What is morningstar CLAUDE.md?

A set of project instructions for MorningStar, an automated coding agent that reads product requirements from Notion and works on a code repository.

Use it to understand MorningStar's Python project structure, installation, command-line usage, and integrations with Notion and Slack.

It gives the agent the project context, setup details, and operating rules it needs to work consistently. It also documents how progress can be reported through Slack, a team chat service.

How lonexreb/morningstar configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lonexreb/morningstar. 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/lonexreb/morningstar/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lonexreb/morningstar

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/lonexreb/morningstar/claude-md/github.svg)](https://agentmods.dev/instructions/lonexreb/morningstar/claude-md)

Your own site

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

Per session 1,018 This file is loaded in full into every session.

When invoked 1,018 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	$0.01018	$0.01018
Opus 5.5	$0.00407	$0.00407
Sonnet 5.5	$0.00204	$0.00204
Haiku 4.5	$0.00102	$0.00102

Measured 2mo ago against content hash 6855e529ed8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

morningstar 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MorningStar

Autonomous coding agent that reads a PRD from Notion, analyzes a codebase, generates tasks, and implements them using Claude Code CLI. Posts progress to Slack.

Tech Stack

Python 3.10+ with typer + rich
Claude Code CLI (headless mode via -p)
Notion MCP for PRD ingestion
Slack webhooks for status updates + bot token for two-way Q&A

Install

pip install -e ".[dev]"

Usage

morningstar run \
  --notion-url "https://notion.so/PRD-abc123" \
  --slack-webhook "https://hooks.slack.com/services/..." \
  --repo /path/to/repo

Project Structure

src/morningstar/
  __init__.py    -- version
  cli.py         -- typer CLI entry point (run, version, dry-run, process-queue, status)
  engine.py      -- core loop + 24/7 queue processor (fetch, plan, execute, commit, PR) + RunRecord history
  banner.py      -- ASCII art banner and branding

morningstar_demo.py  -- standalone walkthrough of process-queue with all I/O mocked
.github/workflows/   -- 15-min cron executor + manual dry-run executor
.claude-plugin/
  plugin.json        -- plugin manifest (name, version, keywords, paths)
  marketplace.json   -- self-hosted marketplace entry (category, tags, source)
agents/morningstar-runner.md  -- autonomous orchestrator agent
skills/run|dry-run|version|watch  -- user-facing slash commands

Conventions

TaskResult and RunRecord are frozen (immutable). RunState and QueueResult are mutable (accumulated in the loop).
All Claude CLI calls go through _run_claude() in engine.py
One-way Slack posts go through slack_post() (webhook)
Two-way Slack Q&A goes through slack_post_and_get_reply() (bot token + polling)
Question detection via parse_question_block() regex on Claude output
Logs written to <target-repo>/.agent-logs/
Run history written to <target-repo>/.morningstar/run-history.jsonl (append-only, capped at 500 records). Surfaced by morningstar status.
Weekly spend ledger lives at <target-repo>/.morningstar/weekly-spend.json (ISO week key + running total).
Budget tracked via RunState.cost -- includes PRD fetch + task gen + execution
All user-supplied inputs are validated before use (model allowlist, webhook URL, task IDs)
AI-generated task IDs are sanitized via _sanitize_task_id() before filesystem use
git add excludes sensitive file patterns (.env, *.pem, *.key, etc.)
PRD fetch runs in a temp directory with read-only tools (no Bash)
Task generation uses read-only tools (no Bash) -- only execution gets write + Bash

Read the full file on GitHub · 93 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 · 93 lines · 1,018 tokens per session scan A 6855e529ed8c

Subscribe to this mod's changes

morningstar CLAUDE.md is an instructions file published in the GitHub repository lonexreb/morningstar (1 stars, last pushed 6mo ago), licensed MIT. It adds 1,018 tokens to every session, about $0.0041 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-agent anthropic-claude automation autonomous-agent background-agent

morningstar CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
morningstar CLAUDE.mdlonexreb/morningstar	Instructions file	1	6mo ago	MIT	A	1,018	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

morningstar: Instructions file for Claude Code