visual-plan

visual-plan is a skill for Claude Code from patrickdappollonio/claude-plugins. It costs 102 tokens per session (4,545 once invoked), scanned A, original, MIT.

A local browser-based document for reviewing an implementation plan. It turns a Markdown plan into a page with diagrams, code differences, styled sections, live updates, and a way to leave comments.

In plain words
What is it for?
Use it to review architecture, database structure, or API changes visually, and to collect feedback on the proposed work.
Why use it?
It makes technical plans easier to understand and discuss before code is changed. It also highlights plans that diagnose a problem without explaining what will be done next.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: names the AskUserQuestion tool; mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the visual-docs plugin — 2 skills shipped together

Good fit Use it to review architecture, database structure, or API changes visually, and to collect feedback on the proposed work.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add patrickdappollonio/claude-plugins
Claude Code
/plugin install visual-docs

Made for: Claude Code.

Or install visual-docs, the plugin that ships this one along with the rest of its 2 skills.

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.

agentmods badge for visual-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/visual-plan/github.svg)](https://agentmods.dev/skills/patrickdappollonio/claude-plugins/visual-plan)
Your own site
<a href="https://agentmods.dev/skills/patrickdappollonio/claude-plugins/visual-plan"><img src="https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/visual-plan/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.

agentmods 80×15 button for visual-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/patrickdappollonio/claude-plugins/visual-plan"><img src="https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/visual-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,545 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00102 $0.04545
Opus 5.5 $0.00041 $0.01818
Sonnet 5.5 $0.00020 $0.00909
Haiku 4.5 $0.00010 $0.00455

Measured 21d ago against content hash bd0fbe97708e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

visual-plan 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 21d ago.

The scan reads SKILL.md. This mod also ships 20 executable files (server/assets/app.js, server/assets/vendor/diff2html.min.js, server/assets/vendor/graphre.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/visual-docs/skills/visual-plan/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Plan

Turn a plan into an interactive document the user reviews in their browser, served entirely from their machine. The plan is a plain markdown file — the bundled server renders it with diagrams, diffs, and styled blocks, live-reloads as you edit it, and collects the user's comments for you to read back.

A plan says what we will do. A recap explains what changed; a plan explains what is wrong and what we will do about it. A section that diagnoses a problem and stops is the plan's most common failure — the reader finishes it asking "so what?" — and the linter flags it (document-quality §2b).

Before anything else, fix who you're writing for: the CEO of the company — a tech-savvy non-developer. Not a fellow engineer, not the person who wrote the code, and not someone who will ever open the repo. This shapes every sentence you write. They decide based on business logic — what changes, why it's worth it, what could go wrong — so explain behavior in plain language and reach for code only when the reader must see it to decide. The linter warns when plain-language sections name code symbols, and those findings must be fixed like any other.

Acknowledge first, then work quietly. Before you do anything else, reply with one short sentence that acknowledges the request and says you're gathering what you need — e.g. "Got it — let me dig into the code and put together a visual plan for the rate-limiting change." This is the one message the user should get up front; never jump straight into tool calls with no reply. Then spend your tokens on the document, not on narrating: do the research and inventory silently — no step-by-step play-by-play, no restating what you found — and surface next with the link (once served) and a one-line pointer. Put the budget you'd spend narrating into the plan's coverage instead.

The sequence — do every step, in order; the last two are the ones agents skip:

  1. Research the change and write the plan file.
  2. Inventory it (silently).
  3. Lint it and fix every finding — required, not optional (§3).
  4. Self-review the rendered document — required (§3): re-read it top to bottom against your inventory before anyone else sees it.
  5. Serve it and hand over the link.
  6. Read and act on comments — then back to 3 and 4 for every edit.

Every write runs write → lint → verify — the first draft and every revision. After an edit, do not serve, share, or say "done" until the linter is clean on that file and you have re-read the changed sections against its closing reminder. Revisions are where agents skip this.

Read the full file on GitHub · 175 lines

Files

What ships with it

31 files 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.

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.

  1. 21d ago Changed bd0fbe97708e
  2. 1mo ago Changed · -178 lines 128bf96d5397
  3. 2mo ago First seen · 353 lines · 102 tokens per session scan A cbf705d8aedb

Subscribe to this mod's changes

visual-plan is a skill published in the GitHub repository patrickdappollonio/claude-plugins (9 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 4,545 once invoked, about $0.0004 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.

Related

visual-plan compared with skills from other repositories

visual-plan next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
visual-planpatrickdappollonio/claude-pluginsSkill9yesterdayMITA102Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code