All skills & plugins / Claude community plugins (Anthropic)

html-plan

Write an implementation plan as one interactive HTML page: a tree of claims, each proved by a mockup, state machine, call stack, schema or code, with the decisions you need to make placed where they matter. Use /html-plan <what to build>.

Type: Plugin by Thariq Shihipar
Catalog: Claude community plugins (Anthropic)
Source: anthropics/claude-plugins-community/html-plan (8 files scanned)
Install and details: Agent Skills Index entry
License: MIT (manifest)
Signals: Bundled scriptsSpawns processes

Pre-approved tools

No allowed-tools or tools list in its SKILL.md, command or agent files, so the agent asks before using tools as usual.

Hooks

No hooks.

MCP servers and apps

None.

Bundled code

2 code files (JavaScript):

Network calls

No HTTP or socket call pattern found in the code.

Starts other programs

2 files. First match per file:

html-plan/skills/html-plan/runtime/pack.mjs:7

import { execFileSync } from 'node:child_process';

html-plan/skills/html-plan/runtime/htmlplan.js:382

for (const [re, kind] of rules) { re.lastIndex = i; const mm = re.exec(code); if (mm && mm.index === i) { const t = mm[0]; let cls = kind;

Credentials referenced

No key, token or secret environment variable found in code or MCP config.

Static scan of commit 06ec7b6 on 2026-10-27. Signals are patterns found in the files, not a verdict: a network call can be the whole point of a skill. Read the linked lines before you decide. How the scan works.