mnemo

mnemo is a skill for Claude Code from Dannykkh/skill-olympus. It costs 132 tokens per session (6,775 once invoked), scanned A, original, MIT.

A file-based memory system for saving conversations, tool activity, and handoff notes between coding sessions. It keeps project memory separate from Claude’s built-in personal memory.

In plain words
What is it for?
Use it to save and search past conversations, create and validate handoffs, manage MEMORY.md and related files, and recover missing conversation records.
Why use it?
It helps an agent continue work with relevant context after a session ends, while allowing sensitive entries or all saving to be excluded.

Skill for Claude Code

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

Part of the skill-olympus plugin — 101 skills, 7 commands, 5 MCP servers shipped together

Good fit Use it to save and search past conversations, create and validate handoffs, manage MEMORY.md and related files, and recover missing conversation records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dannykkh/skill-olympus/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 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 101 skills, 7 commands, 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 mnemo

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/mnemo"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/mnemo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,775 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00132 $0.06775
Opus 5.5 $0.00053 $0.02710
Sonnet 5.5 $0.00026 $0.01355
Haiku 4.5 $0.00013 $0.00677

Measured 15d ago against content hash aeab7ff9cf4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 15d ago.

The scan reads SKILL.md. This mod also ships 35 executable files (evals/evaluate_recall.py, evals/setup_test_env.py, install.js, …), 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.

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/mnemo/SKILL.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 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

실행 요건

기능 런타임 Python이 없으면
대화 자동 저장 · 도구 관찰 로그 · MEMORY.md 규칙 PowerShell / bash + Node.js 정상 동작
누락 턴 복구 (SessionStart) 셸 → Python 조용히 건너뜀 (exit 0)
핸드오프 생성·검증·목록·staleness Python 3 실행 불가 → 아래 대안
변경 계보 수확 · 기억 앵커 검사 Python 3 + Node 실행 불가

Python이 없어도 기억은 계속 쌓입니다. 저장 훅은 셸에서 Node.js 저장기를 실행하며, Python은 쌓인 것을 읽고 분석하는 도구에만 필요합니다. install.js --check의 [4/4]가 현재 상태를 알려주며, Python 없음은 설치 실패로 치지 않습니다. 명령은 python·py·python3 중 --version이 되는 첫 것을 씁니다 — Windows 스토어 별칭 때문에 python만 실패하고 py는 되는 PC가 있습니다 (판정 규칙).

Python 없이 핸드오프 쓰기: references/handoff-template.md를 읽고 docs/handoffs/YYYY-MM-DD-HHMMSS-{slug}.md에 직접 작성합니다. 스캐폴드와 검증만 없을 뿐 핸드오프 계약은 동일합니다. 컨텍스트가 차오르는 순간에 스크립트가 없다고 핸드오프를 포기하지 마세요 — 그게 가장 큰 손실입니다.


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 + 앵커 조회 주입 (Claude·Grok 공용)
│   ├── save-response.ps1/.sh           # Assistant 응답 저장 (Stop)
│   ├── claude-event-store.js           # 입력 세대와 응답 UUID 식별
│   ├── mnemo-record-store.js           # CLI 공통 대기 저장·본문 확인
│   └── reconcile-conversations.ps1/.sh # 누락 턴 복구 (SessionStart)
├── templates/                  # CLAUDE.md 규칙
│   └── claude-md-rules.md
├── scripts/                    # Python 3 (+ 루트 판정에 Node)
│   │   # ── 핸드오프 (세션 경계) ──
│   ├── create_handoff.py       # 스캐폴드 (Origin=현재 CLI가 확인한 요구·출처, Files=관찰, 대체 후보 제시)
│   ├── validate_handoff.py     # 게이트 (feature-bearing: Origin+Diagram 필수)
│   ├── list_handoffs.py        # 목록
│   ├── check_staleness.py      # 핸드오프가 현재 코드 대비 얼마나 낡았나 (git 기준)
│   │   # ── 기억 위생 (진단 전부 · 수정 최소) ──
│   ├── mnemo_doctor.py         # 진입점: 기억 점검, --fix / --upgrade-memory / --promote-structure
│   ├── build_anchor_index.py   # 착수 전 조회: 이 파일에 기대는 결정 (기억 파생)
│   ├── harvest_lineage.py      # 착수 전 조회: 파일별 "언제·왜·어떻게" (핸드오프 파생)
│   ├── check_memory_anchors.py  # 기억이 가리키는 파일이 실재하는가 (CodeMap 이동 힌트)
│   ├── split_memory_file.py    # 복구: 비대한 memory/X.md → X/NNN-*.md + index.md
│   ├── reclassify_observations.py  # 복구: 옛 훅이 오분류한 관찰을 learned로
│   │   # ── 공통 ──
│   ├── reconcile_conversations.py  # JSONL → conversations/ 누락 턴 복구
│   ├── recall.py               # 일반 대화·기억 연결을 읽기 전용으로 조회
│   ├── mnemo_markdown.py       # 회상·닥터의 공통 Markdown 구조 해석
│   └── mnemo_project_root.py   # 프로젝트 루트 판정 (훅과 같은 경계)
├── references/                 # 핸드오프 템플릿
│   ├── handoff-template.md
│   └── resume-checklist.md
├── docs/                       # 상세 문서
│   ├── memory-system.md        # 인지 모델 설명
│   └── memory-hygiene.md       # 기능 4 도구별 상세 (SKILL.md 경량화로 분리)
└── evals/                      # 평가

Read the full file on GitHub · 380 lines

Files

What ships with it

53 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. 15d ago Changed · +6 lines aeab7ff9cf4b
  2. 22d ago Changed · +7 lines 29aee22ed133
  3. 1mo ago Changed · +5 lines bad16f458f69
  4. 1mo ago Changed · +6 lines 7565fb82cd6a
  5. 1mo ago Changed · +63 lines e9894b197439
  6. 1mo ago Changed 11cd0a8a9e12
  7. 1mo ago Changed · +83 lines 87282e6356dd
  8. 1mo ago Changed · +2 lines e52be92345f0
  9. 1mo ago Changed · +10 lines · -19 tokens per session 54fd594ce040
  10. 1mo ago First seen · 198 lines · 151 tokens per session scan A 59bc68064a61

Subscribe to this mod's changes

mnemo is a skill published in the GitHub repository Dannykkh/skill-olympus (7 stars, last pushed 2d ago), licensed MIT. It adds 132 tokens to every session and 6,775 once invoked, about $0.0005 per session on Opus 5.5. 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.