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 Kit4Some/Oh-my-ClaudeClaw --skill memory-opsgit clone --depth 1 https://github.com/Kit4Some/Oh-my-ClaudeClawWrote 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/kit4some/oh-my-claudeclaw/memory-ops)<a href="https://agentmods.dev/skills/kit4some/oh-my-claudeclaw/memory-ops"><img src="https://agentmods.dev/badge/skills/kit4some/oh-my-claudeclaw/memory-ops.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 | $0.00114 | $0.01451 |
| Opus 5 | $0.00057 | $0.00726 |
| Sonnet 5 | $0.00023 | $0.00290 |
| Haiku 4.5 | $0.00011 | $0.00145 |
Grade A, and why
memory-ops 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 7d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Operations - 영구 메모리 관리 스킬
핵심 원칙
- 모든 중요 정보는 저장한다: 대화에서 나온 의사결정, 인사이트, 계획은 메모리에 저장
- 구조화하여 저장한다: 적절한 카테고리, 태그, 중요도를 지정
- 필요할 때 꺼낸다: 관련 컨텍스트가 필요하면 먼저 memory_search
- 주기적으로 정리한다: 오래된/중복 메모리 정리, 요약 통합
카테고리 가이드
| 카테고리 | 용도 | 서브카테고리 예시 |
|---|---|---|
projects |
프로젝트 관련 모든 것 | rutile, sapiens, nexus |
people |
인물 정보, 관계, 미팅 노트 | ken-huang, investors |
knowledge |
학습한 지식, 기술 문서 | web3-security, ai-agents |
tasks |
할일, 진행중인 작업 | urgent, backlog |
daily-logs |
일일 활동 로그 | (날짜 자동 생성) |
inbox |
미분류 임시 저장 | (나중에 분류) |
자동 저장 트리거
대화 중 다음 패턴이 나타나면 메모리 저장을 자동 제안:
- 🔑 의사결정: "~하기로 했다", "~로 결정", "~방향으로"
- 📋 계획/전략: "앞으로 ~할 예정", "계획은 ~"
- 🤝 인물 정보: 새로운 사람 이름 + 역할/관계
- 💡 인사이트: "깨달은 게", "중요한 건", "핵심은"
- 📊 데이터/수치: 매출, 일정, 가격 등 구체적 수치
- ⚠️ 위험/이슈: 문제점, 리스크, 주의사항
저장 워크플로우
1. 빠른 저장 (Quick Store)
사용자: "이거 기억해줘 — Ken Huang이 CSA 공동의장이고 SF에서 3/25에 만나기로 했어"
→ memory_store:
category: "people"
subcategory: null
title: "Ken Huang - CSA 공동의장"
content: "Ken Huang은 Cloud Security Alliance의 공동의장. 3/25 SF 미팅 예정."
tags: ["ken-huang", "csa", "sf-trip", "meeting"]
importance: 7
2. 프로젝트 컨텍스트 저장
사용자: "Sapiens에서 PydanticAI로 마이그레이션하기로 했어"
→ memory_store:
category: "projects"
subcategory: "sapiens"
title: "Framework Migration Decision - PydanticAI"
content: "LangGraph에서 PydanticAI로 마이그레이션 결정. 이유: ..."
tags: ["sapiens", "migration", "pydanticai", "decision"]
importance: 8
3. 지식 저장
사용자: "이 취약점 패턴 저장해줘"
→ memory_store:
category: "knowledge"
subcategory: "web3-security"
title: "Reentrancy Attack Pattern - Cross-function"
content: [detailed content]
tags: ["vulnerability", "reentrancy", "solidity"]
importance: 6
검색 워크플로우
컨텍스트 기반 자동 검색
작업 시작 전 관련 메모리를 선제적으로 검색:
사용자: "RSA Conference 준비 상황 알려줘"
→ 1. memory_search(query: "RSA Conference")
→ 2. memory_search(tag: "rsa")
→ 3. memory_search(category: "projects", query: "rutile conference")
→ 4. 결과 종합하여 응답
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.
- 7d ago First seen · 157 lines · 114 tokens per session scan A 1d7cb6f243d4
memory-ops is a skill published in the GitHub repository Kit4Some/Oh-my-ClaudeClaw (4 stars, last pushed 5mo ago), licensed MIT. It adds 114 tokens to every session and 1,451 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
new
Start a new session — save summary to memory, then mark as reset so next message gets a fresh greeting. OpenClaw-compatible. Triggers on /new, /reset, /agent:new, "nueva sesión", "new session", "reset".
compact
Flush important session context to daily log (manual memory flush). Does NOT invoke native /compact. Triggers on /compact, /agent:compact, /flush, "guarda memoria", "flush".
wiki-write
Add or update wiki content — autonomous ingest from URL, file, or text; autonomous update of existing pages. Auto-creates .wiki/ on first use. Use when: 'save to wiki', 'remember this', 'note this', 'store this', 'add to knowledge base', 'save findings', 'save research', 'save idea', 'write to wiki', 'ingest', 'add…
wiki-view
Wiki dashboard — browse pages, view stats, knowledge graph, export. Use on: 'wiki dashboard', 'wiki stats', 'show wiki', 'wiki pages', 'list wiki', 'wiki graph', 'export wiki', 'wiki overview'.
project-memory
Use to create and maintain durable cross-session project memory and the progress ledger, so long autonomous builds resume cleanly after compaction, restarts, or new sessions. Read it when starting work and update it as decisions and tasks land.
agent-estate
Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.