Instatic is a self-hosted content management system with a visual editor, content tools, and publishing in one Bun server, producing static HTML and CSS pages. It is used to build and manage websites such as blogs, portfolios, and small-business sites.
Borrowing it
Nothing to install: this file belongs to CoreBunch/Instatic. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CoreBunch/Instatic/main/.agents/skills/agent-browser/SKILL.mdgit clone --depth 1 https://github.com/CoreBunch/InstaticWrote 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/corebunch/instatic/agent-browser)<a href="https://agentmods.dev/skills/corebunch/instatic/agent-browser"><img src="https://agentmods.dev/badge/skills/corebunch/instatic/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/corebunch/instatic/agent-browser"><img src="https://agentmods.dev/badge/skills/corebunch/instatic/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Data Exfiltration · line 311 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- medium MCP Rug Pull · line 4 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 552 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00108 | $0.05314 |
| Opus 5.5 | $0.00043 | $0.02126 |
| Sonnet 5.5 | $0.00022 | $0.01063 |
| Haiku 4.5 | $0.00011 | $0.00531 |
Grade A, and why
agent-browser 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 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.
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.
Copies of this mod
8 near-identical copies found in the catalogue:
- agent-browser — 100% identical, 44 lines differ
- agent-browser — 89% identical, 71 lines differ
- agent-browser — 89% identical, 71 lines differ
- agent-browser — 84% identical, 121 lines differ
- agent-browser — 83% identical, 125 lines differ
- agent-browser — 83% identical, 125 lines differ
- agent-browser — 83% identical, 125 lines differ
- agent-browser — 81% identical, 125 lines differ
How it starts
The opening of the file, as written. The whole thing — 626 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
Core Workflow
Every browser automation follows this pattern:
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(get element refs like@e1,@e2) - Interact: Use refs to click, fill, select
- Re-snapshot: After navigation or DOM changes, get fresh refs
agent-browser open https://example.com/form
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"
agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i # Check result
Command Chaining
Commands can be chained with && in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls.
# Chain open + wait + snapshot in one call
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i
# Chain multiple interactions
agent-browser fill @e1 "[email protected]" && agent-browser fill @e2 "password123" && agent-browser click @e3
# Navigate and capture
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png
When to chain: Use && when you don't need to read the output of an intermediate command before proceeding (e.g., open + wait + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs).
Handling Authentication
When automating a site that requires login, choose the approach that fits:
Option 1: Import auth from the user's browser (fastest for one-off tasks)
# Connect to the user's running Chrome (they're already logged in)
agent-browser --auto-connect state save ./auth.json
# Use that auth state
agent-browser --state ./auth.json open https://app.example.com/dashboard
What ships with it
10 files 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.
- references/authentication.md 8.2 KB
- references/commands.md 9.7 KB
- references/profiling.md 3.3 KB
- references/proxy-support.md 4.9 KB
- references/session-management.md 4.2 KB
- references/snapshot-refs.md 4.2 KB
- references/video-recording.md 3.5 KB
- templates/authenticated-session.sh 3.6 KB runs code
- templates/capture-workflow.sh 1.8 KB runs code
- templates/form-automation.sh 1.8 KB runs code
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 · 626 lines · 108 tokens per session scan A d0b650f76cb7
agent-browser is a skill published in the GitHub repository CoreBunch/Instatic (8,966 stars, last pushed 4d ago), licensed MIT. It adds 108 tokens to every session and 5,314 once invoked, about $0.0004 per session on Opus 5.5. 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
agent-browser
Use the agent-browser CLI to exercise web interfaces, inspect rendered accessibility state, verify interactions, and capture screenshots. Use for browser-based UI testing and evidence collection. Do not use as a substitute for deterministic Playwright coverage when an automated regression test is the requested…
ux-acceptance-tester
Perform a goal-driven, black-box UX acceptance journey in a browser and report the path, friction, and observable outcome. Use only in an isolated tester context with a supplied start URL and brief.
ux-acceptance-coordinator
Coordinate black-box, agent-driven UX acceptance journeys against a disposable EmDash admin site. Use when preparing, dispatching, verifying, or reporting a manual browser journey performed by a separate tester agent. Do not use for deterministic Playwright tests or ordinary code review.
repro-public
Reproduce a bug in the public-facing rendered site (not the admin). Attach a container, start the demo dev server, drive public routes with agent-browser, and capture the reproduction as screenshots plus a replayable transcript.
uisandbox
Open a real, built web app in UISandbox — the interactive sandbox in the user's browser, 1:1, with the app's own knobs (brand, colours, fonts, radius, spacing…) — or test one change headlessly, verify it still renders 1:1, get a screenshot and the patch. Use when someone wants to look at their app in a sandbox and…
mobile-viewport-fit
Make full-screen web apps (game boards, tools with fixed header + flexible content + fixed keyboard/footer) fit on mobile without scrolling. Solves the common problem where 100vh includes the browser address bar area on mobile, causing content to overflow below the visible viewport.