transmute-framework CLAUDE.md

Repository instructions for working on Transmute, a Claude Code plugin whose markdown prompts and shell hook drive a 25-stage process from business plan to deployed product.

In plain words
What is it for?
Use them when changing the plugin: identify the right stage, run that stage in a test project, and verify the edited layout and documented commands.
Why use it?
They explain the repository’s structure, commands, and rules so edits can be checked correctly without looking for a build system or application source code.

Instructions file

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 instructions/voxtechnologies/transmute-framework/claude-md
Clone the repo
git clone --depth 1 https://github.com/VoxTechnologies/transmute-framework
Per session 1,167 This file is loaded in full into every session.
When invoked 1,167 The same file — it is already loaded in full.
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 $0.01167 $0.01167
Opus 5 $0.00583 $0.00583
Sonnet 5 $0.00233 $0.00233
Haiku 4.5 $0.00117 $0.00117

Measured 3d ago against content hash a3d42b41b04d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

transmute-framework CLAUDE.md 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 3d 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.

CLAUDE.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repository is

A Claude Code plugin, not an application. Every file is markdown prompt engineering plus one bash hook script. No source code, no package.json, no build step, no dependency install, no automated test suite.

The plugin drives a 25-stage pipeline (23 automated skills, 2 manual stages) that turns a business plan into a deployed product. Its doctrine is the Full-Build Approach: every feature in the plan gets built, and P0→P3 sets build order, never build scope. Reject any edit that introduces MVP-style deferral, phasing, or feature cutting.

The plugin is named transmuter; the repo and framework are named "Transmute". Commands are therefore /transmuter:cast and /transmuter:<stage>. That mismatch shipped as a user-facing bug in v3.0.0 — every documented command matched no installed plugin until v3.0.1 fixed it.

Commands

Nothing to build or lint. To validate a change:

# Load the plugin for one session, from inside a test project directory
claude --plugin-dir /path/to/transmute-framework
# Then run the stage you edited
/transmuter:cast <stage-name>     # e.g. /transmuter:cast brd
/transmuter:<stage-name>          # equivalent direct form

A test project needs a business plan at plancasting/businessplan/*.md (or .pdf). Stage 0 (tech-stack) must run before Stage 1, since the prerequisite hook and most skills read plancasting/tech-stack.md.

plancasting/ is an artifact directory of generated projects. It never exists in this repository.

Layout

Path Role
commands/cast.md /transmuter:cast entry point and stage alias table
agents/transmute-pipeline.md Pipeline orchestrator: Stage Skills Map, gate logic, progress state
agents/*.md (6 others) Teammates spawned by skills, never invoked directly
skills/<stage>/ One directory per stage, two-file pattern (below)
templates/ Files copied into generated projects
hooks/ Live gate-enforcement hook — not .claude-plugin/hooks/, which is stale

Read the full file on GitHub · 71 lines

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. 3d ago First seen · 71 lines · 1,167 tokens per session scan A a3d42b41b04d

Subscribe to this mod's changes

transmute-framework CLAUDE.md is an instructions file published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,167 tokens to every session, about $0.0058 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 instructions, from other repositories