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/netwaif/loadout/configure-storenpx skills add netwaif/loadout --skill configure-storegit clone --depth 1 https://github.com/netwaif/loadoutWrote 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/netwaif/loadout/configure-store)<a href="https://agentmods.dev/skills/netwaif/loadout/configure-store"><img src="https://agentmods.dev/badge/skills/netwaif/loadout/configure-store.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 | $0.00212 | $0.01622 |
| Opus 5 | $0.00106 | $0.00811 |
| Sonnet 5 | $0.00042 | $0.00324 |
| Haiku 4.5 | $0.00021 | $0.00162 |
Grade A, and why
configure-store 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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md 구성 백화점 (loadout / configure-store)
작업 폴더 성격에 맞는 구성 조각을 카탈로그에서 골라 담아 설치한다.
직접 파일을 손으로 쓰지 말 것 — 반드시 이 스킬 폴더의 결정적 설치기 generator/store.py를 실행한다.
절차
- 카탈로그 제시 —
python3 "<이 스킬 폴더>/generator/store.py" --list출력 전문을 그대로 보여준다(요약·발췌 금지). 대상이 Codex(AGENTS.md)면--list --flavor codex로 — 품목 표시명이 codex 기준(예: 저비용 GPT 5.6)으로 나온다. - 대상 폴더·하네스 확인 — 어디에 설치할지 묻는다(정확한 경로 확인). 대상이 Codex(AGENTS.md) 폴더면
--flavor codex를 쓴다(기본은 claude=CLAUDE.md). 사용자가 명시하지 않고 대상 폴더에 AGENTS.md만 있으면 codex인지 확인한다. - 품목 선택 — 사용자가 텍스트로 고른다. 품목 목록을 옵션 선택 위젯(질문 UI)으로 띄우지 말 것 — 위젯은 옵션 개수 제한(예: 4개)이 있어 카탈로그가 조용히 잘린다. 규칙 안내: 같은 코너 품목은 함께 담을 수 없다(예: Fable5 단독 ↔ 멀티에이전트).
- 실행:
python3 "<이 스킬 폴더>/generator/store.py" --target "<대상폴더>" --pick <품목1,품목2> [--flavor codex] --yes - 결과 보고 — 배타 위반(exit 2)이면 위반 내용을 그대로 전달한다. "완료"는 exit 0일 때만.
- 멀티에이전트 포함 시 — multi-agent-starter 플러그인이 설치돼 있어야 한다(store가 그 init.py에 flavor 그대로 위임). 못 찾으면 설치 안내 후 중단. knot·요금가드도 카탈로그에서 담을 수 있다. knot 능동 스킬은 netwaif/knot 플러그인이 제공.
- 요금가드 × codex flavor — 조각 설치와 함께 동봉 워처(
files.codex/→ 대상_shared/guard/)가 자동 복사된다. loadout 단독으로 완결(starter 불필요). 이후 3단계 실행법은 조각 본문·_shared/guard/README.md참조.
반품 (remove)
"구성 빼줘", "조각 반품", "멀티로 갈아타줘"(코너 스왑) 요청 시:
python3 "<이 스킬 폴더>/generator/store.py" --target "<대상폴더>" --remove <품목1,품목2> [--pick <품목>] [--flavor codex] --yes
--pick과 병용하면 제거를 먼저 실행한다 — 같은 코너 갈아타기(예:--remove fable5-solo --pick multiagent)가 한 호출로 끝난다.- 마커 블록을 제거하고, 딸린 파일은 정본과 바이트 일치할 때만 삭제한다(사용자가 수정한 파일은 보존하고 안내). 사용자 데이터(SESSION.md 등)는 건드리지 않는다.
- guard(claude)는
.claude/settings.json의 coach --hook Stop 훅도 함께 제거된다(사용자 훅 보존). - multiagent는 반품 미지원(exit 2) — tasks/ 등 사용자 작업물이 얽혀 있어 수동 정리를 안내한다.
- 미설치 품목 반품은 안내 후 no-op(멱등). 카탈로그에서 빠진 옛 조각도 설치돼 있으면 반품 가능.
- 반품도 손으로 하지 말 것 — 마커 짝을 깨뜨리기 쉽다. 반드시
--remove로.
진단 (doctor)
"구성 점검해줘", "loadout doctor" 요청 시:
python3 "<이 스킬 폴더>/generator/store.py" --target "<대상폴더>" --doctor
What ships with it
31 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.
- generator/fragments/_TEMPLATE/fragment.md 241 B
- generator/fragments/_TEMPLATE/meta.json 196 B
- generator/fragments/_TEMPLATE/README.md 1.0 KB
- generator/fragments/agent-loop/files/prep/goal-prompt.template.md 587 B
- generator/fragments/agent-loop/files/prep/채점표.template.md 360 B
- generator/fragments/agent-loop/fragment.md 1.6 KB
- generator/fragments/agent-loop/meta.json 260 B
- generator/fragments/brief-output/fragment.md 1.2 KB
- generator/fragments/brief-output/meta.json 226 B
- generator/fragments/fable5-lowcost/fragment.codex.md 3.3 KB
- generator/fragments/fable5-lowcost/fragment.md 3.3 KB
- generator/fragments/fable5-lowcost/meta.json 361 B
- generator/fragments/fable5-solo/fragment.md 787 B
- generator/fragments/fable5-solo/meta.json 358 B
- generator/fragments/guard/files.codex/_shared/guard/codex_goal_watch.mjs 6.8 KB runs code
- generator/fragments/guard/files.codex/_shared/guard/README.md 3.5 KB
- generator/fragments/guard/fragment.codex.md 1.3 KB
- generator/fragments/guard/fragment.md 622 B
- generator/fragments/guard/hook.json 171 B
- generator/fragments/guard/meta.json 441 B
- generator/fragments/karpathy/fragment.md 3.4 KB
- generator/fragments/karpathy/meta.json 206 B
- generator/fragments/knot/fragment.md 415 B
- generator/fragments/knot/meta.json 507 B
- generator/fragments/multiagent/meta.json 263 B
- generator/fragments/no-yesman/fragment.md 2.4 KB
- generator/fragments/no-yesman/meta.json 273 B
- generator/fragments/session-handoff/files/SESSION.template.md 899 B
- generator/fragments/session-handoff/fragment.md 2.1 KB
- generator/fragments/session-handoff/meta.json 223 B
- generator/store.py 28 KB runs code
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.
- 5d ago First seen · 67 lines · 212 tokens per session scan A 5d1362b29f9b
configure-store is a skill published in the GitHub repository netwaif/loadout (19 stars, last pushed 15d ago), licensed MIT. It adds 212 tokens to every session and 1,622 once invoked, about $0.0011 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…