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 joao-aires/agent-skills-public --skill browser-extension-developmentgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/browser-extension-development)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/browser-extension-development"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/browser-extension-development/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/joao-aires/agent-skills-public/browser-extension-development"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/browser-extension-development.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 | $0.00046 | $0.01035 |
| Opus 5.5 | $0.00018 | $0.00414 |
| Sonnet 5.5 | $0.00009 | $0.00207 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
browser-extension-development 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 8d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build around the extension's execution boundaries
Use this expertise within the requested activity. A design request ends at design; implementation uses accepted requirements and the project's contribution process. For new work, establish the user action, sites/data involved and useful first slice before selecting entrypoints. Reuse established decisions without another questionnaire. This package targets Chrome/MV3; other browser APIs, stores and background models need their own compatibility evidence.
Establish the actual application
Inspect project instructions, package scripts and lockfile, source configuration, generated manifest and supported browser versions. Trace the feature through the contexts that actually execute it:
| Context | Responsibility and lifetime |
|---|---|
| Popup | Short interaction; destroyed when dismissed. Save meaningful work outside its component/DOM state. |
| Side panel or options page | Longer interaction, still subject to closure and reload. Reconstruct state and pending work deliberately. |
| Content script | Operates on a particular page/frame; shares the DOM with the site while normally running in an isolated JavaScript world. Navigation and extension updates can invalidate it. |
| Extension service worker | Event-driven coordination without a DOM. Can terminate and restart; process globals are temporary caches. |
| Backend, when needed | Trusted credentials, account/resource authority or durable remote work. It is a separate service with its own accepted stack. |
Place each operation where its authority and lifetime fit. A short popup cannot own a long export merely because it started it. Define where completion is stored, how another UI discovers progress, and what happens if the user closes the surface or the worker restarts. A local-only extension does not automatically need a backend or account system.
Preserve the chosen implementation
For existing work, use its framework, package manager, formatter and test runner. For an unresolved new project, compare the smallest sufficient approach: plain bundled extension entrypoints, WXT's entrypoint conventions or CRXJS's Vite integration. Choose from required browsers, framework compatibility, build control, maintenance and team familiarity. React alone does not settle the extension framework.
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.
- 8d ago Changed · +10 lines a57b5afdcd3f
- 11d ago First seen · 52 lines · 46 tokens per session scan A 4b808944a234
browser-extension-development is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 1,035 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 2026-10-24.
Other skills, from other repositories
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…
browser-skill
Use a real web browser - read pages through their accessibility tree, click and type by reference, call the tools a site offers (WebMCP), and hand the page to the owner for logins, CAPTCHAs and final confirmations.