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/kyopark2014/agent-plugins/memory-managernpx skills add kyopark2014/agent-plugins --skill memory-managergit clone --depth 1 https://github.com/kyopark2014/agent-pluginsWhat 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 | $0.00059 | $0.02155 |
| Opus 5 | $0.00030 | $0.01077 |
| Sonnet 5 | $0.00012 | $0.00431 |
| Haiku 4.5 | $0.00006 | $0.00215 |
Grade A, and why
memory-manager 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 2d 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Manager
Complete memory management system for agents, including semantic search, file management, and memory curation workflows.
When to Use This Skill
- Searching for past decisions, preferences, or context
- Reading or writing to memory files
- Managing daily logs and long-term memory
- Organizing and archiving old memory files
- Before answering questions about prior work or conversations
Core Memory Tools
에이전트에 내장된 두 개의 메모리 도구 (langgraph_agent.py에 @tool로 구현):
memory_search(query, max_results?, min_score?)
MEMORY.md + memory/*.md 파일에 대한 키워드 기반 검색.
Use when:
- User asks about past events, decisions, or preferences
- Looking for related information even with different wording
- Need to recall context from previous sessions
Parameters:
query(required): Search query stringmax_results(optional, default: 5): Max results to returnmin_score(optional, default: 0.0): Minimum relevance threshold (0.0-1.0)
Returns:
JSON array of snippets with text, path, from (line), lines, score.
이 도구는 에이전트가 직접 호출합니다 (execute_code 불필요).
memory_get(path, from_line?, lines?)
특정 메모리 Markdown 파일을 직접 읽기.
Use after:
- memory_search to get full context
- When you know the exact file path
Parameters:
path(required): Workspace-relative path (e.g., "MEMORY.md", "memory/2026-02-27.md")from_line(optional, default: 0): Starting line number, 1-indexed (0 = read from beginning)lines(optional, default: 0): Number of lines to read (0 = read entire file)
Returns:
JSON with text (file content) and path.
Graceful degradation:
If file doesn't exist, returns { "text": "", "path": "..." } (no error).
Memory File Structure
MEMORY.md (Long-term memory)
- Curated, important information
- Decisions, preferences, durable facts
- Security: Only loaded in main, private session (not group chats)
memory/YYYY-MM-DD.md (Daily logs)
- Day-to-day notes, running context
- Append-only during the day
- Today + yesterday loaded at session start
What ships with it
2 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.
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.
- 2d ago First seen · 311 lines · 59 tokens per session scan A c6d9984eb067
memory-manager is a skill published in the GitHub repository kyopark2014/agent-plugins (4 stars, last pushed 25d ago), licensed MIT. It adds 59 tokens to every session and 2,155 once invoked, about $0.0003 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
ask-zilliz
Zilliz Cloud onboarding and usage assistant. Helps users understand Zilliz Cloud, choose the right plan, estimate costs, write code, debug issues, and adopt new features like Functions, Volumes, and Global Clusters. Use this skill whenever the user asks about Zilliz Cloud — including plan selection, pricing, cost…
diagnose
Use when the user reports that a Zilliz Cloud cluster or Milvus collection is unhealthy, slow, stuck, returning errors, hitting quotas, or otherwise misbehaving — or when they ask "what's wrong with...", "why is ... slow", "diagnose ...", "troubleshoot ...".
collection
Use when the user wants to create, list, describe, drop, rename, load, release, or manage collections and collection aliases in Milvus.
cluster
Use when the user wants to create, list, describe, delete, suspend, resume, or modify Zilliz Cloud clusters.
external-collection
Use when the user wants to trigger, describe, or list refresh jobs for an external collection (a collection backed by an external data source such as Vector Lake). Note this is the data-plane refresh workflow, not collection CRUD -- for create/drop/load see the collection skill.
backup
Use when the user wants to create, list, describe, delete, export, or restore backups, or manage backup policies on Zilliz Cloud.