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 jxoesneon/Ciel --skill dev-browsergit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/dev-browser)<a href="https://agentmods.dev/skills/jxoesneon/ciel/dev-browser"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/dev-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/jxoesneon/ciel/dev-browser"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/dev-browser.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 | $0.00040 | $0.00651 |
| Opus 5.5 | $0.00016 | $0.00260 |
| Sonnet 5.5 | $0.00008 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
dev-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 26d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIEL ADAPTATION: Dev Browser (Browser Automation Primitive)
This skill provides a CLI-driven browser automation primitive with persistent page state. It is a catalytic primitive — other skills compose on top of it for e2e testing, scraping, and visual verification. Ciel's autonomy ladder gates network access (logged), secrets (user escalation for form-fill credentials), and fs writes outside project (user escalation).
Installation
npm install -g dev-browser
dev-browser install
Capabilities
- Persistent page state: Navigation context survives across script invocations within a session.
- Sandboxed JavaScript scripts: Execute browser control logic via JS scripts, not interactive sessions.
- Navigation:
go to [url], click elements, wait for selectors. - Form interaction: Fill fields, submit forms, handle auth flows.
- Screenshot capture: Visual snapshots for verification and debugging.
- Data extraction: Scrape page content, extract structured data from DOM.
- Web app testing: Automated interaction flows for QA and e2e validation.
Usage Patterns
- Navigate: Open a URL and wait for load —
dev-browsermaintains page state between calls. - Interact: Click buttons, fill forms, submit — chain actions in a single script for atomicity.
- Capture: Take screenshots at key states for visual evidence in verification pipelines.
- Extract: Pull structured data from pages — pair with
regex-vs-llm-structured-textfor parsing. - Test: Automate click-through flows for web app validation — pair with
e2e-testingfor assertions.
Ciel Autonomy Gates
- Network access: Logged by default; no escalation needed for public URLs.
- Form-fill credentials: User escalation required — never auto-fill passwords or API keys without explicit user approval.
- Filesystem writes outside project: User escalation required — screenshots and scraped data must land in project-scoped paths unless user approves otherwise.
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.
- 26d ago Changed · -9 lines 82eda512cd38
- 1mo ago First seen · 66 lines · 40 tokens per session scan A a360660d60e7
dev-browser is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 651 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
ui-regression
This skill should be used when the user asks to "verify UI changes", "test every screen and action", "run regression QA", "check a deployed UI", or "validate an extension release". Test known web and browser-extension workflows on localhost, staging, or production with action coverage, recovery, localization…
playwright-uitest
Generate Playwright UI tests and visual smoke reports for delivery POC frontends.
vibe-behavioral-test-capture
Builds an executable safety net of characterization tests by integrating browser flow recording, API payload snapshotting, DOM state captures, network traces, and mock fixture generation.
browser-testing
A browser-based end-to-end testing workflow, where end-to-end testing means checking a complete user-facing feature through the browser, with test cases stored in Markdown files.
webapp-testing
Verify a local web app in a real browser with page, element, click, form, console and screenshot evidence. Use after a build or UI change; do not implement features or publish deployments with this skill.
nobrainer-browser
Use when the owner says nb-browser or nobrainer-browser, asks to inspect or operate a rendered website, attach to an existing approved Chrome/Edge session, restart an approved non-default Chromium profile for loopback CDP, reproduce a browser flow, run Playwright tests, or record and analyze a Playwright trace. Prefer…