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 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/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/mnemo"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/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 | $0.00132 | $0.06775 |
| Opus 5.5 | $0.00053 | $0.02710 |
| Sonnet 5.5 | $0.00026 | $0.01355 |
| Haiku 4.5 | $0.00013 | $0.00677 |
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.
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 — 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 읽고docs/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
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.
- docs/memory-hygiene.md 21 KB
- docs/memory-system.md 13 KB
- evals/evaluate_recall.py 3.8 KB runs code
- evals/model-expectations.md 5.6 KB
- evals/recall-cases.json 10 KB
- evals/recall-results.md 3.5 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 26 KB runs code
- references/handoff-memory.md 7.1 KB
- references/handoff-template.md 8.4 KB
- references/project-skill-evaluation.md 3.3 KB
- references/project-skill-improvement.md 4.1 KB
- references/project-storage.md 4.7 KB
- references/recall.md 5.7 KB
- references/record-storage.md 2.1 KB
- references/resume-checklist.md 2.7 KB
- references/self-improvement.md 2.0 KB
- references/session-learning.md 2.0 KB
- scripts/build_anchor_index.py 7.7 KB runs code
- scripts/bundle-improvement.js 4.4 KB runs code
- scripts/check_memory_anchors.py 19 KB runs code
- scripts/check_staleness.py 17 KB runs code
- scripts/create_handoff.py 38 KB runs code
- scripts/harvest_lineage.py 18 KB runs code
- scripts/list_handoffs.py 4.6 KB runs code
- scripts/mnemo_doctor.py 82 KB runs code
- scripts/mnemo_markdown.py 6.2 KB runs code
- scripts/mnemo_project_root.py 1.8 KB runs code
- scripts/recall.py 20 KB runs code
- scripts/reclassify_observations.py 9.1 KB runs code
- scripts/reconcile_conversations.py 17 KB runs code
- scripts/split_memory_file.py 15 KB runs code
- scripts/tests/__init__.py 241 B runs code
- scripts/tests/test_anchor_index.py 8.3 KB runs code
- scripts/tests/test_doctor_shared_rules.py 13 KB runs code
- scripts/tests/test_doctor_thread.py 13 KB runs code
- scripts/tests/test_handoff_autofill.py 17 KB runs code
- scripts/tests/test_handoff_component_map.py 12 KB runs code
- scripts/tests/test_handoff_memory.py 6.2 KB runs code
- scripts/tests/test_handoff_origin.py 5.8 KB runs code
- scripts/tests/test_handoff_root.py 6.6 KB runs code
- scripts/tests/test_handoff_tags.py 8.3 KB runs code
- scripts/tests/test_harvest_lineage.py 10 KB runs code
- scripts/tests/test_memory_anchors.py 14 KB runs code
- scripts/tests/test_mnemo_doctor_upgrade.py 11 KB runs code
- scripts/tests/test_mnemo_doctor.py 36 KB runs code
- scripts/tests/test_recall.py 24 KB runs code
- scripts/tests/test_reclassify_observations.py 11 KB runs code
- scripts/tests/test_split_memory_file.py 12 KB runs code
- scripts/validate_handoff.py 29 KB runs code
- templates/claude-md-rules.md 21 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.
- 15d ago Changed · +6 lines aeab7ff9cf4b
- 22d ago Changed · +7 lines 29aee22ed133
- 1mo ago Changed · +5 lines bad16f458f69
- 1mo ago Changed · +6 lines 7565fb82cd6a
- 1mo ago Changed · +63 lines e9894b197439
- 1mo ago Changed 11cd0a8a9e12
- 1mo ago Changed · +83 lines 87282e6356dd
- 1mo ago Changed · +2 lines e52be92345f0
- 1mo ago Changed · +10 lines · -19 tokens per session 54fd594ce040
- 1mo ago First seen · 198 lines · 151 tokens per session scan A 59bc68064a61
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.
Other skills, from other repositories
domain-extract
Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.
capture-practice
Captures an insight or practice discovered during work and registers it in the dotforge practices/inbox.
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.