memory-capture

memory-capture is a command for Claude Code from KumihoIO/kumiho-plugins. It costs 11 tokens per session (407 once invoked), scanned A, original, MIT.

A command for saving one user fact or preference in Kumiho memory so it can be recalled in later sessions. It checks related memories before storing the new entry.

In plain words
What is it for?
Use it to record a fact, decision, or preference supplied by the user, with a title, content, tags, and an appropriate memory location.
Why use it?
It gives the agent a defined way to preserve useful user information instead of losing it when the session ends.

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

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.

agentmods
npx agentmods add commands/kumihoio/kumiho-plugins/memory-capture
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 memory-capture

README.md
[![agentmods](https://agentmods.dev/badge/commands/kumihoio/kumiho-plugins/memory-capture.svg)](https://agentmods.dev/commands/kumihoio/kumiho-plugins/memory-capture)
Your own site
<a href="https://agentmods.dev/commands/kumihoio/kumiho-plugins/memory-capture"><img src="https://agentmods.dev/badge/commands/kumihoio/kumiho-plugins/memory-capture.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 407 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00011 $0.00407
Opus 5 $0.00005 $0.00204
Sonnet 5 $0.00002 $0.00081
Haiku 4.5 $0.00001 $0.00041

Measured 6d ago against content hash 2b3c5ca72151, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

memory-capture 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 6d 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/memory-capture.md · 39 lines

What it actually says

Memory Capture

Store a single user fact or preference into Kumiho memory so it can be recalled in later sessions.

Steps

  1. If no argument was provided, ask the user for the memory text to store.
  2. Call kumiho_memory_engage with the memory text as query to find related existing memories. Hold the returned source_krefs.
  3. Call kumiho_memory_reflect with (pass the session_id the SessionStart card gave you; omit it only if it gave you none, and let the server resolve and report the value it used):
    • response: "Manual memory capture via /memory-capture"
    • captures: one capture with:
      • type: infer from content — "fact" for facts, "decision" for decisions, "preference" for preferences
      • title: short descriptive title with absolute date
      • content: the provided memory text
      • tags: ["manual-capture"]
      • space_hint: the space this belongs in — copy an existing name exactly from a step-2 kref (kref://<project>/<space>/<item>.<kind>; the hint is forwarded verbatim, so capitalization matters), else the capture type (facts, decisions, preferences). Never omit it: an unrouted capture lands at the project root, where reflect's automatic stacking can fold it into an unrelated memory.
    • source_krefs: krefs from step 2 (if any were relevant)
  4. Confirm what was stored and how many edges were created.

Guardrails

  • Do not store secrets (passwords, private keys, API secrets).
  • If the user asks to store sensitive data, ask for confirmation first.
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. 6d ago First seen · 39 lines · 11 tokens per session scan A 2b3c5ca72151

Subscribe to this mod's changes

memory-capture is a command published in the GitHub repository KumihoIO/kumiho-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 407 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.