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 instructions/voxtechnologies/transmute-framework/claude-mdgit 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 | $0.01167 | $0.01167 |
| Opus 5 | $0.00583 | $0.00583 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00117 | $0.00117 |
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.
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 |
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.
- 3d ago First seen · 71 lines · 1,167 tokens per session scan A a3d42b41b04d
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.
Other instructions, from other repositories
Perigon.CLI copilot-instructions.md
Instructions for AterDev/Perigon.CLI, covering github copilot instructions, general guidelines, 技术栈, 项目结构与分层 and 代码风格约定.
arduino-skills AGENTS.md
Instructions for wedsamuel1230/arduino-skills: The canonical skill content is under skills/. Select the smallest matching SKILL.md, and load references/ or docs/ only when the skill points to it.
wgm AGENTS.md
Instructions for agent-frontier/wgm, covering agents.md, build & run, validate (backpressure), operational notes and codebase patterns.
harmont-cli CLAUDE.md
Instructions for harmont-dev/harmont-cli, covering testing, documentation, dsl and keep the sdk, hm init templates, and docs in sync.
HarnessSmith CLAUDE.md
Instructions for EpisodeYu/HarnessSmith, covering claude.md — harnesssmith 项目守则, 0. 协作模式与角色边界, 0.1 只能由人配置的环境(agent 不代劳), 1. think before coding and 2. thin first(薄优先 —— 本项目核心卖点,硬约束).
genesis-architect CLAUDE.md
Claude Code instructions for maioio/genesis-architect, covering genesis architect - claude code instructions, project structure, how this skill works, development workflow and key constraints (enforced in skill.md).