experiment

experiment is a skill for Claude Code, Codex from Kastalien-Research/thoughtbox. It costs 53 tokens per session (1,564 once invoked), scanned A, original, MIT.

A workflow for trying several competing solutions to the same coding problem in separate Git worktrees, which are independent working copies of a repository.

In plain words
What is it for?
Use it to define two to five approaches, have each implemented separately, compare the results, and choose one to merge.
Why use it?
It lets you compare real implementations when you are unsure which approach will work best without mixing their changes together.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/kastalien-research/thoughtbox/experiment
Any agent
npx skills add Kastalien-Research/thoughtbox --skill experiment
Clone the repo
git clone --depth 1 https://github.com/Kastalien-Research/thoughtbox

Made for: Claude Code, Codex.

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 experiment

README.md
[![agentmods](https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/experiment.svg)](https://agentmods.dev/skills/kastalien-research/thoughtbox/experiment)
Your own site
<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/experiment"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/experiment.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,564 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00053 $0.01564
Opus 5 $0.00026 $0.00782
Sonnet 5 $0.00011 $0.00313
Haiku 4.5 $0.00005 $0.00156

Measured 4d ago against content hash 9fa17324ce72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

experiment 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 4d ago.

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.

.agents/skills/experiment/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a parallel experiment: $ARGUMENTS

Purpose

Test multiple competing approaches to the same problem simultaneously. Each approach gets its own git worktree and sub-agent. Results are compared at the end so the best approach can be merged.

This is NOT for parallelizing parts of one plan (use /workflows-work for that). This is for when you genuinely don't know which approach is best and want to try all of them.

Process

Phase 1: Define Tracks (orchestrator does this)

Parse the input (a gap analysis, a list of alternatives, a brainstorm, or a user description) and produce a track list:

TRACK DEFINITION
================
Base branch: <current branch or specified base>

Track A: <name>
  Branch: exp/<slug-a>
  Approach: <1-2 sentence description>
  Files touched: <predicted file list>
  Effort: low | medium | high

Track B: <name>
  Branch: exp/<slug-b>
  ...

[up to 5 tracks]

Conflict check: If two tracks modify the same files in incompatible ways, flag this to the user before proceeding. Parallel experiments must be independent.

Present the track list to the user and wait for confirmation before proceeding.

Phase 2: Create Worktrees

For each track, create a worktree branching from the base:

# From the repo root
git worktree add ../<repo-name>-exp-<slug> -b exp/<slug>

Worktree naming convention: ../<repo-name>-exp-<slug> (sibling to the main repo directory).

Verify all worktrees were created:

git worktree list

Phase 3: Dispatch Sub-Agents (parallel)

Dispatch one sub-agent per track using the Agent tool. All independent tracks run in parallel.

Each sub-agent receives:

  1. Working directory: The worktree path (CRITICAL — sub-agent must cd here)
  2. Track definition: What to implement and why
  3. Source context: Relevant file contents from the base branch (read before dispatching)
  4. Acceptance criteria: What "done" looks like for this track
  5. Instructions:
    • Work ONLY in your assigned worktree directory
    • Write tests for your changes
    • Run tests and report results
    • Commit your work to the worktree's branch
    • Return the structured summary (see format below)

Read the full file on GitHub · 199 lines

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. 4d ago First seen · 199 lines · 53 tokens per session scan A 9fa17324ce72

Subscribe to this mod's changes

experiment is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,564 once invoked, about $0.0003 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

extract-source-sample

Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…

gooseworks-ai/goose-skills · 160 tokens

unity-asmdef

Advise on Unity assembly definitions (asmdef).

Besty0728/Unity-Skills · 15 tokens

okx-cex-earn

Manages OKX Simple Earn (flexible savings/lending), Flash Earn, On-chain Earn (staking/DeFi), Dual Investment (DCD/双币赢), and AutoEarn (自动赚币) via the okx CLI. Use this skill whenever the user wants to check earn balances, browse flash-earn projects, subscribe or redeem earn products, view or set lending rates, monitor…

okx/agent-trade-kit · 274 tokens

metengine-data-agent

Real-time smart money analytics API for Polymarket prediction markets, Hyperliquid perpetual futures, and Meteora Solana LP/AMM pools. 63 endpoints. Pay-per-request via x402 on Solana Mainnet USDC. No API keys.

sendaifun/skills · 57 tokens

carbium

Build on Solana with Carbium infrastructure — bare-metal RPC, Standard WebSocket pubsub, gRPC Full Block streaming (22ms), DEX aggregation via CQ1 engine (sub-ms quotes), gasless swaps, and MEV-protected execution via Jito bundling. Drop-in replacement for Helius, QuickNode, Triton, or Jupiter Swap API.

sendaifun/skills · 78 tokens

pumpfun

Complete PumpFun Protocol guide for building token launches, bonding curves, and AMM integrations on Solana. Covers Pump Program (token creation, buy/sell on bonding curves), PumpSwap AMM (liquidity pools, swaps), fee structures, creator fees, and SDK integration.

sendaifun/skills · 60 tokens