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/devswha/oh-my-gajae-code/preset-packnpx skills add devswha/oh-my-gajae-code --skill preset-packgit clone --depth 1 https://github.com/devswha/oh-my-gajae-codeWrote 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/devswha/oh-my-gajae-code/preset-pack)<a href="https://agentmods.dev/skills/devswha/oh-my-gajae-code/preset-pack"><img src="https://agentmods.dev/badge/skills/devswha/oh-my-gajae-code/preset-pack.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 | $0.00084 | $0.01740 |
| Opus 5 | $0.00042 | $0.00870 |
| Sonnet 5 | $0.00017 | $0.00348 |
| Haiku 4.5 | $0.00008 | $0.00174 |
Grade A, and why
preset-pack 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preset Pack (omg 최종 프리셋 설치)
목적: 확정된 프리셋 2개(daily=사람 세션 / agent=무인 자율 세션)를 사용자
~/.gjc/agent/models.yml에 명시 호출 시에만 병합한다. 정본은 스위트의
references/preset-pack.yml이며, 이 스킬은 그 블록을 이름 단위로 반영하는 절차다.
좌석표 (한눈)
| 좌석 | daily (사람) | agent (무인) |
|---|---|---|
| default | fable-5:medium | sol:medium |
| planner | k3:high | sol:high |
| executor | terra:xhigh | terra:xhigh |
| architect | opus-4-8:medium | opus-4-8:medium |
| critic | opus-4-8:high | opus-4-8:high |
daily— 대화 세션 상주 기본. 주력 fable은 보안 주제에서 클램프로 세션이 죽을 수 있다.agent— 무인 자율 러닝 계약: 주력이 Codex 창(sol)이라 사람 세션의 Claude 창과 쿼터가 분리되고 클램프 무풍. 제작(OpenAI) ↔ 심사(Anthropic) 완전 분리. 클램프로 죽은 세션의 복구 프리셋을 겸한다:gjc -r <세션ID> --mpreset agent.- v1의
deep/sec는 폐지됨(2026-07-20 하코 확정) — 폐지 근거는 정본 yml 하단 기록 참조.
절차
install (기본)
- 정본 위치 결정:
references/preset-pack.yml은 다음 순서로만 해석한다.- 새 프로젝트 binding
<cwd>/.gjc/runtimes/oh-my-gajae-code/root - 새 user binding
~/.gjc/agent/runtimes/oh-my-gajae-code/root - 읽기 전용·기간 한정 compatibility fallback인 기존
<cwd>/.gjc/runtimes/oh-my-gjc/root프로젝트 binding, 이어서~/.gjc/agent/runtimes/oh-my-gjc/rootuser binding - 정확한 현재 checkout
plugins/oh-my-gajae-code/references/preset-pack.yml각 binding은 절대·단일행·canonical root를 담은 일반 파일이어야 하며, binding 또는 그 경로 구성요소·asset·asset 디렉터리에 symlink가 없어야 한다. 하나라도 존재하지만 malformed, symlinked, non-canonical, control-character-containing, multiline, 또는 asset-missing이면 이후 binding/check-out으로 넘어가지 않고 fail-closed한다. 기존 compatibility binding은 읽기만 하며 쓰거나 지우지 않고, user state도 그 이전에는 수정하지 않는다. 모두 없을 때도 정확한 checkout asset만 허용한다. 바인딩·파일 오류면 병합하지 말고https://raw.githubusercontent.com/devswha/oh-my-gajae-code/main/install.sh의 하드닝된 루트 installer를 재실행하도록 안내한다.
- 새 프로젝트 binding
- 백업:
cp ~/.gjc/agent/models.yml ~/.gjc/agent/models.yml.bak-$(date +%s)(파일이 없으면profiles:한 줄짜리 새 파일 생성부터). - 이름 단위 병합: 정본의
daily/agent블록만 사용자profiles:아래에 추가하거나 같은 이름을 교체한다. 다른 프로파일·최상위 키는 절대 건드리지 않는다. - 폐지분 정리(조건부): 사용자
profiles:에deep/sec가 있으면, 정본 하단의retired_v1_profilesfixture와 파스 동등성(YAML 파싱 결과가 좌석까지 완전 동일)으로 비교해 일치할 때만 백업이 있는 상태에서 함께 제거한다. 한 좌석이라도 다르면 사용자 수정본이므로 건드리지 않고 보고만 한다. fixture가 없는 정본(구버전)이면 폐지분 정리를 건너뛴다(fail-closed). - 검증: YAML 파스 확인 후 각 프리셋 활성 스모크 —
GJC_NOTIFICATIONS=0 GJC_SDK_DISABLE=1 gjc --mpreset <p> -p --no-session --no-tools "Reply OK". 실패하면 백업 복원 절차를 안내한다. - 결과 보고: 병합·제거된 프리셋 이름, 백업 경로, 스모크 결과, 활성화 커맨드
(사람 세션
gjc --mpreset daily --default/ 무인 발주gjc --mpreset agent).
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.
- 6d ago First seen · 82 lines · 84 tokens per session scan A 7e2dd7c50bef
preset-pack is a skill published in the GitHub repository devswha/oh-my-gajae-code (34 stars, last pushed 17d ago), licensed MIT. It adds 84 tokens to every session and 1,740 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…