grok-mnemo

grok-mnemo is a skill for Claude Code from Dannykkh/skill-olympus. It costs 96 tokens per session (2,091 once invoked), scanned B, original, MIT.

A long-term memory system for Grok Build, an AI coding tool. It saves conversations between sessions and lets the tool search past discussions and project guidance.

In plain words
What is it for?
Use it to save conversations, search previous decisions, maintain project rules, and create handoffs between sessions.
Why use it?
It reduces the need to repeat earlier context when work continues in a later session.

Skill for Claude Code

Written for Claude Code: UserPromptSubmit hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Part of the skill-olympus plugin — 98 skills, 7 commands, 42 agents, 5 MCP servers shipped together

Good fit Use it to save conversations, search previous decisions, maintain project rules, and create handoffs between sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dannykkh/skill-olympus/grok-mnemo
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.

Any agent
npx skills add Dannykkh/skill-olympus --skill grok-mnemo
Clone the repo
git clone --depth 1 https://github.com/Dannykkh/skill-olympus

Made for: Claude Code.

Or install skill-olympus, the plugin that ships this one along with the rest of its 98 skills, 7 commands, 42 agents, 5 MCP servers.

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 grok-mnemo

README.md
[![agentmods](https://agentmods.dev/badge/skills/dannykkh/skill-olympus/grok-mnemo/github.svg)](https://agentmods.dev/skills/dannykkh/skill-olympus/grok-mnemo)
Your own site
<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/grok-mnemo"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/grok-mnemo/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 grok-mnemo

Your own site · 80×15
<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/grok-mnemo"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/grok-mnemo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00096 $0.02091
Opus 5 $0.00048 $0.01045
Sonnet 5 $0.00019 $0.00418
Haiku 4.5 $0.00010 $0.00209

Measured yesterday against content hash 403a6b2caa5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

grok-mnemo scanned grade B with 1 finding 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.

The scan reads SKILL.md. This mod also ships 4 executable files (hooks/append-event.js, hooks/save-turn.ps1, hooks/save-turn.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

6. **이중 저장 방지 가드**: Grok은 `~/.claude/settings.json`의 Claude 훅도 로드하므로, Claude용 mnemo 훅들은 첫 줄에서 `GROK_HOOK_EVENT` 환경변수를 감지하면 exit 0 (grok-mnemo가 전담)
skills/grok-mnemo/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grok-Mnemo - Grok Build 기억 시스템

기억의 여신 Mnemosyne에서 유래. Claude Code용 Mnemo를 Grok Build(xAI CLI)에 이식.

Grok Build 세션 간 컨텍스트 유지를 위한 장기기억 시스템입니다.

설치

node "<module_root>/install.js"              # 설치 (Grok 미설치 시 자동 skip)
node "<module_root>/install.js" --uninstall  # 제거
node "<module_root>/install.js" --check      # 설치 상태 점검

4종 Mnemo 비교

Claude Code (Mnemo) Codex CLI Antigravity CLI Grok Build (Grok-Mnemo)
2개 (Submit + Stop) 1개 (notify) 1개 (Stop) 1스크립트 2이벤트 (UserPromptSubmit + Stop)
데이터 전달 stdin + transcript JSONL argv JSON stdin JSON stdin JSON (camelCase)
페이로드 prompt / transcript 파싱 input/last-assistant-message transcriptPath / user·model 파싱 prompt(<user_query> 래핑) / lastAssistantMessage
설정 형식 settings.json config.toml config/hooks.json hooks/*.json 자동 스캔
규칙 파일 CLAUDE.md AGENTS.md GEMINI.md ~/.grok/rules/*.md (델타만)
저장 경로 conversations/*-claude.md conversations/*-codex.md conversations/*-antigravity.md conversations/*-grok.md
중복 방지 타임스탬프 turn-id 타임스탬프 이벤트 식별자 또는 세션 입력·응답 상태 + reason 필터

Grok만의 특이점 (실측 근거, Grok Build 0.2.111):

  1. Claude 자산 직접 읽기: 스킬/에이전트/MCP/규칙은 [compat.claude] 기본값으로 ~/.claude/를 직접 읽음 → mnemo 훅만 어댑터 필요 (memory/learned/018 참조)
  2. camelCase envelope: Claude의 transcript_path(snake_case)와 달리 transcriptPath/sessionId/lastAssistantMessage — Claude 훅 스크립트가 그대로 동작하지 않는 이유
  3. <user_query> 래핑: UserPromptSubmit의 prompt<user_query>...</user_query>로 감싸져 옴 → 훅에서 스트립
  4. Stop 이중 발화: 세션 종료 시 observe-only Stop이 한 번 더 발화 (reason: channel_closed|shutdown) → reason == "end_turn"만 저장
  5. Stop stdout 파싱: Stop 훅의 stdout JSON은 stop 결정으로 해석됨 → 훅은 stdout에 아무것도 쓰지 않음 (안내는 stderr)
  6. 이중 저장 방지 가드: Grok은 ~/.claude/settings.json의 Claude 훅도 로드하므로, Claude용 mnemo 훅들은 첫 줄에서 GROK_HOOK_EVENT 환경변수를 감지하면 exit 0 (grok-mnemo가 전담)

핵심 원칙

원칙 설명
빠르게 훅에서 AI 호출 금지
단순하게 파일 기반, DB 없음
검색 가능하게 키워드 + 동의어 확장

Read the full file on GitHub · 119 lines

Files

What ships with it

5 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.

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. yesterday Changed · +12 lines 403a6b2caa5d
  2. 6d ago First seen · 107 lines · 96 tokens per session scan B 81f6c94bb8cf

Subscribe to this mod's changes

grok-mnemo is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 2,091 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.