Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/scroogy-dev/scroogy-agent-skillsnpx agentmods add skills/scroogy-dev/scroogy-agent-skills/ai-workspace-directoryWrote 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/scroogy-dev/scroogy-agent-skills/ai-workspace-directory)<a href="https://agentmods.dev/skills/scroogy-dev/scroogy-agent-skills/ai-workspace-directory"><img src="https://agentmods.dev/badge/skills/scroogy-dev/scroogy-agent-skills/ai-workspace-directory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/scroogy-dev/scroogy-agent-skills/ai-workspace-directory"><img src="https://agentmods.dev/badge/skills/scroogy-dev/scroogy-agent-skills/ai-workspace-directory.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00099 | $0.05664 |
| Opus 5 | $0.00049 | $0.02832 |
| Sonnet 5 | $0.00020 | $0.01133 |
| Haiku 4.5 | $0.00010 | $0.00566 |
Grade A, and why
ai-workspace-directory 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 9d 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
개요
멀티 repo가 한 워크스페이스 아래 모여있는 환경에서, 워크스페이스 루트의 로비 .ai/AI-CONTEXT.md 를 생성하거나 진단·재구성하는 스킬입니다.
ai-workspace(floor 측, 각 repo의 .ai/ 전체 구조 담당)의 자매 스킬이며, 빌딩의 안내판(directory) 역할을 합니다. 로비는 floor 안내도를 가리키는 메타 라우터일 뿐 도메인 콘텐츠를 보유하지 않습니다.
산출물의 본질
- 포함: 라우팅·색인 (어디로 가야 할지 알려주는 안내판)
- 금지: 도메인 지식 본문, 코드 스니펫, floor 상세 목차 — 이건 floor의 책임
파일 경로 규약
| 대상 | 경로 | 담당 스킬 |
|---|---|---|
| 로비 (building 안내판) | <워크스페이스 루트>/.ai/AI-CONTEXT.md |
이 스킬 |
| floor 안내도 (층별 안내도) | <워크스페이스 루트>/<repo>/.ai/AI-CONTEXT.md |
ai-workspace |
규약: 모든 AI-CONTEXT.md는 각자의 .ai/ 디렉토리 안에 있습니다. 프로젝트 루트에 직접 배치하지 않습니다.
대전제 (절대 위배 금지)
- 소스 코드가 무조건 SSoT다.
- markdown은 코드를 가리키는 지도이지 코드의 사본이 아니다.
- 로비는 라우터지 콘텐츠가 아니다. 도메인 지식 본문은 로비에 들어가지 않는다.
- 정보 충돌 시 우선순위: 소스 코드 > 각 repo 안내도 > 이 안내도(상위 워크스페이스).
- 설계 원칙: 컨벤션 우선 (CoC). 멀티 repo는
<상위 워크스페이스>/<repo>컨벤션으로만 지원한다. 각 repo가 어느 상위 워크스페이스에 속하는지는<repo>/../.ai/AI-CONTEXT.md존재로 자동 판정하며, repo 측 안내도에 역참조 메타 필드(building/lobby등)를 두지 않는다 (YAGNI). 컨벤션을 벗어난 구조는 지원하지 않는다.
관련 skill
ai-workspace(자매): 각 floor의.ai/전체 구조와 floor 안내도<repo>/.ai/AI-CONTEXT.md를 생성·갱신합니다. 이 스킬은 그 위에서 building 안내판 역할을 하는 로비를 다룹니다.- 양방향 도메인 동기화:
ai-workspace-directory는 로비의Repos표에 각 repo의path/domain/keywords/status를 적고,ai-workspace는 각 repo의 안내도## 프로젝트 도메인표에 동일한domain/keywords를 적습니다. 두 값은 1:1 동기화 대상입니다 (update모드의 drift 메타 일치 검사가 이를 점검). 역참조(repo → 상위 워크스페이스)는 별도 메타 필드 없이 CoC(<repo>/../.ai/AI-CONTEXT.md존재 자동 판정)로 처리합니다.
참조 문서
- 공통 규칙:
.ai/10_rules/context-loading.md— 있으면 따르며, 이미 적재되어 있으면 재로딩하지 않습니다. - 스킬 고유 추가 참조:
- 현재 워크스페이스 루트의 기존
.ai/AI-CONTEXT.md(있을 경우 —update모드 입력) - 각 floor의
<repo>/.ai/AI-CONTEXT.md(디스크 스캔으로 존재 여부만 확인 —status판정용)
- 현재 워크스페이스 루트의 기존
- 분리 참조 파일 (
references/— 해당 단계에 도달했을 때만 읽습니다):- standard-structure.md — 산출물 표준 섹션 구조 (필수 규칙·골격·섹션별 강제 규칙·repo
status의미). 산출물 형식의 단일 출처 — init-4단계, update-2단계에서 사용 - ssot-checklist.md — SSoT 위배 패턴 진단 체크리스트 — update-1단계에서 사용
- examples.md — update 모드 출력 형식 템플릿 + init/update 완성 예시
- standard-structure.md — 산출물 표준 섹션 구조 (필수 규칙·골격·섹션별 강제 규칙·repo
What ships with it
6 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.
- 9d ago First seen · 305 lines · 99 tokens per session scan A c46901452413
ai-workspace-directory is a skill published in the GitHub repository scroogy-dev/scroogy-agent-skills (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 99 tokens to every session and 5,664 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.