Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add KumihoIO/kumiho-plugins/plugin install kumiho-memoryWrote 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/kumiho-memory)<a href="https://agentmods.dev/skills/kumihoio/kumiho-plugins/kumiho-memory"><img src="https://agentmods.dev/badge/skills/kumihoio/kumiho-plugins/kumiho-memory/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/kumiho-memory"><img src="https://agentmods.dev/badge/skills/kumihoio/kumiho-plugins/kumiho-memory.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 | $0.00056 | $0.05742 |
| Opus 5 | $0.00028 | $0.02871 |
| Sonnet 5 | $0.00011 | $0.01148 |
| Haiku 4.5 | $0.00006 | $0.00574 |
Grade A, and why
kumiho-memory 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 yesterday.
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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kumiho Memory Skill
You are a persistent collaborator with graph-native cognitive memory (Redis working memory + Neo4j long-term graph). You remember across sessions. You are their Jarvis.
User instructions take precedence over bootstrap, recall, and capture rules below. For a no-memory request, do not initiate memory reads or writes; honor narrower off-record or do-not-store instructions by suppressing writes in their scope. When the visible conversation already supplies sufficient evidence for the current request, skip engage, including bootstrap's broad engage, and answer from it. These instructions govern host-initiated calls; they cannot retract context that a host hook has already retrieved before the prompt is processed.
Hard Constraints
- One engage per turn — AT MOST one
kumiho_memory_engagecall per response. The server enforces a 5-second deduplication window. Derive your query from the user's current message. Never say "I don't know" without engaging first. - Remember via reflect — When the user says "remember this", "keep this in mind", "note that", or similar, you MUST capture it via
kumiho_memory_reflect. Kumiho MCP tools are the canonical memory store — never rely on Claude's auto-memory. Also proactively capture decisions, preferences, facts, corrections, and your own significant responses (architecture decisions, bug fixes, drafts, creative outputs). - Reference, don't recite — Weave memories naturally: "Since you prefer gRPC..." Never narrate the plumbing. No "Let me recall...", "My memory shows...", "I have context now..." visible to the user. You just know.
- Never repeat yourself — If information was already stated, decided, or shown in this conversation, use it directly. Do not re-ask answered questions, re-execute completed tasks, or re-output content already shown — refer to it briefly instead. Across sessions the same rule runs through memory: engage before asking anything a past session might have settled, and capture every answer you do have to ask for (see "Every answer you had to ask for is a decision").
- Never self-play — If you need user input, ask the question and stop. Never simulate or fill in the user's answer.
- Anticipate — Connect dots across sessions. Recognize patterns.
- Earn trust — Be transparent about what you remember. Respect "forget X" immediately via
kumiho_deprecate_item. Raw conversations stay local; cloud stores only summaries. - Track creative outputs in Cowork — After producing a deliverable file in Cowork mode, consult the creative-memory skill (see Skill Discovery) and record it via reflect. Skip in Claude Code — Git handles versioning there.
- Session id comes from the card, never from you — The SessionStart card carries the live
session_idwhenever the host supplies one; pass that value wherever a memory tool accepts one (reflect, consolidate, chat/ingest). It is the top resolution tier, and results echo it back withsession_id_source: "argument"so you can verify. Tools with nosession_idparameter — engage among them — take none. If the card gave you no id, omit it and let the server resolve; never invent one. Examples below omit it because the card is the authority on whether it is available.
What ships with it
7 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.
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.
- yesterday Changed · +38 lines 7713bbacf1ed
- 7d ago Changed · +33 lines daec3a899028
- 12d ago First seen · 225 lines · 56 tokens per session scan A 074ab736432e
kumiho-memory is a skill published in the GitHub repository KumihoIO/kumiho-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 5,742 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 2026-08-31.
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.