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 OpenCoven/coven --skill tinyfish-browsergit clone --depth 1 https://github.com/OpenCoven/covenWrote 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/opencoven/coven/tinyfish-browser)<a href="https://agentmods.dev/skills/opencoven/coven/tinyfish-browser"><img src="https://agentmods.dev/badge/skills/opencoven/coven/tinyfish-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/opencoven/coven/tinyfish-browser"><img src="https://agentmods.dev/badge/skills/opencoven/coven/tinyfish-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Data Exfiltration · line 29 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 49 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00052 | $0.00515 |
| Opus 5.5 | $0.00021 | $0.00206 |
| Sonnet 5.5 | $0.00010 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
tinyfish-browser scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST "https://api.browser.tinyfish.ai" \ What it actually says
TinyFish Browser
Create a remote Chromium browser session. Returns a session_id, a cdp_url for driving the browser over the DevTools Protocol, and an authenticated base_url for polling session state.
Requires: TINYFISH_API_KEY environment variable.
Pre-flight Check (REQUIRED)
Before calling the API, verify the key is present:
[ -n "$TINYFISH_API_KEY" ] && echo "TINYFISH_API_KEY is set" || echo "TINYFISH_API_KEY is NOT set"
If the key is not set, stop and ask the user to add it. Get one at https://agent.tinyfish.ai/api-keys. Do NOT fall back to other browser tools.
Create a Session
curl -X POST "https://api.browser.tinyfish.ai" \
-H "X-API-Key: $TINYFISH_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "url": "https://example.com" }'
Helper Script
scripts/browser.sh <url> wraps the curl call:
scripts/browser.sh https://example.com
Response Shape
{
"session_id": "sess_abc123",
"cdp_url": "wss://browser.tinyfish.ai/devtools/browser/…",
"base_url": "https://api.browser.tinyfish.ai/sessions/sess_abc123"
}
Using the Session
cdp_urlis a DevTools Protocol websocket — connect with Playwright/Puppeteer/chrome-remote-interface to drive the page.base_urlis an authenticated polling endpoint (requires theX-API-Keyheader). It is NOT browsable in a normal web view.
Session Lifecycle
Sessions auto-close after ~1 hour of idleness. There is no explicit terminate endpoint — avoid creating one session per user action; reuse sessions keyed by target URL when possible.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 61 lines · 52 tokens per session scan A 1e01c1dc576b
tinyfish-browser is a skill published in the GitHub repository OpenCoven/coven (72 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 515 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
agent-browser
Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.
computer-use
Desktop control that picks the right interface per step — app scripting (AppleScript/JXA), accessibility-first observation and actions, pixel fallback, screenshots, zoom, screen recording, and switching between registered computers. Qualified on macOS; Windows, Linux and HarmonyOS backends are experimental.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
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…
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).