kumiho-personalize

kumiho-personalize is a command for Claude Code from KumihoIO/kumiho-plugins. It costs 19 tokens per session (858 once invoked), scanned A, original, MIT.

A command for changing saved agent identity preferences such as name, language, tone, response length, and behavior rules. It preserves older versions while publishing the updated preferences.

In plain words
What is it for?
Use it to review and edit identity settings, change one or several preference fields, and keep a revision history of those changes.
Why use it?
It lets users change how the agent responds without losing the previous settings. It also shows the current preferences before asking what to update.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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

Good fit Use it to review and edit identity settings, change one or several preference fields, and keep a revision history of those changes.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/kumihoio/kumiho-plugins/kumiho-personalize"><img src="https://agentmods.dev/badge/commands/kumihoio/kumiho-plugins/kumiho-personalize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 858 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 $0.00019 $0.00858
Opus 5 $0.00010 $0.00429
Sonnet 5 $0.00004 $0.00172
Haiku 4.5 $0.00002 $0.00086

Measured 11d ago against content hash 0ca6a3e9110b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kumiho-personalize 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 11d 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/kumiho-personalize.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kumiho Personalize

Update the CognitiveMemory/agent.instruction item with new preferences. Creates a new revision and moves the published tag — old preferences are preserved in revision history.

Steps

  1. Load current preferences — fetch the current published revision:

    kumiho_get_revision_by_tag(
      item_kref = "kref://CognitiveMemory/agent.instruction",
      tag       = "published"
    )
    

    If that returns not-found, retry once with the space-qualified kref — self-hosted CE servers do not resolve the space-less shorthand:

    kumiho_get_revision_by_tag(
      item_kref = "kref://CognitiveMemory/personal/agent.instruction",
      tag       = "published"
    )
    

    Use whichever kref resolved for all subsequent steps.

    If the item doesn't exist at either kref, tell the user: "No identity found yet — start a new session and I'll walk you through the full onboarding." Then stop.

    Parse the metadata fields from the current revision so you can show the user what's currently set.

  2. Show current settings and ask what to change — display the current values in a compact table and ask the user what they'd like to update. Let them change one field or many. The fields are:

    Field Description
    agent_name What the agent calls itself
    user_name What the agent calls the user
    user_languages Preferred languages (e.g. "English, Korean")
    communication_tone casual / professional / balanced
    verbosity concise / balanced / detailed
    user_role User's role or area of expertise
    user_expertise_level beginner / intermediate / advanced
    primary_tools Tools/technologies the user works with
    artifact_dir Where to save conversation artifacts
    timezone User's timezone
    interaction_rules Custom behavior rules
    memory_behaviour How aggressively to remember (minimal / balanced / thorough)

Read the full file on GitHub · 99 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. 11d ago First seen · 99 lines · 19 tokens per session scan A 0ca6a3e9110b

Subscribe to this mod's changes

kumiho-personalize is a command published in the GitHub repository KumihoIO/kumiho-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 858 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.