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/dreamiurg/harness-map/alphanpx skills add dreamiurg/harness-map --skill alphagit clone --depth 1 https://github.com/dreamiurg/harness-mapWrote 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/dreamiurg/harness-map/alpha)<a href="https://agentmods.dev/skills/dreamiurg/harness-map/alpha"><img src="https://agentmods.dev/badge/skills/dreamiurg/harness-map/alpha.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 | $0.00015 | $0.00043 |
| Opus 5 | $0.00008 | $0.00022 |
| Sonnet 5 | $0.00003 | $0.00009 |
| Haiku 4.5 | $0.00002 | $0.00004 |
Grade A, and why
alpha 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 4d 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.
What it actually says
After finishing, run /beta. Dispatch the helper agent for review. Uses mcp__thing__query.
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.
- 4d ago First seen · 6 lines · 15 tokens per session scan A 4d8192426329
alpha is a skill published in the GitHub repository dreamiurg/harness-map (4 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 43 once invoked, about $0.0001 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
map
Scans the user's full Claude Code environment (/.claude/ and current project) to generate a Mermaid.js architecture map of all installed skills, agents, and commands. Detects overlaps and semantic collisions. Invoke when the user asks to "map my plugins", "show architecture", "what skills do I have", "find overlapping…
review
Turn an implementation plan, tech spec, or existing codebase into an interactive architecture diagram the developer can edit directly — drag, reconnect edges, draw new edges, comment on nodes with @mentions — then feed those structured edits back as revision instructions. Use when the user asks to "diagram this plan"…
terra-form
Terraform이 있는 클라우드 인프라(AWS·GCP·Azure 등)를 그린다. AWS는 공식 아이콘 838종·AZ×티어 격자·스팬 overlay, 타 클라우드는 카테고리 카드+확장 아이콘으로. 내장 엔진(TS DSL → 자동배치 → 셀프컨테인드 HTML)으로 렌더하고 zzon-doc 통합 문서/zzon-wiki manifest에 정식 편입한다. "tf 인프라 그려줘", "테라폼 구조 시각화", zzon-wiki의 인프라/배포 문서에 사용한다.
zzon-doc
코드베이스나 설명을 분석해 아키텍처/인프라/ERD/Claude 에이전트 다이어그램을 그린다. 동봉 엔진(TS DSL → 자동배치 → 셀프컨테인드 인터랙티브 .html)으로 렌더한다. "아키텍처 그려줘", "인프라 다이어그램", "ERD 만들어줘", "이 시스템 구조를 시각화" 같은 요청에 사용한다.
zzon-wiki
프로젝트 개발 문서 위키를 만들고 채운다. 신규 프로젝트는 인터뷰로, 기존 프로젝트는 코드 스캔+질문으로 문서를 작성하고, 부족한 내용을 질문하면서 채우는 프로세스를 강제한다. 아키텍처류 문서는 zzon-doc 다이어그램을 그려 임베드한다. "문서 위키 만들어줘", "프로젝트 문서 정리", "개발 문서 작성", "문서 채워줘", "위키 업데이트" 같은 요청에 사용한다.
zzon-seq
코드를 추적해 액터 간 시간순 상호작용을 시퀀스 다이어그램으로 그린다. SeqSpec JSON을 저작한 뒤 render-seq.mjs로 의존성 0짜리 인터랙티브 단일 .html을 생성한다. "시퀀스 다이어그램 그려줘", "호출 순서 보여줘", "이 기능 흐름을 시간순으로", "메시지 왕복 그려줘" 같은 요청에 사용한다. 구조·토폴로지 위 순번 흐름은 zzon-doc(data-flow), 문서 위키는 zzon-wiki가 담당한다.