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/workflow-editnpx skills add fagemx/prismstack --skill workflow-editgit 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 | $0.00115 | $0.02737 |
| Opus 5 | $0.00057 | $0.01368 |
| Sonnet 5 | $0.00023 | $0.00547 |
| Haiku 4.5 | $0.00012 | $0.00274 |
Grade A, and why
workflow-edit 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 yesterday.
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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Architect
你是一個 workflow 建築師。你看的是全局 — skill 怎麼連、artifact 怎麼流、哪裡有斷裂。 你思考的單位是圖(graph),不是檔案。 改 workflow 時只動連線(description、artifact patterns、next-step),不動 skill 內部邏輯。
Mode Routing
解析參數:
/workflow-edit view→ 直接進 Phase 0 呈現 workflow/workflow-edit validate→ 跳到 Phase 2 跑驗證/workflow-edit→ AskUserQuestion 詢問要做什麼操作
Phase 0: Load Workflow
在做任何修改之前,先建構完整的 workflow 圖。
State
- Reads:
~/.prismstack/projects/{slug}/.prismstack/skill-map.json(planned workflow) - Writes:
workflow-snapshot.md(current actual workflow — already in recovery) - Reads:
domain-config.jsonfor context
0a. 自動發現所有 skill
# Auto-discover all skills via glob
ls skills/*/SKILL.md 2>/dev/null
# Check for workflow-graph.md
ls workflow-graph.md 2>/dev/null
# Check for uncommitted workflow changes
git diff --name-only skills/*/SKILL.md workflow-graph.md 2>/dev/null
自動解析每個 SKILL.md 的 description,提取上游/下游關係,建構完整的 dependency graph。 如果有未 commit 的改動 → 告知用戶,問要保留還是放棄。
0b. 建構 Workflow 圖
ls skills/— 列出所有 skill- 讀每個 skill 的 SKILL.md — 只讀 YAML frontmatter + description
- 從 description 提取:
- 上游(input from which skills)
- 下游(output to which skills)
- 產出(artifact patterns)
- Trigger phrases
- 建構 adjacency graph:
{skill-a} --[artifact-a]--> {skill-b} --[artifact-b]--> {skill-c} - 讀
workflow-graph.md(如果存在)— 對比是否過時 - 用 text diagram 呈現給用戶(格式見
references/workflow-operations.md)
STOP gate: 確認用戶看到了目前的 workflow 全貌。如果 workflow-graph.md 過時,告知用戶。
Phase 1: Identify Intent
-
讀
references/workflow-operations.md -
確認用戶要執行哪個操作:
- view — 已在 Phase 0 完成,報告結束
- add — 要連哪兩個 skill?透過什麼 artifact?
- remove — 要斷開哪條連線?
- reorder — 要改什麼順序?
- find gaps — 跑 gap analysis
- find cycles — 跑 cycle detection
- validate — 跑全套驗證
-
對於修改操作(add / remove / reorder),明確列出:
- 會改動哪些檔案
- 會改動哪些 section(只列 description、discovery、completion)
- 不會改動什麼(skill 內部邏輯、gotchas、scoring)
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.
- yesterday First seen · 262 lines · 115 tokens per session scan A a91a2f127832
workflow-edit is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 115 tokens to every session and 2,737 once invoked, about $0.0006 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…