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.
npx skills add momentmaker/kaijutsu --skill dreamgit clone --depth 1 https://github.com/momentmaker/kaijutsuWrote 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.
[](https://agentmods.dev/skills/momentmaker/kaijutsu/dream)<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>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 | $0.00110 | $0.02720 |
| Opus 5 | $0.00055 | $0.01360 |
| Sonnet 5 | $0.00022 | $0.00544 |
| Haiku 4.5 | $0.00011 | $0.00272 |
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.
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
unstuckreaches its walk-away level — a fresh re-entry can manually invokedreamon 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-checkfor cost-tier classification orpolishfor 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.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 1.8 KB
- evals/fixtures/sample.diff 1.2 KB
- prompts/base/fit.md 2.2 KB
- prompts/base/gaps.md 2.2 KB
- prompts/base/honest.md 1.7 KB
- prompts/base/wild.md 2.3 KB
- prompts/extras/adversary.md 2.2 KB
- prompts/extras/inverse.md 2.3 KB
- prompts/extras/status-quo.md 2.4 KB
- prompts/extras/time.md 2.6 KB
- prompts/synthesizer.md 1.9 KB
- README.md 2.2 KB
- skill.yaml 637 B
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.
- 7d ago First seen · 222 lines · 0 tokens per session scan A c8db16b2002d
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.
Other skills, from other repositories
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".