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 agentmods add skills/dannykkh/skill-olympus/mnemonpx skills add Dannykkh/skill-olympus --skill 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/mnemo)<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/mnemo"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/mnemo.svg" alt="Measured on agentmods" 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 | $0.00151 | $0.01880 |
| Opus 5 | $0.00076 | $0.00940 |
| Sonnet 5 | $0.00030 | $0.00376 |
| Haiku 4.5 | $0.00015 | $0.00188 |
Grade A, and why
mnemo 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mnemo - 기억 시스템
기억의 여신 Mnemosyne에서 유래
세션 간 컨텍스트 유지를 위한 통합 메모리 시스템입니다.
설치
node skills/mnemo/install.js # 설치
node skills/mnemo/install.js --uninstall # 제거
핵심 원칙
| 원칙 | 설명 |
|---|---|
| 빠르게 | 훅에서 AI 호출 금지 |
| 단순하게 | 파일 기반, DB 없음 |
| 검색 가능하게 | 키워드 + 동의어 확장 |
| 점진적 공개 | 필요한 깊이까지만 읽기 (Progressive Disclosure) |
| 프라이버시 | <private> 태그로 민감 정보 제외, MNEMO_DISABLE=1로 저장 전체 opt-out |
포함 파일
mnemo/
├── SKILL.md # 이 파일
├── install.js # 설치 스크립트
├── hooks/ # 대화 저장 훅 (root hooks/에 위치)
│ ├── save-conversation.ps1/.sh # User 입력 저장
│ ├── save-tool-use.ps1/.sh # 도구 호출 관찰 로그
│ ├── save-response.ps1/.sh # Assistant 응답 저장 (Stop)
│ └── reconcile-conversations.ps1/.sh # 누락 턴 복구 (SessionStart)
├── templates/ # CLAUDE.md 규칙
│ └── claude-md-rules.md
├── scripts/ # 핸드오프 + reconcile 스크립트
│ ├── create_handoff.py
│ ├── validate_handoff.py
│ ├── list_handoffs.py
│ ├── check_staleness.py
│ └── reconcile_conversations.py # JSONL → conversations/ 복구
├── references/ # 핸드오프 템플릿
│ ├── handoff-template.md
│ └── resume-checklist.md
├── docs/ # 상세 문서
│ └── memory-system.md # 인지 모델 설명
└── evals/ # 평가
기능 1: 대화 자동 저장
[SessionStart 훅] reconcile-conversations
→ 지난 세션에서 놓친 assistant 턴을 JSONL 기준으로 backfill (멱등)
↓
사용자 입력
↓
[UserPromptSubmit 훅] save-conversation
→ 대화 파일에 User 입력 append (<private> 블록 제거)
↓
Claude 도구 호출
↓
[PostToolUse 훅] save-tool-use
→ 도구명 + 파일경로를 toollog에 한 줄 append
↓
Claude 응답 (끝에 #tags 포함)
↓
[Stop 훅] save-response
→ transcript에서 응답 추출 → <private> 블록 제거 → 대화 파일 append
내부 백업 (⚠️ 직접 읽기 금지, reconcile 전용): ~/.claude/projects/<encoded>/*.jsonl
검색 대상 (사람이 읽고 Claude가 grep): conversations/YYYY-MM-DD-claude.md
멱등 인덱스: conversations/.mnemo-index.json (JSONL 줄 uuid 기반)
What ships with it
14 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.
- docs/memory-system.md 9.7 KB
- evals/model-expectations.md 5.6 KB
- evals/results-opus-baseline.md 2.6 KB
- evals/setup_test_env.py 10 KB runs code
- evals/test-scenarios.md 5.2 KB
- install.js 20 KB runs code
- references/handoff-template.md 6.8 KB
- references/resume-checklist.md 2.7 KB
- scripts/check_staleness.py 16 KB runs code
- scripts/create_handoff.py 14 KB runs code
- scripts/list_handoffs.py 4.4 KB runs code
- scripts/reconcile_conversations.py 17 KB runs code
- scripts/validate_handoff.py 14 KB runs code
- templates/claude-md-rules.md 25 KB
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.
- 3d ago First seen · 190 lines · 151 tokens per session scan A d06fb96e4969
mnemo is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed 5d ago), licensed MIT. It adds 151 tokens to every session and 1,880 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
diary
Unified Diary System: A context-preserving automated logger for multi-project development.
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
session-memory
Mandatory memory persistence system across session resets using three markdown surfaces in .claude/cc10x/. Iron law - every workflow must load at start and update at end.
langchain-memory
LangChain memory integration including ConversationBufferMemory, ConversationSummaryMemory, and vector-based memory.
knowledge-graph-management
Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph.