magnum-opus-skills: Instructions file for Claude Code

CLAUDE.md

magnum-opus-skills CLAUDE.md is an instructions file for Claude Code from HermeticOrmus/magnum-opus-skills. It costs 1,404 tokens per session, scanned A, original, MIT.

A seven-stage software-development workflow inspired by alchemy, used to guide major changes to a codebase.

In plain words
What is it for?
It helps plan substantial redesigns, long-accumulated codebase changes, post-acquisition integration, major version changes, and strategic product pivots.
Why use it?
It gives large transformations a deliberate sequence instead of treating them as a series of unrelated refactoring tasks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is HermeticOrmus/magnum-opus-skills's own configuration. It tells Claude Code how to work on magnum-opus-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything magnum-opus-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to HermeticOrmus/magnum-opus-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/HermeticOrmus/magnum-opus-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/magnum-opus-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for magnum-opus-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hermeticormus/magnum-opus-skills/claude-md/github.svg)](https://agentmods.dev/instructions/hermeticormus/magnum-opus-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hermeticormus/magnum-opus-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/hermeticormus/magnum-opus-skills/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for magnum-opus-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hermeticormus/magnum-opus-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/hermeticormus/magnum-opus-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,404 This file is loaded in full into every session.
When invoked 1,404 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01404 $0.01404
Opus 5 $0.00702 $0.00702
Sonnet 5 $0.00281 $0.00281
Haiku 4.5 $0.00140 $0.00140

Measured 12d ago against content hash 80431fc25dab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

magnum-opus-skills 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 12d 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 · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

The seven-stage Magnum Opus engineering workflow. Alchemy applied to software.

"Solve et coagula." — Dissolve and coagulate.

Tradeoff: bias toward intentional transformation over reactive refactoring. The stages provide structure for projects that need fundamental change, not surface tweaks.

The seven stages

# Stage Element Companion command Operation
1 Calcination 🜂 Fire /calcinate Burn what doesn't serve
2 Dissolution 🜄 Water /dissolve Let understanding flow
3 Separation 🜁 Air /separate Gold from dross
4 Conjunction Sacred marriage /conjoin Unite opposites
5 Fermentation 🜅 Decay + rebirth /ferment Trial by failure
6 Distillation Vapor /distill Refine to wisdom
7 Coagulation 🜍 Crystallization /coagulate Shape the final form

When to run the full pipeline

  • Project transformation (substantial change in direction)
  • Codebase that has accumulated 12+ months of accretion
  • Post-acquisition integration
  • Major version cuts (v1 → v2 with real changes)
  • Strategic pivots that change the project's purpose

Not for: feature work, bug fixes, routine refactoring.

Stage 1 — Calcination 🜂 (burn what doesn't serve)

Purpose: identify and remove what no longer aligns with declared intent.

  • Declare three-layer intent (Business + Architectural + Stylistic)
  • Scan for code rot, structural bloat, dependency bloat, doc/test bloat
  • Execute per-item with verify; auto-revert on failure
  • Output: smaller, more aligned codebase

Standalone repo: calcinate-skills.

Stage 2 — Dissolution 🜄 (let understanding flow)

Purpose: build a deep mental model after the burn. Without dissolution, you cleaned but didn't understand.

  • Walk the post-calcinate code
  • Trace data flow from entry points
  • Identify the bones — what's left because it's essential, vs. what's left because nobody touched it
  • Diagram the system in its new lighter form
  • Output: a system you can explain in one sentence

Read the full file on GitHub · 138 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. 12d ago First seen · 138 lines · 1,404 tokens per session scan A 80431fc25dab

Subscribe to this mod's changes

magnum-opus-skills CLAUDE.md is an instructions file published in the GitHub repository HermeticOrmus/magnum-opus-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,404 tokens to every session, about $0.0070 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