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-securitygit 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-security)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/browser-extension-security"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/browser-extension-security/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-security"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/browser-extension-security.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 | $0.00041 | $0.01057 |
| Opus 5.5 | $0.00016 | $0.00423 |
| Sonnet 5.5 | $0.00008 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
browser-extension-security 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect browser privileges to permitted operations
Trace what the feature reads, changes or sends, on which sites, for which actor and after which user action. Review source and built manifest together. A manifest grant permits the extension to use browser capabilities; it does not authorize every message, remote resource or backend account operation. Apply this method within the requested design, implementation or review scope.
Derive grants from behavior
Build a small operation-to-access map. Check the actual API methods, accessed fields and supported Chrome versions in primary documentation instead of assigning a permission from a namespace name.
| Intended behavior | Decision to establish |
|---|---|
| Act on the current page after the user invokes the extension | Can temporary activeTab access and the needed API permission satisfy it? What happens on navigation or a restricted page? |
| Run automatically on known sites | Which content-script matches and host/API grants does the feature really require? |
| Enable an optional site integration | Can runtime optional host access preserve useful behavior when the user declines or revokes it? |
| Fetch from a backend in an extension context | Which fixed origins/endpoints need host access, and what separate application authorization applies? |
activeTab is temporary access following a qualifying invocation; merely querying the active tab or opening a popup URL in a test is not the same event. Broad host access can be necessary for a user-selected all-sites feature, but must be justified by that behavior and its disclosure. Never add it as scaffold convenience or remove it without preserving an explicitly required capability.
Read permission and message boundaries for implementation and audit details. Verify denied/revoked access and the installed permission warning, not only the happy path. Recheck the production manifest after framework generation.
Treat each context according to its trust
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 · +6 lines 51e121eca998
- 11d ago First seen · 53 lines · 41 tokens per session scan A cd012f987cfc
browser-extension-security is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed 8d ago), licensed MIT. It adds 41 tokens to every session and 1,057 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.