The first step of the Midas product-development process: recording a raw product idea and adding a short normalized description. It also initializes the process state and identifies whether the project is new or based on existing work.

Use it when starting a new product or recording its founding idea, then capture the idea, confirm the project mode, and prepare the process for later phases.

It preserves the original idea while creating a stable starting point for later planning, so early wording and decisions are not lost or silently rewritten.

How okuzpe/midas-harness configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to okuzpe/midas-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/okuzpe/midas-harness/main/.agents/skills/idea-intake/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/okuzpe/midas-harness

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/okuzpe/midas-harness/idea-intake/github.svg)](https://agentmods.dev/skills/okuzpe/midas-harness/idea-intake)

Your own site

<a href="https://agentmods.dev/skills/okuzpe/midas-harness/idea-intake"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/idea-intake/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/okuzpe/midas-harness/idea-intake"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/idea-intake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,221 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00058	$0.01221
Opus 5	$0.00029	$0.00611
Sonnet 5	$0.00012	$0.00244
Haiku 4.5	$0.00006	$0.00122

Measured 9d ago against content hash f915ccd9fcea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

idea-intake 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 9d 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/idea-intake/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

idea-intake — Phase 0: capture the idea

Guard + state: <paths.engine>/templates/skill-state-ritual.md (+ AGENTS.md § Safety / Path resolution). Prompt tool: AskQuestion. On Claude Code, fall back to AskUserQuestion if AskQuestion is not wired.

Phase 0 turns a raw, possibly messy idea into a normalized, preserved artifact so the rest of the pipeline has a stable starting point. Preservation is sacred: never rewrite the user's words away — capture them verbatim, then add a normalized layer beside them. Playbook: <paths.engine>/pipeline/0-idea-intake.md.

Precondition: paths.state exists at stage: idea_intake (set by /midas-init). Read it; if Midas is not initialized, direct the user to /midas-init.

Does / Does not

Does	Does not
Preserve raw idea verbatim + add a normalized pitch beside it	Rewrite or “improve” the user's words in the raw block
Confirm `mode` (`greenfield` \| `brownfield`) with the user	Invent audience/metric/non-goals the user never stated
Advance Phase-0 artifacts in `paths.state` (write last)	Run market/arch work or skip to later phases

When NOT

Idea already captured and Phase 0 gate passed → next is /contextualize (track: full only). When track: lite, next is finish Idea+Plan then /plan-sprints — not /contextualize.
Repo has substantial existing code and no Midas state → /midas-adopt (or /midas-init).
User only wants orientation → /midas-status / /midas-help.

Anti-rationalization: do not skip verbatim capture because the idea “sounds simple”; do not infer mode without confirming; mark inferences as assumption, never as fact.

Steps

Capture verbatim. Ask for the idea in their own words (or take what they already gave). Store the raw text unedited in {product}/idea.md under ## Raw idea (preserved verbatim). Append-only — later phases never overwrite it.
Normalize beside the raw capture (<paths.engine>/templates/ → {product}/idea.md):
- one-line pitch (≤ 20 words) a stranger could understand;
- apparent user/audience, problem, hoped-for outcome (rough OK — Phase 1 sharpens);
- non-goals the user already named.
Confirm the mode. Default from paths.state → mode. Confirm via AskQuestion (greenfield | brownfield); if changed, record the correction.
Advance state (write last). Read-modify-write paths.state: list {product}/idea.md under phases.idea_intake.artifacts; set mode if confirmed/changed; refresh updated.

Read the full file on GitHub · 78 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.

9d ago First seen · 78 lines · 58 tokens per session scan A f915ccd9fcea

Subscribe to this mod's changes

idea-intake is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,221 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 2026-08-31.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

midas-harness: Skill for Claude Code