workflow-ideation

workflow-ideation is a skill for Claude Code, Codex from Kastalien-Research/thoughtbox. It costs 33 tokens per session (1,128 once invoked), scanned A, original, MIT.

A structured evaluation of whether a proposed software idea is worth implementing before writing code, specifications, or architecture decisions.

In plain words
What is it for?
Use it to examine an idea through four questions, while checking related accepted architecture decisions and past learnings for relevant context.
Why use it?
It makes the expected outcome, project fit, and opportunity cost explicit before engineering time is committed.

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/workflow-ideation
Any agent
npx skills add Kastalien-Research/thoughtbox --skill workflow-ideation
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 workflow-ideation

README.md
[![agentmods](https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/workflow-ideation.svg)](https://agentmods.dev/skills/kastalien-research/thoughtbox/workflow-ideation)
Your own site
<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/workflow-ideation"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/workflow-ideation.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,128 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 5.1 $0.00033 $0.01128
Opus 5 $0.00016 $0.00564
Sonnet 5 $0.00007 $0.00226
Haiku 4.5 $0.00003 $0.00113

Measured 6d ago against content hash 8e5b1759ce8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

workflow-ideation 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 6d 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/workflow-ideation/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluate whether to proceed with implementing: $ARGUMENTS

Purpose

You are executing Stage 1 (Ideation) of the development workflow. Your job is to determine whether this idea is worth the engineering investment by asking four structured questions. You do NOT write code, specs, or ADRs — you produce a decision.

Process

Step 1: Gather Context

Before asking the questions, gather existing context that might already contain answers:

  1. Check accepted ADRs for prior decisions in this domain:

    ls .adr/accepted/ 2>/dev/null
    

    Read any ADRs that relate to the idea's domain. Note whether their reasoning still holds.

  2. Check compound learnings for prior experience: Search for relevant learnings in knowledge stores, agent memory, and previous reflections.

Present a brief summary of what you found before proceeding to the questions.

Step 2: Ask the Four Questions

Work through these questions with the user. For each question, present your analysis based on the context gathered, then ask the user to confirm, revise, or expand.

Q1: Desired Outcomes

What outcomes are we striving to achieve by implementing this idea? What outcome is this idea "proposed instrumentation" for achieving?

Present your understanding of what the user hopes to accomplish. Be specific — "improve performance" is not an outcome; "reduce API response time from 2s to 200ms for the /search endpoint" is.

Q2: Realistic Outcomes

What outcomes can we reasonably determine we will ACTUALLY get if we implement this? From reading the code, design docs, and any research: what can we say with 90-95% confidence WILL happen?

This is where you do actual investigation. Read relevant code, check dependencies, look at existing implementations. Present what you can say with high confidence about what will actually happen.

Q3: Alignment Check

Compare Q1 answers against Q2 answers, then work through these sub-questions:

3a. Goal Alignment: Is the realistic outcome aligned with our goals? If not, the idea is solving the wrong problem.

Read the full file on GitHub · 113 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. 6d ago First seen · 113 lines · 33 tokens per session scan A 8e5b1759ce8a

Subscribe to this mod's changes

workflow-ideation is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,128 once invoked, about $0.0002 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.