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 memory-compactgit 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/memory-compact)<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/memory-compact"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/memory-compact/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/memory-compact"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/memory-compact.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 | $0.00071 | $0.00987 |
| Opus 5 | $0.00036 | $0.00494 |
| Sonnet 5 | $0.00014 | $0.00197 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
memory-compact 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 6d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Compact - MEMORY.md 압축 스킬
MEMORY.md가 비대해져 성능에 영향을 줄 때 사용합니다.
상세 내용을 memory/*.md로 이동하고, MEMORY.md는 가벼운 인덱스로 복원합니다.
제한 기준
| 항목 | 제한 |
|---|---|
| MEMORY.md 최대 줄 수 | 100줄 |
| MEMORY.md 최대 크기 | 5KB |
| 항목당 최대 줄 수 | 3줄 (인덱스에는 요약만) |
워크플로우
Step 1: 진단
1. MEMORY.md 읽기
2. 줄 수, 바이트 수 측정
3. 100줄 / 5KB 이하면 → "이미 컴팩트합니다" 종료
4. 초과면 → Step 2 진행
Step 2: 분석
각 섹션을 파싱하여 문제를 분류합니다:
| 문제 유형 | 설명 | 조치 |
|---|---|---|
| 쓰레기 데이터 | 로그 출력, 에러 메시지, 설치 로그 등 | 삭제 |
| 상세 내용 인라인 | 인덱스가 아닌 상세 설명이 MEMORY.md에 있음 | memory/*.md로 이동 |
| 중복 항목 | 같은 내용이 반복됨 | 병합 |
| SUPERSEDED 누적 | 오래된 ❌ 항목이 쌓임 | memory/archive.md로 이동 |
Step 3: 압축 실행
1. 쓰레기 데이터 삭제
2. 상세 내용을 적절한 memory/*.md로 이동
- 설계 결정 → memory/architecture.md
- 작업 패턴 → memory/patterns.md
- 도구/라이브러리 → memory/tools.md
- 주의사항 → memory/gotchas.md
3. MEMORY.md에는 키워드 인덱스 항목만 남김
4. SUPERSEDED 항목은 memory/archive.md로 이동
5. 빈 섹션 정리
Step 4: 결과 보고
## Memory Compact 결과
| 항목 | 압축 전 | 압축 후 |
|------|---------|---------|
| 줄 수 | {before_lines} | {after_lines} |
| 크기 | {before_kb}KB | {after_kb}KB |
| 삭제된 항목 | {deleted} |
| 이동된 항목 | {moved} |
### 이동 내역
| 내용 요약 | 이동 대상 |
|-----------|-----------|
| {summary} | memory/{file}.md |
MEMORY.md 올바른 형태 (참고)
# MEMORY.md - 프로젝트 장기기억
## 프로젝트 목표
| 목표 | 상태 |
|------|------|
| 핵심 기능 구현 | 🔄 진행중 |
---
## 키워드 인덱스
| 키워드 | 상세 파일 |
|--------|-----------|
| auth, jwt | [memory/architecture.md](memory/architecture.md) |
| hooks, 훅 | [memory/tools.md](memory/tools.md) |
---
## architecture/
→ [memory/architecture.md](memory/architecture.md)
## patterns/
→ [memory/patterns.md](memory/patterns.md)
## tools/
→ [memory/tools.md](memory/tools.md)
## gotchas/
→ [memory/gotchas.md](memory/gotchas.md)
---
## meta/
- **프로젝트**: my-project
- **마지막 업데이트**: 2026-03-08
금지 사항
- MEMORY.md에 로그 출력, 에러 메시지, 설치 결과를 절대 저장하지 않음
- MEMORY.md에 3줄 이상의 상세 설명을 넣지 않음
- 인덱스 역할이 아닌 내용은 반드시 memory/*.md로 분리
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.
- 6d ago First seen · 128 lines · 71 tokens per session scan A 00923eb1e1cf
memory-compact is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 987 once invoked, about $0.0004 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
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.