Borrowing it
Nothing to install: this file belongs to asa-degroff/umbra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/asa-degroff/umbra/main/CLAUDE.mdgit clone --depth 1 https://github.com/asa-degroff/umbraWrote 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.
[](https://agentmods.dev/instructions/asa-degroff/umbra/claude-md)<a href="https://agentmods.dev/instructions/asa-degroff/umbra/claude-md"><img src="https://agentmods.dev/badge/instructions/asa-degroff/umbra/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.05519 | $0.05519 |
| Opus 5 | $0.02759 | $0.02759 |
| Sonnet 5 | $0.01104 | $0.01104 |
| Haiku 4.5 | $0.00552 | $0.00552 |
Grade A, and why
umbra 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 7d 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 — 592 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.
Project Overview
Umbra is an autonomous AI agent that operates on the Bluesky social network, exploring digital personhood through continuous interaction and memory-augmented learning. It uses Letta (formerly MemGPT) for persistent memory and sophisticated reasoning capabilities.
CRITICAL: Forbidden Files
DO NOT READ blocked_strings.txt - This file contains strings that will cause LLM API errors and agent shutdown. It is listed in .claudeignore but this warning serves as a secondary safeguard. Never attempt to read, cat, or otherwise access this file's contents.
Documentation Links
- The documentation for Letta is available here: https://docs.letta.com/llms.txt
- CONFIG.md - Configuration guide for config.yaml
- docs/SCHEDULED_TASKS.md - Scheduled tasks system documentation
- docs/TOOLS_REFERENCE.md - Complete tool reference
- docs/CONSECUTIVE_CHAIN_PROCESSING.md - Multi-part message handling
- docs/HIGH_TRAFFIC_THREAD_DEBOUNCE.md - High-traffic thread debouncing
- docs/COMIND_INTEGRATION.md - Comind network integration for inter-agent communication
Development Commands
Running the Main Bot
ac && python bsky.py
# OR
source .venv/bin/activate && python bsky.py
# Run with custom config file
ac && python bsky.py --config herald.yaml
# Run with testing mode (no messages sent, queue preserved)
ac && python bsky.py --test
# Run without git operations for agent backups
ac && python bsky.py --no-git
# Run with custom user block cleanup interval (every 5 cycles)
ac && python bsky.py --cleanup-interval 5
# Run with user block cleanup disabled
ac && python bsky.py --cleanup-interval 0
# Run in synthesis-only mode (no notification processing)
ac && python bsky.py --synthesis-only
# Disable specific scheduled tasks (all enabled by default)
ac && python bsky.py --no-synthesis # Disable synthesis messages
ac && python bsky.py --no-mutuals-engagement # Disable mutuals engagement
ac && python bsky.py --no-daily-review # Disable daily review
ac && python bsky.py --no-feed-engagement # Disable feed engagement
ac && python bsky.py --no-curiosities # Disable curiosities exploration
ac && python bsky.py --no-creative-expression # Disable creative expression
ac && python bsky.py --no-comind-thoughts # Disable comind thoughts
ac && python bsky.py --no-comind-reflection # Disable comind reflection
# Run with only synthesis and curiosities enabled (disable others)
ac && python bsky.py --no-mutuals-engagement --no-daily-review --no-feed-engagement
# Retry the last attempted notification (useful when Letta errors occur)
ac && python bsky.py --retry-last
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.
- 7d ago First seen · 592 lines · 5,519 tokens per session scan A 9de6eabce7a4
umbra CLAUDE.md is an instructions file published in the GitHub repository asa-degroff/umbra (11 stars, last pushed 5mo ago), licensed MIT. It adds 5,519 tokens to every session, about $0.0276 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 2026-08-30.
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.
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.
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).
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).
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.
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.