What is unworldly CLAUDE.md?

An instruction file for unworldly, a Python tool that records, replays, and audits AI-agent activity, including file changes and shell commands. It documents the project layout, commands, and development rules.

Guiding work on the recorder’s command-line interface, event tracking, risk scoring, integrity checks, tests, linting, and type checking.

It gives agents the repository context and rules needed to make changes consistently while preserving the project’s local-first recording and risk-checking approach.

How DilawarShafiq/unworldly configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to DilawarShafiq/unworldly. 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/DilawarShafiq/unworldly/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/DilawarShafiq/unworldly

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dilawarshafiq/unworldly/claude-md/github.svg)](https://agentmods.dev/instructions/dilawarshafiq/unworldly/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dilawarshafiq/unworldly/claude-md"><img src="https://agentmods.dev/badge/instructions/dilawarshafiq/unworldly/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dilawarshafiq/unworldly/claude-md"><img src="https://agentmods.dev/badge/instructions/dilawarshafiq/unworldly/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,892 This file is loaded in full into every session.

When invoked 2,892 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.

Model	Per session	Once invoked
Fable 5.1	$0.02892	$0.02892
Opus 5.5	$0.01157	$0.01157
Sonnet 5.5	$0.00578	$0.00578
Haiku 4.5	$0.00289	$0.00289

Measured 2mo ago against content hash b017e0a68964, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unworldly 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 2mo 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 · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Rules — Unworldly

Project Context

Unworldly is the flight recorder for AI agents. It records, replays, and audits everything AI agents do on your system — file changes AND shell commands.

Repo: https://github.com/DilawarShafiq/unworldly
Package: unworldly-recorder on PyPI
Version: 0.4.1 (live on PyPI + GitHub Release)
Main branch: master
Tech: Python 3.10+, click, watchdog, rich
Test: pytest | Lint: ruff | Types: mypy --strict
Constitution: .specify/memory/constitution.md (6 principles: Agent-Agnostic, Local-First Privacy, Zero Interference, Risk-First Design, CLI-First, Ship Small)

Source Layout

unworldly/
  cli.py             — CLI entry (click): watch, replay, report, verify, list/ls
  types.py           — WatchEvent, Session, AgentInfo, CommandInfo, RiskLevel
  risk.py            — File risk scoring (danger/caution/safe patterns)
  command_risk.py    — Command risk scoring (shell command patterns)
  command_monitor.py — Cross-platform process monitor (polls ps/wmic)
  config.py          — Config loader (.unworldly/config.json)
  integrity.py       — SHA-256 hash chain, session seal, verify
  agent_detect.py    — AI agent identity detection (8 agents)
  display.py         — Terminal output (ANSI colors, risk badges)
  session.py         — Session CRUD, incremental saving, hash chain
  watcher.py         — watchdog file watcher + command monitor integration
  replay.py          — Session playback with timing + list command
  report.py          — Terminal + markdown report generation
  hipaa_risk.py      — Optional HIPAA PHI detection module
  __init__.py        — Public API exports (v0.4.1)
tests/
  test_risk.py, test_command_risk.py, test_command_monitor.py
  test_session.py, test_integrity.py, test_agent_detect.py
  test_config.py, test_display.py, test_hipaa_risk.py

Key Rules

Sessions stored as JSON in .unworldly/sessions/
Events unified: file changes and commands share WatchEvent type
Risk pattern order: HIPAA (if enabled) → danger → safe → caution
Incremental session saving (every event) for crash resilience
Agent identity detected at session start (env vars → parent process → process list)
Auto-commit after completing work (user preference)

Read the full file on GitHub · 255 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.

2mo ago First seen · 255 lines · 2,892 tokens per session scan A b017e0a68964

Subscribe to this mod's changes

unworldly CLAUDE.md is an instructions file published in the GitHub repository DilawarShafiq/unworldly (10 stars, last pushed 26d ago), licensed MIT. It adds 2,892 tokens to every session, about $0.0116 per session on Opus 5.5. 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.

AI Safety ai ai-agents cli cybersecurity devtools

unworldly CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
unworldly CLAUDE.mdDilawarShafiq/unworldly	Instructions file	10	26d ago	MIT	A	2,892	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

unworldly: Instructions file for Claude Code