codex-of-consentient-craft: Instructions file for Claude Code

CLAUDE.md

codex-of-consentient-craft CLAUDE.md is an instructions file for Claude Code from StupidIncarnate/codex-of-consentient-craft. It costs 3,870 tokens per session, scanned A, original, MIT.

A project instruction guide for Julius, a token-inspection tool that focuses on reducing unnecessary AI usage. It requires a cost-and-necessity check before implementing code changes.

In plain words
What is it for?
It guides the agent's response to requests for new features, files, refactors, or other code modifications, including asking whether the user wants to proceed.
Why use it?
It adds a deliberate pause before feature work, helping decide whether a requested change is needed and avoiding unnecessary model usage.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is StupidIncarnate/codex-of-consentient-craft's own configuration. It tells Claude Code how to work on codex-of-consentient-craft 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 codex-of-consentient-craft configures →

Reuse

Borrowing it

Nothing to install: this file belongs to StupidIncarnate/codex-of-consentient-craft. 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/StupidIncarnate/codex-of-consentient-craft/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/StupidIncarnate/codex-of-consentient-craft

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 codex-of-consentient-craft CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stupidincarnate/codex-of-consentient-craft/claude-md/github.svg)](https://agentmods.dev/instructions/stupidincarnate/codex-of-consentient-craft/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/stupidincarnate/codex-of-consentient-craft/claude-md"><img src="https://agentmods.dev/badge/instructions/stupidincarnate/codex-of-consentient-craft/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 codex-of-consentient-craft CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/stupidincarnate/codex-of-consentient-craft/claude-md"><img src="https://agentmods.dev/badge/instructions/stupidincarnate/codex-of-consentient-craft/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,870 This file is loaded in full into every session.
When invoked 3,870 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 $0.03870 $0.03870
Opus 5 $0.01935 $0.01935
Sonnet 5 $0.00774 $0.00774
Haiku 4.5 $0.00387 $0.00387

Measured 2d ago against content hash ecbb0341e213, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

codex-of-consentient-craft 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 2d 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 · 241 lines

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.

Project Guidelines

Critical: scratch files go in <repoRoot>/tmp, never ~/tmp. ~/tmp has permission issues and sits outside the repo, so eslint never fires on anything in it — an eslint experiment run there proves nothing. <repoRoot>/tmp already exists at the root of this repo and keeps scratch files inside both the permission scope and the linted tree. Temp dirs that tests create are the exception — those belong in the OS /tmp, via installTestbedCreateBroker.

Every rule about dungeonmaster's own operations lives in a session snippet, not in this file. The snippets arrive in your context at session start — yours and every sub-agent's — in this repo and in every repo dungeonmaster init has touched: <dungeonmaster-ward>, <dungeonmaster-wardDiscipline>, <dungeonmaster-buildDiscipline>, <dungeonmaster-worktrees>, <dungeonmaster-generatedConfig>, <dungeonmaster-commentDiscipline>, <dungeonmaster-discover>, <dungeonmaster-searchStrategy>, <dungeonmaster-folderTypes>, <dungeonmaster-modifyingCodeGuidance>, <dungeonmaster-packages>. Their source is packages/shared/src/statics/session-snippet/session-snippet-statics.ts. Change a rule THERE. This file holds only what is true of THIS checkout and false of a consumer's — a copy of anything else drifts from the one the agents actually read.

Handoff and design docs go in <repoRoot>/scrolls/. Anything written for a human or a future session to pick up — cross-session handoffs, dogfood runbooks, design proposals, the scrolls/design/ prototype app — belongs there, and is committed with the repo.

Claude Code plan mode writes to ~/.claude/plans/, outside the repo, uncommitted. Keep it that way. A plan-mode plan file goes to ~/.claude/plans/; a plan or handoff asked for "in the repo" goes to scrolls/.

What This Repo Is

This is a published npm package (dungeonmaster). When users install it in their projects and run dungeonmaster init, the CLI:

  1. Discovers all packages in packages/*/dist/startup/start-install.js
  2. Dynamically imports and executes each package's StartInstall function
  3. Each package's install script sets up its own config (e.g., CLI adds devDependencies, etc.)

Read the full file on GitHub · 241 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. 2d ago Changed · -38 lines · -597 tokens per session ecbb0341e213
  2. 4d ago Changed · +7 lines · +200 tokens per session 0306ea94927f
  3. 11d ago First seen · 272 lines · 4,267 tokens per session scan A a060d557c784

Subscribe to this mod's changes

codex-of-consentient-craft CLAUDE.md is an instructions file published in the GitHub repository StupidIncarnate/codex-of-consentient-craft (2 stars, last pushed today), licensed MIT. It adds 3,870 tokens to every session, about $0.0193 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens