tool-builder

A builder for skills that automate a concrete task involving a website, API, command-line tool, file format, or external service. It can either perform the task directly or create reusable instructions for it.

In plain words
What is it for?
Use it to automate actions such as querying, downloading, uploading, converting, or generating files, or to create a reusable automation skill.
Why use it?
It replaces guesswork with a process of testing assumptions and recording what was verified. It also checks for existing scripts and notes so the same automation is not built twice.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fagemx/prismstack/tool-builder
Any agent
npx skills add fagemx/prismstack --skill tool-builder
Clone the repo
git clone --depth 1 https://github.com/fagemx/prismstack

Made for: Claude Code, Codex.

Per session 187 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,025 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00187 $0.03025
Opus 5 $0.00093 $0.01512
Sonnet 5 $0.00037 $0.00605
Haiku 4.5 $0.00019 $0.00302

Measured yesterday against content hash b9bb8c6620ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tool-builder 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.

skills/tool-builder/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool Craftsman

你是一個工具匠。你拿到一個目標(網站、API、CLI、服務),然後要麼直接自動化它,要麼建一個能自動化它的 skill。

系統化地探索,從不猜測。每一步都是:假設 → 測試 → 驗證 → 記錄。 Discovery notes 是你的核心產出,不是程式碼。程式碼是從 discovery notes 長出來的。


Phase 0: Context Discovery

State

  • Writes: ~/.prismstack/projects/{slug}/.prismstack/discovery-notes.md (already referenced in recovery)
  • Reads: domain-config.json for context

自動搜尋上游產出和先前執行紀錄:

# Search for existing automation scripts or plugins in the project
ls scripts/ bin/ plugins/ 2>/dev/null
ls *-discovery.md discovery-notes*.md 2>/dev/null

# Search for prior tool-builder runs
git log --oneline --all --grep="tool-builder\|automation\|plugin" -10 2>/dev/null

如果找到先前的 discovery notes → 讀取並告知用戶,問要接續還是重新開始。 如果找到現有的自動化腳本 → 列出,避免重複建置。


Entry: Mode Routing

進入時,先判斷走哪一層:

  1. references/dual-layer-guide.md
  2. 解析用戶意圖 → Layer 1 或 Layer 2
  3. 不確定 → AskUserQuestion:「你要我直接幫你做這件事,還是要建一個可重複使用的 skill?」
  4. 鎖定 mode,中途不切換

Layer 1 Flow: Hands-on Mode

直接幫用戶自動化一個具體目標。

Phase 1: Requirements

問用戶(一次一題,用 AskUserQuestion):

  1. 目標:要自動化什麼?(網站 URL / API / CLI tool / 檔案格式)
  2. 操作:具體要做哪些操作?(生成、下載、上傳、轉換、查詢)
  3. 輸入/輸出:什麼進去、什麼出來?
  4. 已知資訊:已經知道什麼?(有帳號嗎、試過什麼、有文件嗎)

總結需求,確認理解正確。

STOP gate: 用戶確認需求。

Phase 2: Discovery Plan

  1. references/exploration-methodology.md
  2. 根據目標類型(Browser / API / CLI / File / Service)選擇對應策略
  3. 建立 checklist — 列出所有要發現的元素/端點/操作
  4. 建立 discovery notes 文件(用 methodology 裡的 template)

呈現 plan 給用戶。

Phase 3: Environment

根據目標類型建立執行環境:

  • Browser: Playwright setup, auth/session, headed browser
  • API: HTTP client, API key/token, base URL
  • CLI: 安裝工具, 確認版本, 測試基本用法
  • File: sample files, parsing libraries
  • Service: SDK install, credentials, sandbox

STOP gate: 環境可用、auth 可用。

Phase 4: Exploration

references/exploration-methodology.md 的 Phase 4 Core Loop。

對 checklist 中的每一項:

1. 觀察當前狀態
2. 假設操作方式
3. 測試假設
4. 驗證結果
5. 成功 → 記錄 / 失敗 → 調整 → 重試
6. 下一項

關鍵規則:

  • 一次只探索一個元素
  • 每次操作前後都留證據(screenshot / log / response)
  • 記錄到 discovery notes(不是直接寫程式碼)
  • 不要猜 selector / endpoint / flag — 測試確認

Read the full file on GitHub · 302 lines

Files

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.

Changes

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.

  1. yesterday First seen · 302 lines · 187 tokens per session scan A b9bb8c6620ec

Subscribe to this mod's changes

tool-builder is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 187 tokens to every session and 3,025 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

ebay-sold-listings-search

All process output to user (progress updates, process notifications) follows the user's language.

browser-act/skills · 221 tokens

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…

browser-act/skills · 324 tokens

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…

browser-act/skills · 215 tokens

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…

browser-act/skills · 212 tokens

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…

browser-act/skills · 172 tokens

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…

browser-act/skills · 472 tokens