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-addgit 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 | $0.00018 | $0.00778 |
| Opus 5 | $0.00009 | $0.00389 |
| Sonnet 5 | $0.00004 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
extension-add 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a new feature surface to the current extension project. The user said: $ARGUMENTS
Parse arguments
- First argument: feature type, one of:
sidebar,popup,content-script,background,newtab,options,devtools - Second argument (optional): framework, one of:
react,vue,svelte,preact,vanilla. Default: detect from existing project, fall back toreact
Steps
-
Validate the project
- Check that
src/manifest.jsonexists - Read it to understand what's already configured
- Detect the framework from existing dependencies in
package.json
- Check that
-
Get the reference pattern If MCP tool
extension_add_featureis available, use it. It returns the exact manifest additions, files to create, and reference template.If MCP tool
extension_templates(action: "source") is available, read the reference template source to get real implementation patterns. -
Update manifest.json Add the required fields to
src/manifest.json. Use the extension.dev cross-browser format:Feature Chromium Firefox Sidebar "chromium:side_panel": {"default_path": "sidebar/index.html"}+"chromium:permissions": ["sidePanel"]"firefox:sidebar_action": {"default_panel": "sidebar/index.html"}Popup "chromium:action": {"default_popup": "action/index.html"}"firefox:browser_action": {"default_popup": "action/index.html"}Content script "content_scripts": [{"matches": ["<all_urls>"], "js": ["content/scripts.ts"]}]Same Background "background": {"chromium:service_worker": "background.ts", "firefox:scripts": ["background.ts"]}Same (prefixed) New tab "chrome_url_overrides": {"newtab": "newtab/index.html"}Same Options "options_ui": {"page": "options/index.html", "open_in_tab": true}Same DevTools "devtools_page": "devtools/index.html"Same
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 · 64 lines · 18 tokens per session scan A 7e35a00e28aa
extension-add is a command published in the GitHub repository extensiondev/mcp (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 18 tokens to every session and 778 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.