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 KumihoIO/kumiho-plugins --skill dream-stategit 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/skills/kumihoio/kumiho-plugins/dream-state)<a href="https://agentmods.dev/skills/kumihoio/kumiho-plugins/dream-state"><img src="https://agentmods.dev/badge/skills/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/skills/kumihoio/kumiho-plugins/dream-state"><img src="https://agentmods.dev/badge/skills/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 | $0.00053 | $0.00538 |
| Opus 5 | $0.00026 | $0.00269 |
| Sonnet 5 | $0.00011 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
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 5d 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.
What it actually says
Dream State (Codex)
Use the existing kumiho_memory_dream_state MCP tool on Codex's configured
backend. Do not introduce a Python command, change CE/Cloud, or implement
another maintenance engine.
-
Explain briefly that a full cycle can enrich/tag memories and deprecate redundant entries. Assessment can use the backend's configured LLM even in dry-run mode; this is not the keyless
kumiho_memory_consolidate(summary=...)session-summary operation. Local CE routing does not by itself imply a local assessment model. -
For
--dry-run, a preview request, or an ambiguous cleanup request, call:{"dry_run": true, "allow_published_deprecation": false, "max_deprecation_ratio": 0.5}Pass
projectonly when the user supplied a project scope. Never fan out across every project. If the user explicitly requested an applied run, usedry_run: falsewithout an extra confirmation loop. Adding or testing this skill is not permission to run maintenance on real memories. -
Keep published-item protection enabled and the deprecation cap at 0.5 or a stricter requested value. Do not turn on
maintenance_llm, change providers, pass an API key, or raise the cap to get past an error. Reuse existing SDK-managed configuration; no credentials in chat or arguments. -
Summarize the returned assessed/deprecated/enriched/linked counts, duration, warnings, circuit-breaker status, and report kref when present. Do not invent counts, equate deprecation with permanent deletion, or promise that nothing important can ever change. Distinguish preview from applied work.
-
If the configured assessment model or memory backend is unavailable, report the actual limitation and stop that run. Do not substitute another backend or silently repeat a potentially costly cycle. A user who only wants a session summary can instead request keyless consolidation.
Do not schedule this automatically. If the user explicitly requests recurring maintenance, use Codex's supported automation workflow with their requested scope; do not create OS cron/Task Scheduler jobs or embed credentials.
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.
- 5d ago First seen · 43 lines · 53 tokens per session scan A 0a1b5bd4d67b
dream-state is a skill published in the GitHub repository KumihoIO/kumiho-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 538 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 2026-09-05.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.