An index of commands for Hypothesis-Driven Development (HDD), a workflow where Architecture Decision Records guide implementation and validation.

Use it to find the overview, initialize a session, move through phases, manage state, and locate the detailed modules.

It makes the available session, research, planning, validation, and decision commands easier to discover.

index — Command for Claude Code by Kastalien-Research: An index of commands for Hypothesis-Driven Development (HDD), a…

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 commands/kastalien-research/thoughtbox/index

Clone the repo

git clone --depth 1 https://github.com/Kastalien-Research/thoughtbox

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/kastalien-research/thoughtbox/index.svg)](https://agentmods.dev/commands/kastalien-research/thoughtbox/index)

Your own site

<a href="https://agentmods.dev/commands/kastalien-research/thoughtbox/index"><img src="https://agentmods.dev/badge/commands/kastalien-research/thoughtbox/index.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,202 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01202
Opus 5	$0.00000	$0.00601
Sonnet 5	$0.00000	$0.00240
Haiku 4.5	$0.00000	$0.00120

Measured yesterday against content hash 57aa900d6242, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

index 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.

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.

apps/web/.claude/commands/hdd/index.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hypothesis-Driven Development (HDD)

Commands for working with the hypothesis-driven development workflow where ADRs are the source of truth, not code.

Core Principle

Code is an implementation artifact. ADRs (Architecture Decision Records) are the source of truth.

Available Commands

Core Workflow

overview

Complete explanation of the hypothesis-driven development approach, workflow phases, and philosophy.

quick-reference

Quick command reference and cheat sheet for the HDD workflow.

Session Management

init

Initialize a new HDD session by creating local workflow state and linking the user-selected tracker only when one is explicitly in scope.

state

State management, checkpoints, and phase transitions.

Phase Commands

research

Phase 1: Research existing ADRs, rejected approaches, and form hypotheses.

stage-adr

Phase 2: Create staging ADR with context, decision, hypotheses, and validation criteria.

validate

Phase 4: Validate hypotheses through automated testing and required manual user testing.

decide

Phase 5: Make accept/reject decision based on validation results and migrate ADRs.

Router + Modules

hdd is a thin orchestrator router.
Focused phase modules live in ./modules/.
State contract: ./state.md

Workflow Summary

Research → 🚦 → Stage ADR → 🚦 → Implement → Validate+Manual → 🚦 → Accept/Reject
   ↓      User      ↓       User       ↓         Testing      User       ↓
docs/adr  Approve staging/  Approve  Code +                  Confirm  docs/adr
rejected          docs/adr          Tests                             or rejected/

🚦 = Required User Approval Checkpoint

User interaction is required at EVERY phase:

After Research - Approve hypotheses
After Staging ADR - Approve implementation plan
During Validation - Perform manual testing
Before Decision - Confirm accept/reject
Before Rejection - Approve rejection (if applicable)

Read the full file on GitHub · 159 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.

yesterday First seen · 159 lines · 0 tokens per session scan A 57aa900d6242

Subscribe to this mod's changes

index is a command published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,202 tokens. 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 2026-09-03.

Planning ai-agents claude claude-code claudecode mcp model-context-protocol

index