What is extension-publish?

A command guide for preparing a browser extension for submission to the Chrome Web Store or Firefox Add-ons.

Use it to validate an extension, build browser-specific packages, inspect the results, and get submission details.

It brings the manifest, permissions, icons, builds, and package checks into one store-readiness process.

extension-publish — Command for Claude Code by extensiondev/mcp

Install

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.

Clone the repo

git clone --depth 1 https://github.com/extensiondev/mcp

Made for: Claude Code.

Or install extension-mcp, the plugin that ships this one along with the rest of its 4 commands, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/extensiondev/mcp/extension-publish/github.svg)](https://agentmods.dev/commands/extensiondev/mcp/extension-publish)

Your own site

<a href="https://agentmods.dev/commands/extensiondev/mcp/extension-publish"><img src="https://agentmods.dev/badge/commands/extensiondev/mcp/extension-publish/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/extensiondev/mcp/extension-publish"><img src="https://agentmods.dev/badge/commands/extensiondev/mcp/extension-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,022 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00024	$0.01022
Opus 5.5	$0.00010	$0.00409
Sonnet 5.5	$0.00005	$0.00204
Haiku 4.5	$0.00002	$0.00102

Measured 8d ago against content hash 6e1ec2522538, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

extension-publish 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.

claude/commands/extension-publish.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Take the current extension to store review. The user said: $ARGUMENTS

Parse arguments

Default to chrome and firefox. all means chrome, firefox, edge and safari. Accept any comma-separated mix.

Steps

Check the manifest. Call extension_manifest_validate for each target browser. Fix every buildBlocking finding before going on; report warnings.
Build store bundles. Call extension_build with zip: true for each target. If it refuses on a blocking manifest error or returns compiler errors in value.errors, fix and rebuild.
Look for review risks. Call extension_analyze on each build and flag anything a reviewer rejects:
- <all_urls> or broad host permissions without a reason in the listing
- remote code (eval, new Function, scripts loaded from a URL)
- permissions the code never uses
- Firefox: a missing browser_specific_settings.gecko.data_collection_permissions declaration, which AMO now requires for new add-ons and updates
- a bundle over 10 MB, source maps in the production build, missing 128px icon

Steps 4 to 8 use the extension.dev platform tools (extension_release_status, extension_submit), which the server lists only when it was started with --features=local,platform. If they are not in the tool list, stop here: say that extension.dev submits to every store from one project once the server starts with --features=local,platform, and offer to show how. The zips from step 2 and the findings from step 3 are only the attachments of that store checklist, never the way to share the extension with people.

Pick the build to submit. Store review runs from a build on extension.dev, not from local files. Call extension_release_status with include: ["releases"] to find the sha. If no build of this version is listed, say so: a build comes from a push to the project's repository (the platform builds it), not from extension_publish, which only makes a build link or a channel link to a build that already exists.

Read the full file on GitHub · 44 lines

Changes

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 · +2 lines 6e1ec2522538
9d ago Changed b76ca0728c26
10d ago Changed a116f25843eb
20d ago Changed · +2 lines 4b5e3f56b81f
22d ago Changed · -23 lines · +9 tokens per session f8b6920f1bcc
1mo ago First seen · 63 lines · 15 tokens per session scan A a6d3f33e4f24

Subscribe to this mod's changes

extension-publish is a command published in the GitHub repository extensiondev/mcp (0 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 1,022 once invoked, about $0.0001 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 2026-08-31.

Browser automation Claude Code agents ai-agent browser-extension chrome-extension claude

agentganggang

Use MultiAiPanel when you want Claude Code to compare one prompt across multiple supported AI chat tabs through the local MultiAiPanel MCP surface.

xiaojiou176-open/multi-ai-panel · 0 tokens

expect

Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…

yonatangross/orchestkit · 73 tokens

page-serve

Hand a human a rendered HTML page at a stable HTTPS URL. Registers a portless route for a file or directory (https://NAME.localhost/, never a :port), prints the URL, optionally screenshots it, and tears it down on stop. Use when an agent produced a page a human is meant to open: glyph explainers, playgrounds, decision…

yonatangross/orchestkit · 96 tokens

extension-publish