ideate

An admission process for large, unproven ideas. It researches the idea using original sources, compares it with existing project records, and adds an independent challenge before recording whether the idea survives.

In plain words
What is it for?
Use it when an expensive or uncertain idea needs evidence, comparison with prior decisions, and adversarial review before being accepted or rejected.
Why use it?
It helps expose weak assumptions before an idea leads to detailed plans, specifications, and code branches.

Command

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/intentdriven/abcd/ideate
Clone the repo
git clone --depth 1 https://github.com/intentdriven/abcd
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,871 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 $0.00050 $0.01871
Opus 5 $0.00025 $0.00936
Sonnet 5 $0.00010 $0.00374
Haiku 4.5 $0.00005 $0.00187

Measured yesterday against content hash f441e72d2675, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ideate 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.

commands/ideate.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/abcd:ideate — the idea-admission gauntlet

An exciting idea is cheapest to kill in its first hour and most expensive to kill after it has minted intents, specs, and branches. This runs the admission interview and records the outcome.

Ideate is optional and never a gate. Nothing requires it: /abcd:capture and /abcd:intent work exactly as they always do, and skipping ideate is not a mistake to warn about. Reach for it when an idea is big and unproven enough that being wrong about it would be expensive.

The binary does no judging. The three legs below are yours to run. abcd ideate record validates what they produced, proves every citation names a real record, and writes the durable verdict. It never fetches a source and never forms an opinion.

The three legs, in order

The order is not cosmetic — each leg changes what the next one is looking at — and abcd ideate record refuses a payload whose legs are missing or out of order.

Leg 1 — Primary-source research

Research the idea's load-bearing claims: the ones that, if false, take the idea with them. For each, open the primary source — the paper, the specification, the API reference, the original data — and check the claim against it.

A secondary citation is not a check. In the run this protocol comes from, three secondary-source claims were falsified once the primary was opened, one of them an extraction artefact that no source ever said.

Produce, for each claim: the claim, the primary source (a URL or a document reference), and the finding — verified, falsified, or unverifiable. An honest unverifiable is a result; a missing source is not, and the binary refuses a claim that names none.

Leg 2 — Record grill

Read the existing record before anything else is decided — the brief, the intents in every bucket (drafts/, planned/, shipped/, disciplines/, superseded/), the ADRs, the principles, the research notes under .abcd/development/research/notes/, and the decision log .abcd/work/DECISIONS.md. Answer one question: does an entry already cover, contradict, or supersede this idea?

Read the full file on GitHub · 162 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. yesterday First seen · 162 lines · 50 tokens per session scan A f441e72d2675

Subscribe to this mod's changes

ideate is a command published in the GitHub repository intentdriven/abcd (3 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,871 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.

Related

Other commands, from other repositories