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-deliverygit 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-delivery)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/browser-extension-delivery"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/browser-extension-delivery/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-delivery"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/browser-extension-delivery.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 | $0.00934 |
| Opus 5.5 | $0.00018 | $0.00374 |
| Sonnet 5.5 | $0.00009 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
browser-extension-delivery 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 11d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deliver the reviewed extension artifact
Establish the requested stopping point: readiness assessment, local packaging, upload, review submission or publication. Preparation does not imply authorization for the later actions. Reuse the project's CI, versioning and release authority. Use available general delivery, privacy/security and product expertise for shared decisions; without it, retain artifact traceability, compatible updates, truthful disclosure and controlled promotion using project evidence and current primary sources.
Establish the release candidate
Build the accepted source with locked dependencies and production configuration. Determine the extension's actual browser version field, independently of an npm/package release label. Inspect the generated manifest and full packaged tree, including code/resources from dependencies. An extension store ZIP contains the built extension with manifest.json at its root, not the source repository or its parent build directory.
Use release evidence and automation for packaging and CI details. Keep the tested artifact's identity through promotion; rebuilding after verification can produce a different candidate. Check client data migrations and behavior changes for existing installations, especially permission changes and account/entitlement compatibility. Store delivery and browser update timing are asynchronous; do not promise immediate fleet-wide rollout or downgrade.
Assess the listing and data flow
| Evidence | What to reconcile |
|---|---|
| Functional purpose | Actual extension behavior, advertised capabilities, installation/onboarding and accessible reviewer steps |
| Access requests | Generated grants, necessary site/API scope and user-facing permission justification |
| Data handling | Actual collection, local/off-device processing, recipients, retention and relevant disclosure/consent |
| Assets | Bundled icons and current store dimensions/formats; real screenshots of the candidate rather than placeholders |
| Executable content | Bundled code, CSP, dependencies and the current remotely hosted code rules |
| Commercial behavior | Accurate pricing/entitlement claims and permitted account/payment flows, if the product has them |
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.
- 11d ago First seen · 48 lines · 46 tokens per session scan A 9421e1a32f0d
browser-extension-delivery 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 934 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.