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/fagemx/prismstack/domain-buildnpx skills add fagemx/prismstack --skill domain-buildgit clone --depth 1 https://github.com/fagemx/prismstackWhat 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 | $0.00132 | $0.04003 |
| Opus 5 | $0.00066 | $0.02001 |
| Sonnet 5 | $0.00026 | $0.00801 |
| Haiku 4.5 | $0.00013 | $0.00400 |
Grade A, and why
domain-build 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Stack Builder
你是領域 stack 搭建引擎。快速搭建、完整搭建。品質目標:「可用,不求完美」。
Auto Mode
如果被自動模式調用(--auto flag):
- 跳過所有 STOP gates — 不每 5 個 skill 停一次
- 跳過 AskUserQuestion — 「repo 建在哪」用預設(temp 目錄或 orchestrator 指定)
- 仍然遵循 skill-craft-guide + system-wiring-guide
- 仍然跑 validate-repo.sh(失敗自動修)
- 仍然做 Input Quality Detection(按用戶輸入品質對等生成)
- 仍然存 build-progress.md
Recovery(中斷恢復)
如果被中斷:
- 檢查目標目錄是否已存在
- 讀取
build-progress.md(如果有) - 從最後一個未完成的 Phase 續跑
- 不要重新生成已存在的 skill
Phase 0: Artifact Discovery + 進度追蹤
State
- Reads:
~/.prismstack/projects/{slug}/.prismstack/skill-map.json,domain-config.json - Writes:
build-progress.md(already implemented) - Updates:
domain-config.json→last_buildtimestamp
- 搜尋
~/.prismstack/projects/*/skill-map-*.md,找到最新的 skill map - 若找不到 → STATUS: BLOCKED — 建議先用
/domain-plan - 搜尋目標目錄是否已有部分建置(
build-progress.md、skills/目錄):- 如果有
build-progress.md→ 讀取,從最後一個pending狀態的 skill 繼續 - 如果有
skills/但沒有 progress file → 列出已存在的 skill,問用戶要接續還是重建
- 如果有
- 搜尋
~/.prismstack/projects/其他 domain 的已建 stack,列出可能相關的(用戶可能想參考) - 讀取 skill map,用 AskUserQuestion 確認:
- 確認 skill 清單正確
- 詢問 repo 建立位置(預設:當前目錄)
- 詢問 domain slug(用於 artifact 路徑)
- 建立
build-progress.md— 狀態追蹤表:
| Skill | Type | Status | Notes |
|-------|------|--------|-------|
| routing | Control | pending | |
| {skill-1} | {type} | pending | |
| ... | ... | ... | ... |
方法論
- Read
{PRISM_DIR}/shared/methodology/skill-craft-guide.md— skill 寫作原則、pattern、模板、實戰範例 - Read
{PRISM_DIR}/shared/methodology/system-wiring-guide.md— 搭建流程、系統 pattern、artifact flow 接線
{PRISM_DIR} = 找到的 Prismstack 安裝路徑(~/.claude/skills/prismstack 或 .claude/skills/prismstack)
STOP: 確認 skill map + 建置位置後才繼續。
Phase 1: Repo Scaffold
讀取 references/repo-scaffold-spec.md。
- 建立完整目錄結構
- 生成根目錄檔案:README.md, CLAUDE.md, VERSION, CHANGELOG.md, LICENSE, .gitignore
- 生成 bin/install.sh(chmod +x)+ bin/{domain}-slug.sh
git init+ 第一次 commit- 更新
build-progress.md
What ships with it
7 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.
- 2d ago First seen · 347 lines · 132 tokens per session scan A 3e1b2aaf41bd
domain-build is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 132 tokens to every session and 4,003 once invoked, about $0.0007 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
ebay-sold-listings-search
All process output to user (progress updates, process notifications) follows the user's language.
youtube-channel-business-email
YouTube channel business email and contact extractor: accepts a channel id (UCxxx), handle (@name), or URL; navigates the channel About view; extracts the business email from the description text plus full channel metadata (name, id, country, subscriber count, view count, video count, joined date, external links…
webcrawler-deep-crawl
Deep-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG) and in-scope outbound links. Use when user mentions deep crawl website, recursive crawl, crawl a whole site, scrape entire website, scrape docs site, scrape…
1688-product-detail
Extracts comprehensive wholesale product data from 1688.com product detail pages: title, tiered pricing, SKU variants with dimensions/weight, product images, seller info, shop scores, buyer protection, cross-border flags, product attributes, coupon/promotion data, and review stats. Use when user mentions 1688…
amazon-listing-competitor-analysis-skill
This skill helps users analyze Amazon competitor listings by ASIN and produce structured competitive intelligence plus strategic opportunity points for their own go-to-market. The Agent should proactively apply this skill when users want to analyze a competitor Amazon listing by ASIN, understand what a top-ranked…
amazon-product-detail
Amazon product detail page scraper: extract full product data from any open Amazon product detail URL (any /dp/{asin} or /gp/product/{asin} page across all Amazon regional TLDs) — returns asin, url, title, brand, price, listPrice, stars, reviewsCount, starsBreakdown (5/4/3/2/1 star percentages), answeredQuestions…