dream

dream is a skill for Claude Code, Codex from momentmaker/kaijutsu. It costs 110 tokens per session (2,720 once invoked), scanned A, original, MIT.

A pre-planning discussion method that examines an idea through eight different perspectives, including hidden assumptions, weak reasoning, time-related changes, and possible misuse.

In plain words
What is it for?
It is for evaluating an open-ended idea before committing to a specification, implementation plan, or major decision.
Why use it?
Ideas can look sound until their assumptions and edge cases are made explicit. Examining them before writing a specification or plan can reveal that the problem or proposed direction needs changing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for evaluating an open-ended idea before committing to a specification, implementation plan, or major decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/momentmaker/kaijutsu/dream
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.

Any agent
npx skills add momentmaker/kaijutsu --skill dream
Clone the repo
git clone --depth 1 https://github.com/momentmaker/kaijutsu

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 dream

README.md
[![agentmods](https://agentmods.dev/badge/skills/momentmaker/kaijutsu/dream.svg)](https://agentmods.dev/skills/momentmaker/kaijutsu/dream)
Your own site
<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/dream"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/dream.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,720 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.02720
Opus 5 $0.00055 $0.01360
Sonnet 5 $0.00022 $0.00544
Haiku 4.5 $0.00011 $0.00272

Measured 7d ago against content hash c8db16b2002d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

dream 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 7d 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.

skills/core/dream/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dream

Pre-implementation interrogation. The user has an idea. Before they spec it, plan it, or commit to it — pressure-test it through 8 lenses.

This is the EARLIEST stage in the kaijutsu pipeline:

dream → spec → plan → implement → polish → ship

Nothing else covers this slot today. brainstorm preset gives you 5 OPTIONS to solve a problem; dream interrogates whether the problem is the right shape in the first place.

When to invoke

  • The user says "what do you think about X?" / "should we do X?" / "is X worth pursuing?"
  • Before any non-trivial spec/plan
  • When the user types /dream <topic>
  • When kaijutsu's unstuck reaches its walk-away level — a fresh re-entry can manually invoke dream on the topic to break the groove (no automatic integration in v0.8.0)
  • Composed by future skills via deps.skills

When NOT to invoke

  • Trivial fix (1-line bug, typo, dependency bump). Dream's lens machinery is overkill for a "should I rename this var?" question.
  • The user has already committed. dream is for OPEN ideas, not retrospective justification.
  • The topic IS already structured (spec exists, plan exists). Use scope-check for cost-tier classification or polish for review-and-fix instead.

vs brainstorm preset

brainstorm preset dream skill
Question shape "Give me 5 ways to solve X" "Should we even pursue X?"
Output options to pick perspectives to weigh
Stage after commitment to solve X before commitment
Lens count 1 prompt per agent 4-8 lenses per agent
Compose with implementation skills downstream spec-driven-development downstream

Both can be useful in sequence: dream first to validate the problem shape, then brainstorm to enumerate solutions. Don't substitute one for the other.

Anti-sycophancy gates (NON-NEGOTIABLE)

Every lens prompt opens with explicit forbid list. The user does not need encouragement. They need real perspective. Dream is worse than useless if it produces validating noise.

Read the full file on GitHub · 222 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. 7d ago First seen · 222 lines · 0 tokens per session scan A c8db16b2002d

Subscribe to this mod's changes

dream is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 2mo ago), licensed MIT. It adds 110 tokens to every session and 2,720 once invoked, about $0.0006 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.