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/humanerd-drew/opencode-drewgent/session-pattern-archivernpx skills add humanerd-drew/opencode-drewgent --skill session-pattern-archivergit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWhat 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 | $0.00000 | $0.01879 |
| Opus 5 | $0.00000 | $0.00940 |
| Sonnet 5 | $0.00000 | $0.00376 |
| Haiku 4.5 | $0.00000 | $0.00188 |
Grade A, and why
session-pattern-archiver 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Pattern Archiver
Discord thread/대화가 종료되면 → Obsidian 판단 패턴 세션 노트로 자동 기록.
트리거
|| 유형 | 조건 | 우선순위 |
||------|------|----------|
|| Auto (thread_close) | Discord thread archived/locked → gateway event hook | highest |
|| Auto (thread_delete) | Discord thread deleted → gateway event hook | highest |
|| Auto (inactivity) | thread 2시간 미활동 → cron (c7041bc0a7b9) | 높음 |
|| Manual | /sync-obsidian 명령 | 항상 가능 |
출력 노트 형식
생성 위치: MEMORY/sessions/YYYY-MM/YYYY-MM-DD_project-title.md
# Session: [Thread Title]
**Date**: YYYY-MM-DD
**Trigger**: thread_close | thread_delete | inactivity | manual
**Participants**: @user1, @user2
## 🎯 의도 (Humanerd's Intent)
[이 작업을 왜 시작했는가 — Humanerd의 목적]
## 🧠 사고방식 (Reasoning Pattern)
[문제를 어떻게 풀어가려 했는가]
[왜 이 방법을 선택했는가]
## ⚖️ 가치 판단 (Value Judgments)
[이 상황에서 무엇을 우선시했는가]
[이것은重要하고 저것은 덜 중요하다 — 왜?]
## 👁️ 맹점 (Blind Spots)
[Humanerd가 자주 놓치는 것]
[에이전트가 대신 확인해줘야 할 것]
[과거 이 종류의 실수 기록]
## ✅ 결정 & 액션 (Decisions)
- **결정/액션 A** → 이유: ..., 다음: ...
## 🔗 관련 노트
`[[projects/X]]`, `[[skills/Y]]`, `[[sessions/prior-session]]`
## 📋 Follow-ups
- [ ] [todo by when - who]
## Meta
**Archived**: YYYY-MM-DD HH:MM
**Pattern completeness**: full | partial | inferred
Clarify 질문 (비동기, Discord DM)
inactivity / manual 트리거 → Clarify 전송 (이전 버전) 2026-04-13 이후: 모든 트리거에서 Clarify DM 비활성화 — "세션패턴 정리는 나에게 묻지 말고 알아서 하기" 지시 반영. 모든 archive는 즉시 Obsidian 노트 생성만 수행.
📝 세션 패턴 정리해드릴게요 — 30초만 답변주세요:
🎯 **의도**: 이 작업의目的是?
⚖️ **가치**: 무엇을優先했나요?
👁️ **맹점**: 놓치기 쉬운 것은?
24시간 무응답 → 부분 정보로 노트 생성 (completeness=inferred)
thread_close / thread_delete 이벤트에서는 Clarify 생략 — 즉시 아카이브 (사용자 지시: "세션패턴 정리는 나에게 묻지 말고 알아서 하기")
Backlink 규칙
생성 후 projects/ 노트 업데이트:
- thread topic과 관련된
[[projects/X]]검색 - 해당 프로젝트 노트 하단에
## Sessions\n- [[sessions/YYYY-MM-DD_title]]추가 - 없으면
[[projects/uncategorized]]에 추가
사용법
/sync-obsidian # 현재 thread 수동 동기화
/sync-obsidian [thread_id] # 특정 thread 동기화
/sync-obsidian --project=X # 프로젝트별 세션 모두 동기화
What ships with it
1 file 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 · 188 lines · 0 tokens per session scan A 7452a4b46305
session-pattern-archiver is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,879 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.