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 mupengi-bot/mupengism --skill memory-systemgit clone --depth 1 https://github.com/mupengi-bot/mupengismWrote 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/mupengi-bot/mupengism/memory-system)<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/memory-system"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/memory-system.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 | $0.00100 | $0.02043 |
| Opus 5 | $0.00050 | $0.01022 |
| Sonnet 5 | $0.00020 | $0.00409 |
| Haiku 4.5 | $0.00010 | $0.00204 |
Grade A, and why
memory-system 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory System v2 — 3-Tier Hierarchical Memory 🐧
통합: agent-memory-kit의 자기 개선 + 세션 연속성 + 실수 추적 기능이 병합되었습니다.
Architecture
| Tier | File | Purpose | Size Limit | Update Frequency |
|---|---|---|---|---|
| L1 | memory/L1-active.md |
Immediate working context | ~100 lines | Every session |
| L2 | memory/L2-weekly.md |
Weekly decisions & insights | ~400 lines | Weekly |
| L3 | MEMORY.md |
Permanent archive | Unlimited | As needed |
L1 — Active Context
Current day's state. Load this first every session.
Contains: Today's events, active tasks, bot status, next actions, key values to remember.
Rules:
- Overwrite daily — yesterday's L1 becomes a daily file (
memory/YYYY-MM-DD.md) - Keep under 100 lines
- Structure: 핵심 사건 → 진행 중 → 핵심 가치관 → 다음 할 일
L2 — Weekly Digest
Week's accumulated decisions and insights.
Contains: Key decisions made, weekly insights, project status snapshots, people updates.
Rules:
- Reset weekly (Sunday or Monday)
- Old L2 content promotes to L3 or gets archived as
memory/L2-week-YYYY-MM-DD.md - Keep under 400 lines
- Only include items with lasting relevance (>1 day lifespan)
L3 — Long-term Archive (MEMORY.md)
Permanent knowledge base. Curated wisdom.
Contains: Core insights, 형님's teachings, identity principles, project histories, relationship notes.
Rules:
- Priority tagged:
[P1]critical,[P2]important,[P3]reference - Searchable tags:
<!-- [태그명] -->for grep - Remove outdated entries periodically
- Only promote items that passed the "will this matter in a month?" test
Promotion Flow
Daily events → L1 (today)
↓ (end of day)
memory/YYYY-MM-DD.md (archive)
↓ (significant items)
L2 (weekly digest)
↓ (lasting insights)
L3 (permanent)
Promotion Criteria
L1 → L2: Decision that affects future work, insight worth remembering beyond today, relationship change, project milestone.
What ships with it
3 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.
- 7d ago First seen · 290 lines · 100 tokens per session scan A cafde98dc431
memory-system is a skill published in the GitHub repository mupengi-bot/mupengism (10 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 2,043 once invoked, about $0.0005 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
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
learning-capture
Log corrections, errors, and discoveries to orbital/LESSONS.md so future sessions avoid repeating mistakes.
obsidian
A skill for working with an Obsidian vault, which is a folder of Markdown notes used as a personal knowledge base. It covers creating, extending, searching, and organizing notes, including links, tags, folders, and daily entries.
channel-canvas
How to work with a channel's standing project context — the "Archie" canvas a team pins in a channel — and with the channel's pinned-messages index. Load this when a channel has project context attached (presented to you as channel project context), when a pinned-messages index is in front of you or one of its lines…