Agent skill

Omm Scan

by oh-my-mermaid in oh-my-mermaid/oh-my-mermaid

Scan codebase architecture and generate/update .omm/ documentation.

MITAuto-check passedDevelopment

Install Omm Scan

skills CLI

$ npx skills add oh-my-mermaid/oh-my-mermaid --skill omm-scan -a claude-code

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

GitHub CLI

$ gh skill install oh-my-mermaid/oh-my-mermaid omm-scan --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/oh-my-mermaid/oh-my-mermaid.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/omm-scan .claude/skills/omm-scan && 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/

Paste into Claude Code

Install the "omm-scan" agent skill from https://github.com/oh-my-mermaid/oh-my-mermaid/tree/main/skills/omm-scan into .claude/skills/omm-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omm-scan", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/oh-my-mermaid/oh-my-mermaid/tree/main/skills/omm-scan

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add oh-my-mermaid/oh-my-mermaid --skill omm-scan -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install oh-my-mermaid/oh-my-mermaid omm-scan --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oh-my-mermaid/oh-my-mermaid.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/omm-scan .agents/skills/omm-scan && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "omm-scan" agent skill from https://github.com/oh-my-mermaid/oh-my-mermaid/tree/main/skills/omm-scan into .agents/skills/omm-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omm-scan", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add oh-my-mermaid/oh-my-mermaid --skill omm-scan -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install oh-my-mermaid/oh-my-mermaid omm-scan --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oh-my-mermaid/oh-my-mermaid.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/omm-scan .cursor/skills/omm-scan && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "omm-scan" agent skill from https://github.com/oh-my-mermaid/oh-my-mermaid/tree/main/skills/omm-scan into .cursor/skills/omm-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omm-scan", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/oh-my-mermaid/oh-my-mermaid.git --path skills/omm-scan

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add oh-my-mermaid/oh-my-mermaid --skill omm-scan -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install oh-my-mermaid/oh-my-mermaid omm-scan --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oh-my-mermaid/oh-my-mermaid.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/omm-scan .gemini/skills/omm-scan && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "omm-scan" agent skill from https://github.com/oh-my-mermaid/oh-my-mermaid/tree/main/skills/omm-scan into .gemini/skills/omm-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omm-scan", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install oh-my-mermaid/oh-my-mermaid omm-scan

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add oh-my-mermaid/oh-my-mermaid --skill omm-scan -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/oh-my-mermaid/oh-my-mermaid.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/omm-scan .github/skills/omm-scan && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "omm-scan" agent skill from https://github.com/oh-my-mermaid/oh-my-mermaid/tree/main/skills/omm-scan into .github/skills/omm-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omm-scan", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add oh-my-mermaid/oh-my-mermaid --skill omm-scan -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install oh-my-mermaid/oh-my-mermaid omm-scan --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oh-my-mermaid/oh-my-mermaid.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/omm-scan .opencode/skills/omm-scan && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "omm-scan" agent skill from https://github.com/oh-my-mermaid/oh-my-mermaid/tree/main/skills/omm-scan into .opencode/skills/omm-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omm-scan", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: omm-scan
GitHub stars: 2.7k
Token cost: ~1.8k tokens
SKILL.md length: 637 words
Files: 1
Skills in repo: 3
Repo updated: Apr 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Scan codebase architecture and generate/update .omm/ documentation.

Works in 5 steps: Check Language → Explore the Codebase → Select Perspectives → …
The user says omm scan
SKILL.md covers Purpose, Prerequisites, Step 0: Check Language and Step 1: Explore the Codebase, plus 5 more sections
Calls npm

What it does

Omm Scan is an agent skill from oh-my-mermaid/oh-my-mermaid. Scan codebase architecture and generate/update .omm/ documentation. Use when the user says "omm scan", "scan architecture", "update architecture", "refresh diagrams".

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Diagrams. It works with Mermaid. The repository describes itself as: Turn complex codebases into clear, navigable architecture diagrams with Claude Code. The licence is MIT.

When your agent uses it

The user says omm scan
Scan architecture
Update architecture
Refresh diagrams

Example prompts

“omm scan”
“scan architecture”
“update architecture”
“/omm-scan”

Requirements

Node.js

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Check Language
Explore the Codebase
Select Perspectives
Generate Perspectives with Recursive Drill-Down
Summarize

What it can do on your machine

Read from SKILL.md and the folder at commit 38ccdb6. 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:
- npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
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

Omm Scan loads about 1.8k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 637 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~44
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 oh-my-mermaid/oh-my-mermaid at commit 38ccdb6, republished under its MIT licence (© oh-my-mermaid). 637 words, ~1,811 tokens.

Download SKILL.mdSave it as .claude/skills/omm-scan/SKILL.md (or your agent's skills folder).

name: omm-scan
description: Scan codebase architecture and generate/update .omm/ documentation. Use when the user says "omm scan", "scan architecture", "update architecture", "refresh diagrams".

omm-scan — Perspective-Based Architecture Scanner

Purpose

Analyze the codebase and generate .omm/ architecture documentation using perspective-driven recursive analysis.

A perspective is a top-level element — a distinct way to look at the architecture.
Each element in a diagram gets analyzed recursively. If it has internal structure, it becomes a child element (subdirectory with its own diagram). If not, it stays a leaf.
The filesystem determines nesting. Element IDs in diagrams match child directory names. The viewer resolves groups from the filesystem.

Prerequisites

bash

command -v omm || npm install -g oh-my-mermaid

If the install fails, tell the user: "Please run npm install -g oh-my-mermaid in your terminal, then try again."

Step 0: Check Language

bash

omm config language

Write field content (description, context, constraint, concern, todo, note) in the configured language. Default is English. Element IDs, directory names, and diagram node IDs are always English kebab-case.

Step 1: Explore the Codebase

Use Glob and Read to understand the project:

Read package.json, pyproject.toml, or equivalent manifests
List top-level directories to identify module boundaries
Read key entry points (main, index, app files)
Look for route definitions, service layers, database connections, external integrations

Step 2: Select Perspectives

From the catalog below, choose which perspectives are meaningful for this codebase.

Perspective Catalog

Perspective	When to create	What it answers
`overall-architecture`	Always	What exists and how pieces relate
`request-lifecycle`	Any server/API	How a request enters and gets handled end-to-end
`data-flow`	Any data processing, DB usage	Where data comes from, transforms, and lands
`dependency-map`	Complex module graph	What depends on what, what's shared
`external-integrations`	External APIs/services	What the system connects to and why
`state-transitions`	Stateful features (frontend or backend)	How state changes and what triggers it
`route-page-map`	Frontend with routing	Page structure and navigation flow
`command-surface`	CLI tools	Command hierarchy and dispatch
`extension-points`	Plugin/extension systems	Extension architecture and registry
`pipeline`	ML/data pipelines	Stage topology and data flow
`orchestration`	Event-driven/queue systems	Publisher, subscriber, broker topology
`storage`	2+ storage systems	Storage topology (DB, cache, queue, object store)

Don't force perspectives that don't exist in the code.

Step 3: Generate Perspectives with Recursive Drill-Down

For each selected perspective, follow this recursive process:

3a. Write the perspective diagram

Element IDs match child directory names. The viewer resolves nesting from the filesystem.

bash

omm write <perspective> diagram - <<'MERMAID'
graph LR
    renderer["Renderer\nsrc/renderer/"]
    renderer -->|"IPC invoke/on"| main-process["Main Process\nsrc/main/"]
    main-process -->|"spawn PTY"| engine-system["Engine System\nsrc/main/engine/"]
    main-process -->|"read/write JSON"| data-store["Data Store\nsrc/main/store.ts"]
    main-process -->|"xterm.js"| terminal-dock["Terminal Dock\nsrc/renderer/src/panel/"]
MERMAID

3b. Write the other 6 fields

Each as a separate omm write command: description, context, constraint, concern, todo, note.

Show full SKILL.md (306 more words)Show less

3c. Recursive drill-down: analyze every element

For every element in the diagram:

Analyze the code it represents (Glob + Read the relevant files/directories)
Write description for every node — no exceptions. This creates the element directory. Optionally write other fields (context, constraint, concern, todo, note) if relevant — Write in the configured language.
bash
```
omm write <perspective>/<element-name> description - <<'EOF'
(what this element does, which files/dirs it covers)
EOF
```
Decide leaf or group:
- Distinct internal components found → write a diagram and recurse deeper (it becomes a group)
- No meaningful sub-components (single file, trivial wrapper, external system) → write remaining fields only (it stays a leaf)

If group — write diagram and recurse:

bash

omm write <perspective>/<element-name> diagram - <<'MERMAID'
graph LR
    (internal elements)
MERMAID

Then repeat step 3c for each element in this diagram.

Example recursion

text

overall-architecture (perspective)
  elements: renderer, main-process, engine-system, data-store, terminal-dock

  → analyze renderer (src/renderer/)
    → finds: App.tsx, components/, hooks/, stores/, world/
    → group → write diagram with: components, stores, world
      → analyze components → 15 .tsx files, no sub-structure → leaf
      → analyze stores → 4 zustand stores → leaf
      → analyze world → OfficeCanvas + PixiJS logic → leaf

  → analyze main-process (src/main/)
    → finds: ipc.ts, auth/, engine/, terminal-session-service.ts, store.ts
    → group → write diagram with: auth, engine, terminal-session
      → analyze auth → auth-service.ts, callback-server.ts → leaf
      → analyze engine → claude-code.ts, codex.ts → leaf

  → analyze data-store (src/main/store.ts)
    → single file → leaf

  → analyze terminal-dock (src/renderer/src/panel/)
    → TerminalDock.tsx, DockManager → leaf

Step 4: Summarize

Report what was created/updated and suggest omm view to view.

Diagram Rules

Element IDs must match the child directory name. Use kebab-case: main-process, data-store, terminal-dock.

Element labels use two-line format: name + file path, separated by \n:

text

main-process["Main Process\nsrc/main/"]
auth-service["Auth Service\nsrc/auth/service.ts"]

Every edge must have a meaningful label: A -->|"why this connection exists"| B
More elements in one diagram means you should recurse deeper.
Use graph LR for most diagrams, graph TD for hierarchies.

Use classDef for visual distinction when helpful:

Style	Color	When to use
`external`	`#585b70`	Third-party services outside your codebase
`concern`	`#f38ba8`	Known risk or bottleneck
`entry`	`#89b4fa`	Entry points (HTTP handler, CLI, queue consumer)
`store`	`#a6e3a1`	Persistent storage (DB, cache, file system)

text

classDef external fill:#585b70,stroke:#585b70,color:#cdd6f4
classDef concern fill:#f38ba8,stroke:#f38ba8,color:#1e1e2e
classDef entry fill:#89b4fa,stroke:#89b4fa,color:#1e1e2e
classDef store fill:#a6e3a1,stroke:#a6e3a1,color:#1e1e2e

General Rules

Write each field as a separate omm write command. Each omm write must be its own Bash tool call.
Do not rewrite elements that haven't changed.
Do not create circular references. A child element must never reference its parent.

Files

Just SKILL.md in skills/omm-scan of oh-my-mermaid/oh-my-mermaid.

Open the folder on GitHubat commit 38ccdb6

Compare with similar skills

Omm Scan 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.

Omm Scan compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Omm Scan this skilloh-my-mermaid/oh-my-mermaid	2.7k	—	~1.8k	Automated safety check: Pass	MIT	6 mo ago
Archify Diagramstt-a1i/archify	82k	—	~2.9k	Automated safety check: Pass	MIT	today
Diagram Designcathrynlavery/diagram-design	49k	1 repos	~7.6k	Automated safety check: Pass	MIT	today
Draw.io Diagram StudioAgents365-ai/drawio-skill	10k	—	~2.4k	Automated safety check: Notes	MIT	today
Pretty Mermaid Rendererimxv/Pretty-mermaid-skills	1.5k	—	~2k	Automated safety check: Pass	MIT	1 mo ago
Archify Diagram BuilderUnclecheng-li/AI_Animation	1.5k	2 repos	~4.1k	Automated safety check: Pass	MIT	6 days ago

Similar skills

Archify Diagrams
tt-a1i/archify
Creates interactive architecture, workflow, sequence, data-flow and lifecycle diagrams as standalone HTML with inline SVG, themes and image or video export.
82k GitHub stars~2.9k tokensUpdated today
DevelopmentAuto-check passed
Diagram Design
cathrynlavery/diagram-design
Creates branded diagrams, from architecture, flowchart and sequence to charts and maps, as self-contained HTML with inline SVG, with import from draw.io, Mermaid and Excalidraw.
49k GitHub starsUsed in 1 repo~7.6k tokens
DevelopmentAuto-check passed
Draw.io Diagram Studio
Agents365-ai/drawio-skill
Creates and edits editable draw.io diagrams from descriptions, code, infrastructure files, SQL and API schemas, with sync, review, test and export tools.
10k GitHub stars~2.4k tokensUpdated today
DevelopmentAuto-check: notes
Pretty Mermaid Renderer
imxv/Pretty-mermaid-skills
Writes and renders Mermaid diagrams as themed SVG, PNG or terminal ASCII and Unicode art with a bundled Node.js CLI that needs no browser.
1.5k GitHub stars~2k tokensUpdated 1 mo ago
DevelopmentAuto-check passed
Archify Diagram Builder
Unclecheng-li/AI_Animation
Builds validated architecture, workflow, sequence, data-flow and lifecycle diagrams as standalone interactive HTML from a small JSON spec, with optional motion and image export.
1.5k GitHub starsUsed in 2 repos~4.1k tokens
DevelopmentAuto-check passed
Mermaid
WH-2099/mermaid-skill
Generate Mermaid diagrams from user requirements. An agent skill from WH-2099/mermaid-skill.
288 GitHub starsUsed in 4 repos~958 tokens
DevelopmentAuto-check passed

Questions about Omm Scan

What does Omm Scan do?

Scan codebase architecture and generate/update .omm/ documentation. Omm Scan is an agent skill from oh-my-mermaid/oh-my-mermaid.omm/ documentation.

When should I use Omm Scan?

Omm Scan fits situations like: the user says omm scan; scan architecture; update architecture; refresh diagrams.

How do I install Omm Scan in Claude Code?

Run `npx skills add oh-my-mermaid/oh-my-mermaid --skill omm-scan -a claude-code`. Or copy the skill folder (skills/omm-scan in oh-my-mermaid/oh-my-mermaid) into .claude/skills/omm-scan in your project. Claude Code loads it when a task matches its description.

How do I install Omm Scan in Codex?

Run `npx skills add oh-my-mermaid/oh-my-mermaid --skill omm-scan -a codex`. Or copy the skill folder (skills/omm-scan in oh-my-mermaid/oh-my-mermaid) into .agents/skills/omm-scan in your project. Codex loads it when a task matches its description.

Can I use Omm Scan 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 oh-my-mermaid/oh-my-mermaid --skill omm-scan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/omm-scan, .gemini/skills/omm-scan, .github/skills/omm-scan and .opencode/skills/omm-scan in your project.

What does Omm Scan need to run?

Going by SKILL.md and its folder, Omm Scan needs the command-line tools its instructions call (npm). Our summary lists: Node.js.

Does Omm Scan access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Omm Scan 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 Omm Scan use?

Omm Scan 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 Omm Scan use?

About 1.8k tokens (SKILL.md is roughly 7.2k 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 Omm Scan?

Skills that share tags, products or a category with Omm Scan: Archify Diagrams (tt-a1i/archify, 82k stars), Diagram Design (cathrynlavery/diagram-design, 49k stars), Draw.io Diagram Studio (Agents365-ai/drawio-skill, 10k stars) and Pretty Mermaid Renderer (imxv/Pretty-mermaid-skills, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Omm Scan?

oh-my-mermaid (a GitHub organization) maintains it in oh-my-mermaid/oh-my-mermaid, which has 2,701 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on April 7, 2026.

Source: oh-my-mermaid/oh-my-mermaid on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Omm Scan

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

omm-scan — Perspective-Based Architecture Scanner

Purpose

Prerequisites

Step 0: Check Language

Step 1: Explore the Codebase

Step 2: Select Perspectives

Perspective Catalog

Step 3: Generate Perspectives with Recursive Drill-Down

3a. Write the perspective diagram

3b. Write the other 6 fields

3c. Recursive drill-down: analyze every element

Example recursion

Step 4: Summarize

Diagram Rules

General Rules

Files

Compare with similar skills

Similar skills

More from oh-my-mermaid/oh-my-mermaid

Related

Questions about Omm Scan