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.
git clone --depth 1 https://github.com/KumihoIO/kumiho-pluginsWrote 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/commands/kumihoio/kumiho-plugins/dream-state)<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.
<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>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 | $0.00015 | $0.00757 |
| Opus 5 | $0.00008 | $0.00378 |
| Sonnet 5 | $0.00003 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00076 |
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.
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
-
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."
-
Check if the user passed
--dry-runas an argument. If so, mention that this will be assessment-only — no changes will be applied. -
Call the consolidation tool:
kumiho_memory_dream_state( dry_run = <true if --dry-run, false otherwise> ) -
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."
-
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:
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 · 90 lines · 15 tokens per session scan A 725f738af495
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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.