Agent skill

Scout

by 3x-haust in 3x-haust/oh-my-design

Find, inspect and analyze whole-screen references for actual task and visual decisions without implementing.

MITAuto-check passed

Install Scout

skills CLI
$ npx skills add 3x-haust/oh-my-design --skill scout -a claude-code

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

GitHub CLI
$ gh skill install 3x-haust/oh-my-design scout --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/3x-haust/oh-my-design.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/scout .claude/skills/scout && 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
scout
GitHub stars
198
Token cost
~357 tokens
SKILL.md length
174 words
Files
2
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Find, inspect and analyze whole-screen references for actual task and visual decisions without implementing.

  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Scout is an agent skill from 3x-haust/oh-my-design. Find, inspect and analyze whole-screen references for actual task and visual decisions without implementing.

Its SKILL.md is about 360 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: Design cognition loop for Codex, Claude Code, and Pi-compatible agents — frame, diverge, see, reframe. The licence is MIT.

Example prompts

  • “/scout”

What it can do on your machine

Read from SKILL.md and the folder at commit f6a2144. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Scout loads about 357 tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 174 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~357

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 3x-haust/oh-my-design at commit f6a2144, republished under its MIT licence (© 3x-haust). 174 words, ~357 tokens.

Download SKILL.mdSave it as .claude/skills/scout/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
scout
description
Find, inspect and analyze whole-screen references for actual task and visual decisions without implementing.

Scout

Inside an already delegated Scout task, this skill is bootstrap only: follow the injected role, do not spawn another Scout or expand into standalone work.

Read the current brief and protocol/reference-assembly.md. Use the recorded omd ref browse session: choose roots/searches, follow actual links/similarity, inspect whole-screen shots, keep with a reason and rights context. Optional crops supplement the kept parent. Domain and design lanes remain independent; preserve market policy and actual access failures. No guessed evidence or overlay removal.

End at coverage, saturation or native budget with honest debt. Await command completion, not inventory polling. Inspect actual images, publish reference-analysis with browse analysis-set/check, then applicable research and ref apply-set/check. Every requested surface has direct/partial/brief-derived decisions and real gaps. Makers receive selected whole screens plus analysis; blind Eye/Glance receive neither imagery nor rationale. Study rights do not permit asset shipping.

Return receipts, previews, analysis and limitations. A browse success is not research completeness, visual quality or user approval. Do not implement or ask the user to choose references; representative direction choice is a later step.

© 3x-haust, 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/scout of 3x-haust/oh-my-design.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit f6a2144

Compare with similar skills

Scout 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.

Scout compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scout this skill3x-haust/oh-my-design198—~357Automated safety check: PassMIT
Node Inspect Debuggeropenclaw/openclaw392k1 repos~894Automated safety check: PassMIT
Agent Scout Explorerruvnet/ruflo74k2 repos~1.6kAutomated safety check: PassMIT
Bio Crispr Screens Screen QcFreedomIntelligence/OpenClaw-Medical-Skills3.1k—~2.1kAutomated safety check: PassNone
Skill Scoutaffaan-m/ECC276k1 repos~1.1kAutomated safety check: PassMIT
Skill Scoutaffaan-m/ECC276k—~735Automated safety check: PassMIT

Similar skills

  • Node Inspect Debugger

    openclaw/openclaw

    Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.

    392k GitHub starsUsed in 1 repo~894 tokens
    Frontend & DesignAuto-check passed
  • Agent skill for scout-explorer - invoke with $agent-scout-explorer

    74k GitHub starsUsed in 2 repos~1.6k tokens
    Auto-check passed
  • Bio Crispr Screens Screen Qc

    FreedomIntelligence/OpenClaw-Medical-Skills

    Quality control for pooled CRISPR screens. An agent skill from FreedomIntelligence/OpenClaw-Medical-Skills.

    3.1k GitHub stars~2.1k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed
  • Skill Scout

    affaan-m/ECC

    Search existing local, marketplace, GitHub, and web skill sources before creating a new skill.

    276k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Skill Scout

    affaan-m/ECC

    新しいスキルを作成する前に、ローカル・マーケットプレイス・GitHub・Webの既存スキルを検索する。スキルの作成・ビルド・フォーク・検索を行う際に使用。

    276k GitHub stars~735 tokensUpdated yesterday
    Auto-check passed
  • A skill your agent uses when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where screenshots alone are not enough.

    276k GitHub starsUsed in 1 repo~2k tokens
    Game DevelopmentAuto-check passed

More from 3x-haust/oh-my-design

All 10 skills in this repo
  • Figma

    3x-haust/oh-my-design

    Implement an already chosen Figma target faithfully while verifying unrepresented behavior, states and responsive gaps.

    198 GitHub stars~474 tokensUpdated 5 days ago
    Auto-check passed
  • Ultradesign

    3x-haust/oh-my-design

    Design and implement the requested scope through real references, representative direction choice and measured review.

    198 GitHub stars~676 tokensUpdated 5 days ago
    Auto-check passed
  • Audit

    3x-haust/oh-my-design

    Audit current renders and stress coverage, repair real defects and stop under the bound refinement policy.

    198 GitHub stars~335 tokensUpdated 5 days ago
    Auto-check passed
  • Coach

    3x-haust/oh-my-design

    Interpret recurring measured findings and honest trends without turning taste into a skill score.

    198 GitHub stars~192 tokensUpdated 5 days ago
    Auto-check passed
  • Concepts

    3x-haust/oh-my-design

    Dispatch the existing candidate-generation stage from minimal tokens to one authentic direction choice.

    198 GitHub stars~293 tokensUpdated 5 days ago
    Auto-check passed
  • Critique

    3x-haust/oh-my-design

    Review actual current design evidence and rank observable problems without implementing changes.

    198 GitHub stars~318 tokensUpdated 5 days ago
    Auto-check passed

Questions about Scout

What does Scout do?

Find, inspect and analyze whole-screen references for actual task and visual decisions without implementing. Scout is an agent skill from 3x-haust/oh-my-design. Find, inspect and analyze whole-screen references for actual task and visual decisions without implementing.

How do I install Scout in Claude Code?

Run `npx skills add 3x-haust/oh-my-design --skill scout -a claude-code`. Or copy the skill folder (skills/scout in 3x-haust/oh-my-design) into .claude/skills/scout in your project. Claude Code loads it when a task matches its description.

How do I install Scout in Codex?

Run `npx skills add 3x-haust/oh-my-design --skill scout -a codex`. Or copy the skill folder (skills/scout in 3x-haust/oh-my-design) into .agents/skills/scout in your project. Codex loads it when a task matches its description.

Can I use Scout 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 3x-haust/oh-my-design --skill scout -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scout, .gemini/skills/scout, .github/skills/scout and .opencode/skills/scout in your project.

What does Scout need to run?

SKILL.md names no scripts, command-line tools or credentials: Scout is instructions for the agent only.

Does Scout 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 Scout 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 Scout use?

Scout 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 Scout use?

About 357 tokens (SKILL.md is roughly 1.4k 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 Scout?

Skills that share tags, products or a category with Scout: Node Inspect Debugger (openclaw/openclaw, 392k stars), Agent Scout Explorer (ruvnet/ruflo, 74k stars), Bio Crispr Screens Screen Qc (FreedomIntelligence/OpenClaw-Medical-Skills, 3.1k stars) and Skill Scout (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scout?

3x-haust (a GitHub user) maintains it in 3x-haust/oh-my-design, which has 198 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 5, 2026.

Source: 3x-haust/oh-my-design on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.