per session scan A 362f7b9d0229
agent-browser is a skill published in the GitHub repository paperclipai/paperclip (106,159 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,103 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
app-launcher
Launch applications, open URLs in browser, and list running processes. Requires approval for launching applications.
tutti-workspace-app-factory
Create, convert, or repair one Tutti workspace app as either a self-contained publishable package under package/ or a Chrome-style local debug app under .tutti/dev-app/. Use for mention://workspace-app-factory/create handoffs, mention://workspace-app-factory handoffs, standalone app generation, adapting existing…
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron apps — navigating, forms, clicks, screenshots, data extraction, testing web apps, UI checks, the dashboard Electron shell, or the user's own logged-in Chrome via the browser relay or Panerelay (SSO/2FA). Triggers: "open…
data-scraper
Use when data lives on a website with no usable API — listings, prices, public records — and the scrape must stay legal and not get blocked: legal gate, extraction path, durable selectors, pacing, resilience. NOT parsing bytes you already hold into fields (that is structured-extraction), NOT a documented API or key…
run-dashboard-e2e-local-changes
Run Playwright E2E (tests/e2e/) against the docker/ all-in-one harness so it reflects LOCAL code changes, not a stale cached image.
ui-visual-self-review
Use when you are about to hand off any UI change - the four-width check and the screenshot checklist that decide whether the screen is really done.