Agent skill

Smallest Test

by greenfield-inc in greenfield-inc/Pane

Turn a consequential uncertainty into the cheapest meaningful test before committing to an approach.

Custom licenceAuto-check passed

Install Smallest Test

skills CLI
$ npx skills add greenfield-inc/Pane --skill smallest-test -a claude-code

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

GitHub CLI
$ gh skill install greenfield-inc/Pane smallest-test --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/greenfield-inc/Pane.git skills-src && mkdir -p .claude/skills && cp -r skills-src/main/src/services/paneChatBundle/skills/smallest-test .claude/skills/smallest-test && 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
smallest-test
GitHub stars
522
Token cost
~665 tokens
SKILL.md length
343 words
Files
1
Skills in repo
35
Repo updated
First seen
Licence
Custom licence

At a glance

Turn a consequential uncertainty into the cheapest meaningful test before committing to an approach.

  • How could we test this?
  • SKILL.md covers Find the uncertainty, Design the test, Run the experiment and Return the learning
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Is this worth building?

What it does

Smallest Test is an agent skill from greenfield-inc/Pane. Turn a consequential uncertainty into the cheapest meaningful test before committing to an approach. Use for "how could we test this?", "is this worth building?", or choosing a small experiment to resolve an assumption.

Its SKILL.md is about 670 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Terminal-first, open-source AI agent manager for any CLI agent (agent agnostic), any OS (mac, windows, linux). The Open-Source Agentic Development Environment for running…

When your agent uses it

  • How could we test this?
  • Is this worth building?
  • Choosing a small experiment to resolve an assumption

Example prompts

  • “how could we test this?”
  • “is this worth building?”
  • “/smallest-test”

What it can do on your machine

Read from SKILL.md and the folder at commit c038a7b. 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

Smallest Test loads about 665 tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 343 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~665

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 343 words (~665 tokens).

“You are an experiment designer. Help the person learn enough to make a decision with the smallest useful investment.”

— opening of SKILL.md by greenfield-inc, Custom licence
name
smallest-test

Read the full SKILL.md on GitHub

Files

Just SKILL.md in main/src/services/paneChatBundle/skills/smallest-test of greenfield-inc/Pane.

Open the folder on GitHubat commit c038a7b

Compare with similar skills

Smallest Test 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.

Smallest Test compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Smallest Test this skillgreenfield-inc/Pane522—~665Automated safety check: PassCustom licence
Uncertainty And UnitsK-Dense-AI/scientific-agent-skills48k1 repos~5.4kAutomated safety check: NotesMIT
Uncertainty Acknowledgmentaiming-lab/MetaClaw3.5k—~208Automated safety check: PassMIT
Meaningful Identifiershashintel/hash1.7k—~308Automated safety check: PassAGPL-3.0
Smallest-Visual DiagramsYeachan-Heo/oh-my-claudecode40k—~885Automated safety check: PassMIT
ML Committee Uncertaintylearningmatter-mit/AtomisticSkills176—~2.3kAutomated safety check: PassMIT

Similar skills

  • Uncertainty And Units

    K-Dense-AI/scientific-agent-skills

    Tracks physical units and propagates measurement uncertainty in scientific calculations using pint and uncertainties.

    48k GitHub starsUsed in 1 repo~5.4k tokens
    Research & ScienceAuto-check: notes
  • Uncertainty Acknowledgment

    aiming-lab/MetaClaw

    A skill your agent uses when you are not sure about a fact, have outdated knowledge, or the question is contested.

    3.5k GitHub stars~208 tokensUpdated 4 mo ago
    AI & LLM EngineeringAuto-check passed
  • Naming guidance for callback parameters and local variables in TypeScript.

    1.7k GitHub stars~308 tokensUpdated today
    DevelopmentAuto-check passed
  • Smallest-Visual Diagrams

    Yeachan-Heo/oh-my-claudecode

    Picks the smallest visual that carries structure when prose alone would not: pseudocode, call tree, component or file tree, Mermaid or diff, and skips it when prose is enough.

    40k GitHub stars~885 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • ML Committee Uncertainty

    learningmatter-mit/AtomisticSkills

    Quantify prediction uncertainty of MACE MLIPs using committee (ensemble) models; flag high-uncertainty structures for DFT verification.

    176 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed
  • Journal Of Risk And Uncertainty

    franklee16/academic-research-skills

    A skill your agent uses when targeting Journal of Risk and Uncertainty (JRU) or deciding whether a decision-under-risk manuscript fits this venue.

    223 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed

More from greenfield-inc/Pane

All 35 skills in this repo
  • Page

    greenfield-inc/Pane

    House standard for any HTML page written for a person. An agent skill from greenfield-inc/Pane.

    522 GitHub stars~759 tokensUpdated today
    Auto-check passed
  • Session Trace

    greenfield-inc/Pane

    Publish an agent session as a readable trace page in Grain, with the story, key moments, every request and step on a timeline, subagents, and the pull requests it opened.

    522 GitHub stars~836 tokensUpdated today
    Auto-check passed
  • Discussion

    greenfield-inc/Pane

    Have an interactive discussion about a topic, approach, feature, or bug without making code changes.

    522 GitHub stars~666 tokensUpdated today
    Auto-check passed
  • Excalidraw PR Diagrams

    greenfield-inc/Pane

    Create Excalidraw diagram JSON files and PR visual overviews that make visual arguments.

    522 GitHub stars~9.4k tokensUpdated today
    Auto-check passed
  • HTML Explainer

    greenfield-inc/Pane

    The house standard for any skill that renders an HTML page for a person to read, covering design tokens, typography, components, diagrams, and quality gates so every generated page shares one calm…

    522 GitHub stars~1.6k tokensUpdated today
    Auto-check: notes
  • Pane Work

    greenfield-inc/Pane

    Answer questions about the user's own work in Pane, read-only.

    522 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

Questions about Smallest Test

What does Smallest Test do?

Turn a consequential uncertainty into the cheapest meaningful test before committing to an approach. Smallest Test is an agent skill from greenfield-inc/Pane. Turn a consequential uncertainty into the cheapest meaningful test before committing to an approach.

When should I use Smallest Test?

Smallest Test fits situations like: how could we test this?; is this worth building?; choosing a small experiment to resolve an assumption.

How do I install Smallest Test in Claude Code?

Run `npx skills add greenfield-inc/Pane --skill smallest-test -a claude-code`. Or copy the skill folder (main/src/services/paneChatBundle/skills/smallest-test in greenfield-inc/Pane) into .claude/skills/smallest-test in your project. Claude Code loads it when a task matches its description.

How do I install Smallest Test in Codex?

Run `npx skills add greenfield-inc/Pane --skill smallest-test -a codex`. Or copy the skill folder (main/src/services/paneChatBundle/skills/smallest-test in greenfield-inc/Pane) into .agents/skills/smallest-test in your project. Codex loads it when a task matches its description.

Can I use Smallest Test 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 greenfield-inc/Pane --skill smallest-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/smallest-test, .gemini/skills/smallest-test, .github/skills/smallest-test and .opencode/skills/smallest-test in your project.

What does Smallest Test need to run?

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

Does Smallest Test 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 Smallest Test 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 Smallest Test use?

Smallest Test has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Smallest Test use?

About 665 tokens (SKILL.md is roughly 2.7k 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 Smallest Test?

Skills that share tags, products or a category with Smallest Test: Uncertainty And Units (K-Dense-AI/scientific-agent-skills, 48k stars), Uncertainty Acknowledgment (aiming-lab/MetaClaw, 3.5k stars), Meaningful Identifiers (hashintel/hash, 1.7k stars) and Smallest-Visual Diagrams (Yeachan-Heo/oh-my-claudecode, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Smallest Test?

greenfield-inc (a GitHub organization) maintains it in greenfield-inc/Pane, which has 522 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 9, 2026.

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