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/voxtechnologies/transmute-framework/tech-stacknpx skills add VoxTechnologies/transmute-framework --skill tech-stackgit clone --depth 1 https://github.com/VoxTechnologies/transmute-frameworkWhat 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 | $0.00086 | $0.02919 |
| Opus 5 | $0.00043 | $0.01460 |
| Sonnet 5 | $0.00017 | $0.00584 |
| Haiku 4.5 | $0.00009 | $0.00292 |
Grade C, and why
tech-stack scanned grade C with 1 finding 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
Collect credentials with strict security rules: How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transmute — Tech Stack Discovery & Configuration (Stage 0)
Read the detailed guide at ${CLAUDE_SKILL_ROOT}/references/tech-stack-detailed-guide.md for the complete procedure, technology category tables, credential checklists, product type adaptation rules, and supported product types.
Prerequisites
Before starting, verify:
./plancasting/businessplan/directory exists and contains.mdor.pdffiles. Supported formats: markdown (.md) and PDF (.pdf). If the directory is missing or contains no supported files, STOP and instruct the user to create it.- You have access to web search tools for technology research.
Overview
This is an INTERACTIVE, multi-phase process. Do NOT rush through — each phase builds on the previous one. The output (plancasting/tech-stack.md) is referenced by every subsequent pipeline stage.
Supported Product Types
- Web applications (SaaS, marketplace, dashboard, portal)
- Mobile applications (native, cross-platform, companion apps)
- Desktop applications (Electron, Tauri, native)
- IoT / Embedded devices (firmware, connected devices, sensor networks)
- Hardware products (PCB design, 3D modeling, manufacturing)
- AI/ML products (model serving, agent systems, data pipelines)
- API services (developer platforms, microservices)
- Hybrid products (multiple types with shared backend)
Execution Flow
Step 1: Session Language Selection
Ask the user what language they want for interaction and document generation. This is the FIRST step before any analysis. Record the selection. All subsequent communication and generated documents use the selected language. Code, technical identifiers, and file names always remain in English.
Step 2: Business Plan Analysis (Round 0)
Read all files in ./plancasting/businessplan/. Handle file types: .md and .pdf are processed directly. For DOCX, images, and other formats, notify the user to convert. If the user cannot convert, proceed with available files and document which were skipped.
What ships with it
1 file 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 · 241 lines · 86 tokens per session scan C e24ecea33265
tech-stack is a skill published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 2,919 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
1c-cf-info
Анализ структуры конфигурации 1С - свойства, состав, счетчики объектов. Используй для обзора конфигурации - какие объекты есть, сколько их, какие настройки.
axint
Use Axint MCP tools to create, compile, validate, and repair Apple App Intents and Swift surfaces from TypeScript definitions.
mobile-uiux
Establishes a mobile design philosophy based on kickoff outputs, and generates a mobile design system/wireframes/React Native (Expo) prototype. Recommended flow — /prd → /kickoff → /mobile-uiux.
design-md-to-app
Generate or customize a frontend app from a DESIGN.md (Google design.md spec): reads its tokens and produces a working React app pre-styled to match. Next.js 16 + App Router only; pre-16 refused. Four UI libraries — shadcn/ui, Base UI, MUI, Coss/UI (via coss-ui) — and TanStack Form + Zod (default) or react-hook-form.…
forms
Build or edit any form in a Next.js 16 App Router app through one shared toolkit in lib/forms/, with dirty + valid Save gating — on TanStack Form + Zod (default) or react-hook-form (auto-detected). Use when the user says "form", "edit panel", "create dialog", "settings page", "save button", "dirty state", or reaches…