keymem

keymem is a skill for Claude Code from donggyun112/keymem. It costs 56 tokens per session (842 once invoked), scanned A, original, MIT.

A memory protocol for keeping useful facts about a user, project, or past decision available across conversations.

In plain words
What is it for?
It helps recall stored information, handle corrections, organize memories with keys and namespaces, and save durable facts from a conversation.
Why use it?
It reduces the need to repeat important context and helps avoid relying on unverified or outdated memories.

Skill for Claude Code

Written for Claude Code: UserPromptSubmit hook event.

Part of the keymem plugin — 1 skill, 1 hook, 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 skills/donggyun112/keymem/keymem
Any agent
npx skills add donggyun112/keymem --skill keymem
Clone the repo
git clone --depth 1 https://github.com/donggyun112/keymem

Made for: Claude Code.

Or install keymem, the plugin that ships this one along with the rest of its 1 skill, 1 hook, 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 keymem

README.md
[![agentmods](https://agentmods.dev/badge/skills/donggyun112/keymem/keymem.svg)](https://agentmods.dev/skills/donggyun112/keymem/keymem)
Your own site
<a href="https://agentmods.dev/skills/donggyun112/keymem/keymem"><img src="https://agentmods.dev/badge/skills/donggyun112/keymem/keymem.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 842 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 $0.00056 $0.00842
Opus 5 $0.00028 $0.00421
Sonnet 5 $0.00011 $0.00168
Haiku 4.5 $0.00006 $0.00084

Measured 2d ago against content hash f0f16b7c6120, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

keymem 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 2d 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.

skills/keymem/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

keymem protocol

Recall (open the turn)

  • Before the first reply, and whenever the topic shifts, call recall silently.
  • query = short noun keywords ("거주지", not "어디 살아"); context = the raw user utterance. Keys match keywords, content matches sentences — the two cues take different paths.
  • Split multi-fact questions into several recall calls.
  • On {status:"no_match"}, retry with one of the returned nearest_keys, or browse_keys(namespace).
  • A hit returns ranked keys plus one passive Top-1 memory. Use it directly when relevant, apply its validity, and use connected_keys[].key_id when another graph hop is useful.
  • For alternatives or fuller context: read_key(key_id, query, namespace)read_memory(memory_id, via_key_id, namespace). This explicit traversal may reinforce the selected path and learn aliases.
  • <keymem-surfaced> blocks (the UserPromptSubmit hook) are previews. Load the exact record with read_memory, apply its validity status, and ignore it when irrelevant.

Freshness and confirmation

  • read_memory retrieves a fact and may reinforce the key path; it does not confirm or deepen the memory, verify current truth, or refresh it.
  • fresh may be used normally. Qualify aging facts when currentness matters.
  • Never assert a stale fact as current. Verify it externally or ask the user.
  • Call confirm_memory only after an explicit current user assertion, an authoritative current source, or direct observation.
  • Never call confirm_memory merely because read_memory returned the content successfully.
  • Changed fact → correct. Junk fact → forget. Wrong key → dismiss.

Remember (close the turn)

  • Before ending every reply, check whether the turn revealed something durable: a name, preference, decision, correction, project fact, or goal. If it did, save it silently in the same turn.
  • remember(content, keys) with 3–6 keys. Each key is ONE atomic concept of 1–2 words ("recall", "적중률" — never "recall 적중률 개선"). Phrase keys become unreachable singletons.
  • Keys MUST span both Korean and English, plus colloquial variants. Reuse the canonical concepts recall returned instead of minting near-duplicates.
  • Act on hints in the response (near_keys, language_note).
  • Use correct — never a second remember — when a stored fact changes. forget to drop one.
  • namespace groups memories by project/context; pass the active one consistently.
  • A turn that surfaced a durable fact but saved nothing is a bug.

Read the full file on GitHub · 60 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. 2d ago Changed · +14 lines f0f16b7c6120
  2. 6d ago First seen · 46 lines · 56 tokens per session scan A caae059be27c

Subscribe to this mod's changes

keymem is a skill published in the GitHub repository donggyun112/keymem (3 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 842 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.

Related

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.

garrytan/gbrain · 52 tokens

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.…

mem0ai/mem0 · 273 tokens

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…

danielmiessler/LifeOS · 196 tokens

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.

opensquilla/opensquilla · 44 tokens

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…

shiwenwen/hope-agent · 115 tokens

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.

GanyuanRan/Aegis · 45 tokens