Agent skill

Plan Preview

by u-ichi in u-ichi/reviewable-html-workbench

Plan Mode の <proposedplan を出す直前に、計画の段階・依存関係・検証観点を一時HTMLで視覚確認したい時に使う agent-internal skill。Use this agent-internal skill to create a temporary HTML preview for a plan just before presenting…

MITAuto-check passedAgent Workflows

Install Plan Preview

skills CLI
$ npx skills add u-ichi/reviewable-html-workbench --skill plan-preview -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install u-ichi/reviewable-html-workbench plan-preview --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/u-ichi/reviewable-html-workbench.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/plan-preview .claude/skills/plan-preview && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
plan-preview
GitHub stars
298
Used in
1 other repo
Token cost
~1.8k tokens
SKILL.md length
671 words
Files
2
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Plan Mode の <proposedplan を出す直前に、計画の段階・依存関係・検証観点を一時HTMLで視覚確認したい時に使う agent-internal skill。Use this agent-internal skill to create a temporary HTML preview for a plan just before presenting…

  • Works in 3 steps: renderer repo root… → payloadを標準入力で渡して、次を実行する。preview は auto… → 成功したら返却JSONの url を 本文に入れる。推奨表記
  • : final HTML artifacts
  • SKILL.md covers 役割, Role, Strict procedure profile and 言語方針 / Language behavior, plus 12 more sections
  • Calls python3

What it does

Plan Preview is an agent skill from u-ichi/reviewable-html-workbench. Plan Mode の <proposedplan を出す直前に、計画の段階・依存関係・検証観点を一時HTMLで視覚確認したい時に使う agent-internal skill。Use this agent-internal skill to create a temporary HTML preview for a plan just before presenting <proposedplan. plugin配布だけで発火し、ユーザーにCLI実行を求めず、agentが plan-preview CLIでセッション限定URLを作り、本文に自然に差し込む。Triggers: planをグラフィカルに見たい, planを図で確認したい, この計画をHTMLでプレビューして, 計画をHTMLで確認したい, graphical plan review, proposedplanをプレビューして, 計画URLを入れて, preview this plan as HTML, show this plan visually, graphical plan preview, add a plan preview URL…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows, covering Planning, Architecture decision records and HTML artifacts. It works with Python. The repository describes itself as: Claude Code / Codex CLI plugin for generating reviewable HTML documents with preview, inline review comments, and agent feedback ingestion. The licence is MIT.

When your agent uses it

  • : final HTML artifacts
  • Reviewable design docs
  • Comment ingestion
  • Permanent publication

Example prompts

  • “/plan-preview”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. renderer repo root を作業ディレクトリにする。現在のチャットやworkspaceのcwdをrepo rootとして扱わない。
  2. payloadを標準入力で渡して、次を実行する。preview は auto mode を既定にし、Tailscale IPv4 を検出できる場合は Tailscale URL を優先する。
  3. 成功したら返却JSONの url を 本文に入れる。推奨表記

What it can do on your machine

Read from SKILL.md and the folder at commit 60bde37. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Plan Preview loads about 1.8k tokens when it runs. Until then it costs about 191 tokens; SKILL.md has 671 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~191
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from u-ichi/reviewable-html-workbench at commit 60bde37, republished under its MIT licence (© u-ichi). 671 words, ~1,813 tokens.

Download SKILL.mdSave it as .claude/skills/plan-preview/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
plan-preview
description
Plan Mode の `<proposed_plan>` を出す直前に、計画の段階・依存関係・検証観点を一時HTMLで視覚確認したい時に使う agent-internal skill。Use this agent-internal skill to create a temporary HTML preview for a plan just before presenting `<proposed_plan>`. plugin配布だけで発火し、ユーザーにCLI実行を求めず、agentが `plan-preview` CLIでセッション限定URLを作り、本文に自然に差し込む。Triggers: planをグラフィカルに見たい, planを図で確認したい, この計画をHTMLでプレビューして, 計画をHTMLで確認したい, graphical plan review, proposed_planをプレビューして, 計画URLを入れて, preview this plan as HTML, show this plan visually, graphical plan preview, add a plan preview URL, preview the proposed plan。使用しない場面: 通常の最終HTML生成、レビュー可能な設計資料作成、コメント取り込み、恒久成果物の公開、外部アップロードが必要な図式化。Do not use for: final HTML artifacts, reviewable design docs, comment ingestion, permanent publication, or external-upload diagrams.
argument-hint
[plan-preview-payload.json]
strict_procedure
true

plan-preview

役割

Plan Mode で正式な <proposed_plan> を提示する直前に、同じ計画内容を一時HTML previewとして出す。

このskillは利用者が手でコマンドを打つためのものではない。agentが計画本文を組み立てた段階で plan-preview CLIを呼び、返却JSONの url を <proposed_plan> 内へ自然に入れる。

Plan Mode 中の計画確認プレビューは、このskillが優先入口になる。通常の最終HTML成果物を作る visual-html-renderer の document-model.json → render → validate → preview フローへ流さない。

Role

Create a temporary visual preview for a Plan Mode proposal. The user should not run the CLI manually. The agent calls plan-preview, receives a session-scoped URL, and places that URL naturally inside the <proposed_plan> text. During Plan Mode, plan preview requests should route here instead of the final-artifact visual-html-renderer document-model flow.

Strict procedure profile

  • Strictness: strict-procedure。Plan Mode の正式な実装基準は <proposed_plan> 本文であり、previewは判断補助として扱う。
  • Hard gates: 外部サービス送信、shared state変更、永続ファイル出力、skill実行時にhookを動的に追加しない(plugin同梱の静的hook定義は対象外)。
  • Forcing function: plan-preview CLI、TTL付き一時ディレクトリ、Plan preview: <url> 行、失敗時の明示。
  • Completion receipt: <proposed_plan> 内に preview URL または Plan preview: unavailable (<reason>) を含める。

言語方針 / Language behavior

Follow the language of the latest user request for progress updates, preview labels, and the surrounding plan text. 日本語の計画依頼には日本語で、英語の計画依頼には英語で返す。Plan preview: <url> の固定ラベルは互換性のため英語のまま使ってよい。

発火条件

次のいずれかに当たる場合、このskillを使う。

  • ユーザーが plan のグラフィカル表示、図示、preview URL、graphical plan review を求めている。
  • ユーザーが Plan Mode 中に「この計画をHTMLでプレビューして」「計画をHTMLで確認したい」のように求めている。
  • ユーザーが preview this plan as HTML, show this plan visually, graphical plan preview, add a plan preview URL, preview the proposed plan のように求めている。
  • 計画に phase、依存関係、並列worker、検証層、リスク・前提の分岐があり、文字だけでは確認しづらい。
  • plugin利用者の体験として、Plan Mode の本文に自然にURLが入っていることが求められている。

Trigger Conditions

Use this skill when the user asks for a graphical plan view, diagrammed plan, preview URL, preview this plan as HTML, show this plan visually, graphical plan preview, add a plan preview URL, or preview the proposed plan. During Plan Mode, use this skill for plan preview requests instead of visual-html-renderer. Also use it when the plan has phases, dependencies, parallel workers, verification layers, or risk branches that are hard to inspect as plain text.

使用しない場面

  • 最終成果物としてHTMLを生成する場合。これは visual-html-renderer を使う。
  • レビュー可能な設計資料を作り、HTML上のコメントを取り込む場合。これは reviewable-design-doc を使う。
  • planとは無関係な説明資料、恒久公開資料、Notion投稿、外部アップロードが必要な図式化。

Do Not Use For

Do not use this skill for final HTML artifacts, reviewable design documents, comment ingestion, unrelated explainers, permanent publications, Notion posts, or diagrams that require external uploads.

入力payload

agentは <proposed_plan> に入れる直前の計画全文を source_text にそのまま入れる。要約・並べ替え・削除・言い換えは禁止。 受理されるトップレベル key は title / source_text / diagrams だけ。source_text は必須。 diagrams は図が理解を助ける章だけに絞り、各図の after_heading は原文見出しのプレーンテキストと完全一致させる。

json
{
  "title": "Plan Preview",
  "source_text": "<proposed_plan> に出す計画本文 markdown 全文をそのまま",
  "diagrams": [
    {
      "after_heading": "実装手順",
      "title": "処理フロー",
      "mermaid": "flowchart TD\n  plan --> implementation"
    }
  ]
}

外部画像URL、外部asset、機密情報、未確定のsecret値はpayloadに入れない。

Input Payload

Put the full markdown plan text that will appear in <proposed_plan> into source_text exactly as-is. Do not summarize, reorder, delete, or rephrase it for preview generation. The accepted top-level keys are only title, source_text, and diagrams; source_text is required. Use diagrams only for sections where a diagram helps comprehension, and make each after_heading exactly match the plain-text heading in the source plan. Do not include external image URLs, external assets, secrets, or unconfirmed secret values.

Show full SKILL.md (285 more words)Show less

CLI手順

  1. renderer repo root を作業ディレクトリにする。現在のチャットやworkspaceのcwdをrepo rootとして扱わない。
  2. payloadを標準入力で渡して、次を実行する。preview は auto mode を既定にし、Tailscale IPv4 を検出できる場合は Tailscale URL を優先する。
bash
python3 -m scripts.html_review_workbench.cli plan-preview --payload - --ttl 1800 --mode auto
  1. 成功したら返却JSONの url を <proposed_plan> 本文に入れる。推奨表記:
text
Plan preview: http://<tailscale-ip-or-127.0.0.1>:<port>/index.html

Codex sandbox内で Tailscale 検出に失敗する場合は、IPだけを先に取得して HTML_REVIEW_WORKBENCH_TAILSCALE_IP=<tailscale-ip> を渡してから plan-preview --mode auto を起動する。

  1. 失敗しても計画提示を止めない。代わりに短い理由を入れる。
text
Plan preview: unavailable (<short reason>)
  1. stop_command はagent用の後片付け手段であり、通常はユーザーに実行させない。TTLで自動終了する。

CLI Workflow

Run the CLI from the renderer repo root. Pass the plan payload through standard input with python3 -m scripts.html_review_workbench.cli plan-preview --payload - --ttl 1800 --mode auto. On success, insert Plan preview: <url> into <proposed_plan>. On failure, do not block the plan; insert Plan preview: unavailable (<short reason>). The returned stop_command is for agent cleanup and normally should not be handed to the user.

計画本文との関係

  • 正式な実装基準は <proposed_plan> のテキスト。previewだけに存在する項目を作らない。
  • preview URLは本文の冒頭または末尾ではなく、計画の確認に自然な位置へ置く。
  • preview作成のために計画を短縮しない。HTMLは原文と同じ章構成・同じ内容で表示する。
  • HTMLに追加されるのは、agentが diagrams で指定した図だけ。実装範囲や約束をpreviewだけに追加しない。
  • previewの生成に失敗した場合でも、<proposed_plan> 自体は成立させる。

Relationship to the Plan Text

The authoritative implementation plan is the <proposed_plan> text, not the preview alone. Do not add implementation scope that exists only in the preview. Place the URL where it helps review the plan. Do not shorten the plan to make preview generation easier. The HTML preview must show the same section structure and same content as the original plan. The only added content is the diagrams explicitly provided by the agent in diagrams. If preview generation fails, still produce the plan with the unavailable reason.

禁止事項

  • ユーザーに CLI を実行させない。
  • Plan Mode の前にhookを自動追加しない。
  • output/ やplugin cacheにpreview成果物を残さない。
  • 外部アップロードを使わない。
  • Preview Runtime は auto mode で Tailscale IPv4 を優先し、検出できない場合だけ 127.0.0.1 にfallbackする。
  • preview URLを正式な実装基準として扱わない。

Guards

Do not ask the user to run the CLI. Do not auto-add hooks before Plan Mode. Do not leave preview artifacts in output/ or plugin cache. Do not use external uploads. Prefer Tailscale IPv4 in auto mode and fall back to 127.0.0.1 only when needed. Do not treat the preview URL as the authoritative implementation plan.

© u-ichi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/plan-preview of u-ichi/reviewable-html-workbench.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 60bde37

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in u-ichi/reviewable-html-workbench, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Plan Preview next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Plan Preview compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plan Preview this skillu-ichi/reviewable-html-workbench2981 repos~1.8kAutomated safety check: PassMIT
Stitch Upload To Stitchmajiayu000/claude-skill-registry6661 repos~1.1kAutomated safety check: NotesMIT
Plannotator Visual Explainerbacknotprop/plannotator9.2k—~1.7kAutomated safety check: PassApache-2.0
Htmlvspecdisler/pi-agent-observability145—~4.7kAutomated safety check: NotesMIT
Htmlspecdisler/pi-agent-observability145—~3kAutomated safety check: PassMIT
PRP Visual Companion PageWirasm/prp2.3k—~1kAutomated safety check: PassMIT

Similar skills

  • Stitch Upload To Stitch

    majiayu000/claude-skill-registry

    Upload local assets (images, mockups, extracted HTML, design markdown) to a Stitch project.

    666 GitHub starsUsed in 1 repo~1.1k tokens
    Agent WorkflowsAuto-check: notes
  • Plannotator Visual Explainer

    backnotprop/plannotator

    Builds self-contained HTML explainers for plans, pull requests and technical concepts in Plannotator's theme, then opens them in its annotation view.

    9.2k GitHub stars~1.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Htmlvspec

    disler/pi-agent-observability

    Creates a visual engineering implementation plan as a single self-contained HTML page saved to specs/<name.html — the plan authored directly in styled HTML, with one AI-generated diagram image per…

    145 GitHub stars~4.7k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check: notes
  • Htmlspec

    disler/pi-agent-observability

    Creates a text-only engineering implementation plan as a single self-contained HTML page saved to specs/<name.html — the plan authored directly in styled HTML plus a freeform HTML zone where the…

    145 GitHub stars~3k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed
  • Writes a self-contained HTML companion beside a PRP plan or review that shows the diagram, steps, risks, verdict and findings, each item with a stable id.

    2.3k GitHub stars~1k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Writes a self-contained HTML page beside a PRP plan or review that shows the diagram, steps, risks or findings, with a stable id on every item.

    2.3k GitHub stars~990 tokensUpdated 6 days ago
    DevelopmentAuto-check passed

More from u-ichi/reviewable-html-workbench

  • Reviewable Design Doc

    u-ichi/reviewable-html-workbench

    要求・設計・アーキテクチャ・未決事項を整理し、レビュー可能な設計資料HTMLを作りたい時に使う。Use this skill to structure requirements, design, architecture, alternatives, decisions, and unresolved issues into a review-ready HTML design document.

    298 GitHub starsUsed in 1 repo~8.6k tokens
    Auto-check passed
  • Visual HTML Renderer

    u-ichi/reviewable-html-workbench

    HTMLを最終成果物として生成・検証・プレビューしたい時に使う共通レンダラー。Use this shared renderer when the user wants content turned into a final, validated, previewable HTML artifact.

    298 GitHub starsUsed in 1 repo~8.7k tokens
    Auto-check passed

Works with

Questions about Plan Preview

What does Plan Preview do?

Plan Mode の <proposedplan を出す直前に、計画の段階・依存関係・検証観点を一時HTMLで視覚確認したい時に使う agent-internal skill。Use this agent-internal skill to create a temporary HTML preview for a plan just before presenting…. Plan Preview is an agent skill from u-ichi/reviewable-html-workbench. Plan Mode の <proposedplan を出す直前に、計画の段階・依存関係・検証観点を一時HTMLで視覚確認したい時に使う agent-internal skill。Use this agent-internal skill to create a temporary HTML preview for a plan just before presenting <proposedplan.

When should I use Plan Preview?

Plan Preview fits situations like: : final HTML artifacts; reviewable design docs; comment ingestion; permanent publication.

How do I install Plan Preview in Claude Code?

Run `npx skills add u-ichi/reviewable-html-workbench --skill plan-preview -a claude-code`. Or copy the skill folder (skills/plan-preview in u-ichi/reviewable-html-workbench) into .claude/skills/plan-preview in your project. Claude Code loads it when a task matches its description.

How do I install Plan Preview in Codex?

Run `npx skills add u-ichi/reviewable-html-workbench --skill plan-preview -a codex`. Or copy the skill folder (skills/plan-preview in u-ichi/reviewable-html-workbench) into .agents/skills/plan-preview in your project. Codex loads it when a task matches its description.

Can I use Plan Preview in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add u-ichi/reviewable-html-workbench --skill plan-preview -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plan-preview, .gemini/skills/plan-preview, .github/skills/plan-preview and .opencode/skills/plan-preview in your project.

What does Plan Preview need to run?

Going by SKILL.md and its folder, Plan Preview needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Plan Preview access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Plan Preview safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Plan Preview use?

Plan Preview is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Plan Preview use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Plan Preview?

Skills that share tags, products or a category with Plan Preview: Stitch Upload To Stitch (majiayu000/claude-skill-registry, 666 stars), Plannotator Visual Explainer (backnotprop/plannotator, 9.2k stars), Htmlvspec (disler/pi-agent-observability, 145 stars) and Htmlspec (disler/pi-agent-observability, 145 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plan Preview?

u-ichi (a GitHub user) maintains it in u-ichi/reviewable-html-workbench, which has 298 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 10, 2026.

Source: u-ichi/reviewable-html-workbench on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.