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 agentmods add commands/extensiondev/mcp/extension-publishgit clone --depth 1 https://github.com/extensiondev/mcpWhat 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 | $0.00015 | $0.00577 |
| Opus 5 | $0.00008 | $0.00289 |
| Sonnet 5 | $0.00003 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00058 |
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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare the current extension for store submission. The user said: $ARGUMENTS
Parse arguments
Default to both (Chrome + Firefox). If the user specifies chrome or firefox, target only that store.
Steps
-
Validate the manifest If MCP tool
extension_manifest_validateis available, use it with the target browsers. Otherwise, readsrc/manifest.jsonand check:- Has
name,version,description - Has appropriate
manifest_versionfor each target - Permissions are minimal (no unnecessary permissions)
- Has icons (at least 16x16, 48x48, 128x128)
- Has
-
Build for each target browser
npx extension build --browser=chrome --zip npx extension build --browser=firefox --zip -
Inspect the builds If MCP tool
extension_analyzeis available, use it for each browser build. Check:- Total size under 10MB (store limit)
- No source maps in production build
- Has manifest.json in dist
- Has icons
-
Report store readiness
Chrome Web Store
- Zip location:
dist/chrome/<name>.zip - Submit at: https://chrome.google.com/webstore/devconsole
- Checklist:
- manifest_version: 3
- Icons: 128x128 PNG
- Description under 132 characters (for listing)
- Screenshots: 1280x800 or 640x400
- Privacy policy URL (if using sensitive permissions)
Firefox Add-ons (AMO)
- Zip location:
dist/firefox/<name>.zip - Submit at: https://addons.mozilla.org/developers/
- Checklist:
- manifest_version: 2 (recommended for broadest compat) or 3
- No Chrome-only APIs without polyfill
- Source code zip if using a bundler:
npx extension build --browser=firefox --zip --zip-source - AMO requires source code review for minified/bundled code
- Zip location:
-
Flag issues that would cause store rejection:
<all_urls>host permission without justificationactiveTab+scriptingwithout clear use case- Remote code loading (eval, Function constructor, remote scripts)
- Excessive permissions for the extension's functionality
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.
- yesterday First seen · 63 lines · 15 tokens per session scan A a6d3f33e4f24
extension-publish is a command published in the GitHub repository extensiondev/mcp (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 15 tokens to every session and 577 once invoked, about $0.0001 per session on Opus 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.
Other commands, from other repositories
agentganggang
Use MultiAiPanel when you want Claude Code to compare one prompt across multiple supported AI chat tabs through the local MultiAiPanel MCP surface.
build-agent
Build an AI agent on Cloudflare using the Agents SDK.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
adopt-roadmap.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
github-menu-issues-list.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
landing-page-generator.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.