dream-state

dream-state is a command for Claude Code from KumihoIO/kumiho-plugins. It costs 15 tokens per session (757 once invoked), scanned A, original, MIT.

A command that reviews and organizes stored memories by finding patterns, adding metadata, identifying duplicates, and marking low-value entries for retirement. A dry-run option can assess the memories without changing them.

In plain words
What is it for?
Use it after many sessions, when searches become cluttered, periodically for memory maintenance, or when you want to organize saved memories.
Why use it?
It helps keep a growing memory store relevant when it becomes noisy or repetitive. Safety limits protect published memories and restrict how much can be retired at once.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code; built for openclaw.

Part of the kumiho-memory plugin — 1 skill, 5 commands, 7 hooks, 1 MCP server shipped together

Good fit Use it after many sessions, when searches become cluttered, periodically for memory maintenance, or when you want to organize saved memories.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kumihoio/kumiho-plugins/dream-state
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.

Clone the repo
git clone --depth 1 https://github.com/KumihoIO/kumiho-plugins

Made for: Claude Code.

Or install kumiho-memory, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 7 hooks, 1 MCP server.

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-state

README.md
[![agentmods](https://agentmods.dev/badge/commands/kumihoio/kumiho-plugins/dream-state/github.svg)](https://agentmods.dev/commands/kumihoio/kumiho-plugins/dream-state)
Your own site
<a href="https://agentmods.dev/commands/kumihoio/kumiho-plugins/dream-state"><img src="https://agentmods.dev/badge/commands/kumihoio/kumiho-plugins/dream-state/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.

agentmods 80×15 button for dream-state

Your own site · 80×15
<a href="https://agentmods.dev/commands/kumihoio/kumiho-plugins/dream-state"><img src="https://agentmods.dev/badge/commands/kumihoio/kumiho-plugins/dream-state.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 757 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 $0.00015 $0.00757
Opus 5 $0.00008 $0.00378
Sonnet 5 $0.00003 $0.00151
Haiku 4.5 $0.00002 $0.00076

Measured 9d ago against content hash 725f738af495, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dream-state 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.

claude/commands/dream-state.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dream State

Trigger the Dream State consolidation pipeline. This mirrors biological sleep-phase memory processing: it replays recent memories, extracts patterns, enriches metadata, and deprecates low-value or redundant entries — all under conservative safety guards.

When to suggest this to the user

  • After a heavy burst of activity (many sessions in a short period)
  • When memory recall starts returning noisy or redundant results
  • Periodically (e.g., end of week) as memory hygiene
  • When the user asks to "clean up" or "organize" their memories

Steps

  1. Explain what Dream State does in plain language:

    "Dream State reviews your stored memories — scoring relevance, flagging duplicates, adding missing tags, and identifying connections between memories. It won't delete anything important: published items are protected, and there's a hard cap on how much can be deprecated in one run."

  2. Check if the user passed --dry-run as an argument. If so, mention that this will be assessment-only — no changes will be applied.

  3. Call the consolidation tool:

    kumiho_memory_dream_state(
      dry_run = <true if --dry-run, false otherwise>
    )
    
  4. When the run completes, summarize the report for the user:

    • How many memories were assessed
    • How many were deprecated (and why)
    • How many got metadata enrichments or new tags
    • How many new relationships were discovered
    • Duration

    Example:

    "Dream State reviewed 42 memories. Deprecated 3 duplicates, enriched tags on 7 items, and found 5 new connections between related memories. Everything else was kept as-is."

  5. If the circuit breaker triggered (>50% deprecation capped), mention it:

    "The safety circuit breaker kicked in — the consolidation wanted to deprecate more than 50% of assessed memories, which usually means something's off. I capped it and kept the rest. You may want to review manually."

Automated scheduling

Dream State runs best on a schedule (nightly or weekly). Claude Code doesn't have built-in cron, but you can set it up at the OS level:

Read the full file on GitHub · 90 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. 9d ago First seen · 90 lines · 15 tokens per session scan A 725f738af495

Subscribe to this mod's changes

dream-state is a command published in the GitHub repository KumihoIO/kumiho-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 757 once invoked, about $0.0001 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.