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.
npx skills add Dannykkh/skill-olympus --skill grok-mnemogit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote 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/dannykkh/skill-olympus/grok-mnemo)<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.
<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>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 | $0.00096 | $0.02091 |
| Opus 5 | $0.00048 | $0.01045 |
| Sonnet 5 | $0.00019 | $0.00418 |
| Haiku 4.5 | $0.00010 | $0.00209 |
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.
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) 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) | |
|---|---|---|---|---|
| 훅 | 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):
- Claude 자산 직접 읽기: 스킬/에이전트/MCP/규칙은
[compat.claude]기본값으로~/.claude/를 직접 읽음 → mnemo 훅만 어댑터 필요 (memory/learned/018 참조) - camelCase envelope: Claude의
transcript_path(snake_case)와 달리transcriptPath/sessionId/lastAssistantMessage— Claude 훅 스크립트가 그대로 동작하지 않는 이유 <user_query>래핑: UserPromptSubmit의prompt는<user_query>...</user_query>로 감싸져 옴 → 훅에서 스트립- Stop 이중 발화: 세션 종료 시 observe-only Stop이 한 번 더 발화 (
reason: channel_closed|shutdown) →reason == "end_turn"만 저장 - Stop stdout 파싱: Stop 훅의 stdout JSON은 stop 결정으로 해석됨 → 훅은 stdout에 아무것도 쓰지 않음 (안내는 stderr)
- 이중 저장 방지 가드: Grok은
~/.claude/settings.json의 Claude 훅도 로드하므로, Claude용 mnemo 훅들은 첫 줄에서GROK_HOOK_EVENT환경변수를 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 |
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.
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 · +12 lines 403a6b2caa5d
- 6d ago First seen · 107 lines · 96 tokens per session scan B 81f6c94bb8cf
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.
Other skills, from other repositories
handoff
Structured session handoff — preserves context for seamless continuation across sessions.
lesson-learned
Extract learnings and save as memory files (file-based memory system). Use when: "lesson learned", "what did we learn", "learning", "remember".
context-budget
Analyzes where context tokens are being spent and identifies optimization opportunities. Use when sessions feel slow or context is running out.
pattern-extractor
Analyzes captured patterns from continuous learning to extract reusable workflows and anti-patterns. Use when you want to review what's been learned across sessions.
throughline
Use when the user asks to use Throughline from Codex, continue or restore Throughline memory, export read-only handoff context for a local launcher, prepare a new Codex thread handoff, summarize a captured Codex session, or check whether the Throughline Codex Stop hook captured the current session. Hide long…
domain-extract
Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.