monstrare

monstrare is a skill for Claude Code from S-Nakamur-a/conductor. It costs 139 tokens per session (3,742 once invoked), scanned A, original, MIT.

A change-explanation tool that turns a branch's code changes into a readable page with diagrams and short text. It groups changes by topic and shows flows, sequences, before-and-after states, or decision paths.

In plain words
What is it for?
It helps document changed files, trace calls between code areas, create a story JSON file, check that every changed file is covered, and publish the result as an Artifact.
Why use it?
It helps reviewers understand how a change works without reading every diff line first, while still identifying concerns that should or should not block approval.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable.

Part of the conductor plugin — 5 skills, 1 MCP server shipped together

Good fit It helps document changed files, trace calls between code areas, create a story JSON file, check that every changed file is covered, and publish the result as an Artifact.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/s-nakamur-a/conductor/monstrare
Install

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.

Any agent
npx skills add S-Nakamur-a/conductor --skill monstrare
Clone the repo
git clone --depth 1 https://github.com/S-Nakamur-a/conductor

Made for: Claude Code.

Or install conductor, the plugin that ships this one along with the rest of its 5 skills, 1 MCP server.

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 monstrare

README.md
[![agentmods](https://agentmods.dev/badge/skills/s-nakamur-a/conductor/monstrare/github.svg)](https://agentmods.dev/skills/s-nakamur-a/conductor/monstrare)
Your own site
<a href="https://agentmods.dev/skills/s-nakamur-a/conductor/monstrare"><img src="https://agentmods.dev/badge/skills/s-nakamur-a/conductor/monstrare/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 monstrare

Your own site · 80×15
<a href="https://agentmods.dev/skills/s-nakamur-a/conductor/monstrare"><img src="https://agentmods.dev/badge/skills/s-nakamur-a/conductor/monstrare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,742 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 $0.00139 $0.03742
Opus 5.5 $0.00056 $0.01497
Sonnet 5.5 $0.00028 $0.00748
Haiku 4.5 $0.00014 $0.00374

Measured yesterday against content hash 6c6500d2ef2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

monstrare 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/monstrare.py, scripts/test_monstrare.py), 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/conductor/skills/monstrare/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

monstrare

変更を主題に分け、主題ごとに「その変更の仕組みが一目で分かる図」を描いたページを作る。 読む人は全ての diff を読まなくても、何がどう繋がって動くようになったかを掴める。 全ての変更行を説明する検査は revidere の役目で、ここではしない。代わりに、変更したファイルが 1 つ残らずどれかの主題に入っていることだけをスクリプトが検査する。

$ARGUMENTS

引数にベース (origin/main など) があれば、手順 1 で --base に渡す。

手順

スクリプトは python3 "${CLAUDE_SKILL_DIR}/scripts/monstrare.py" で走らせる (以下 monstrare.py)。 同じプラグインの revidere のスクリプトを借りて動くので、revidere の dir も要る。 スクリプトは利用者の index や作業ツリーに何も書かない。自分で差分を読むときも git diff-index -p -M を使う。

  1. 一覧を作る。 monstrare.py prepare [--base <ref>] をリポジトリの中で走らせる。 1 行目に作業 dir (毎回 $TMPDIR の下に新しく作られる) が、続いて範囲と変更ファイルの一覧が出る。 exit 2 はベースが決められない等の失敗、exit 3 は差分が無い。どちらも出た文をそのまま利用者に伝えて終える。
  2. 読む。 今のブランチ以外を読むときは git worktree add で作業コピーを作らない。作業ツリーが clean なら git switch で切り替えて回し、終わったら戻す。出た範囲のとおり git diff-index -p -M <base> を走らせ、 変更されたファイルと、図にする流れの呼び出し元・呼び出し先まで読む。一覧にあって差分に出ないパスは 未追跡の新規ファイルなので中身を読む。図は「どこから呼ばれ、どこへ渡るか」まで読まないと描けない。
  3. 書く。 下の「主題と図の規則」に従った JSON を <作業dir>/story.json に書く。
  4. 検査する。 monstrare.py check <作業dir>。
    • exit 0 なら次へ。
    • exit 1 は、どの主題にも入っていないファイルがある。出たファイルを、扱っている主題の files に足すか、 新しい主題を作って story.json を直し、もう一度 check。2 回直しても残るなら次へ進む (ページに残りが出る)。
    • exit 2 は story.json が読めないか、欄が欠けているか、指したパスや行が差分に無い。名指しされた所を直して もう一度 check。2 回直しても通らなければ、出た文を利用者に伝えて終える。
  5. ページにする。 monstrare.py render <作業dir> が <作業dir>/story.html を書いてパスを出す。 render も story.json を検査し直すので、手順 6 で直したあとも check を経ずに render してよい。
  6. 見る。 ブラウザを操作できるツールがこのセッションにあれば、story.html を開いてページ全体を 1 枚だけ撮る (file: を開けないツールなら、作業 dir で python3 -m http.server --bind 127.0.0.1 を裏で起こして開き、撮ったら止める。 --bind を外すと、未コミットの変更を含む diff が LAN から読める)。 図の文字のはみ出し・重なり・消えた文字を 1 回だけ直して render し直す。撮り直しはしない。ツールが無ければ飛ばす。
  7. 出す。 ページには変更したコードの抜粋がそのまま載る。そのことを利用者に 1 行で伝えてから、 Artifact ツールで story.html を publish し、リンクを返す。ツールが作業 dir のファイルを読めないと断ったら、 このセッションが読める場所 (scratchpad など) へコピーして、そちらを publish する。Artifact ツールが無いセッションなら、 使えないと伝えて story.html のパスを返す。

コードへのリンクは、origin が GitHub で、指す側のコミットが origin に push 済みのときだけ付く。

Read the full file on GitHub · 151 lines

Files

What ships with it

2 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. yesterday Changed · -10 lines · -14 tokens per session 6c6500d2ef2a
  2. 2d ago First seen · 161 lines · 153 tokens per session scan A 2bbf95e512f8

Subscribe to this mod's changes

monstrare is a skill published in the GitHub repository S-Nakamur-a/conductor (2 stars, last pushed 2d ago), licensed MIT. It adds 139 tokens to every session and 3,742 once invoked, about $0.0006 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 2026-11-04.

Related

monstrare compared with skills from other repositories

monstrare next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
monstrareS-Nakamur-a/conductorSkill22d agoMITA139Claude Code
code-simplifierValorVie/custom-skillsSkill55d agoMITA41Codex
codebase-designValorVie/custom-skillsSkill55d agoMITA57Codex
improve-codebase-architectureValorVie/custom-skillsSkill55d agoMITA32Claude Code, Codex
code-reviewValorVie/custom-skillsSkill55d agoMITA94Codex
code-reviewDonchitos/Claude-Code-Game-StudiosSkill36k19d agoMITA20Claude Code
tech-debtDonchitos/Claude-Code-Game-StudiosSkill36k19d agoMITA25Claude Code