maidan: Instructions file for Claude Code

CLAUDE.md

maidan CLAUDE.md is an instructions file for Claude Code from david-engelmann/maidan. It costs 34,719 tokens per session, scanned A, original, MIT.

A project guide for Maidan, a Rust workspace made of multiple related code packages for an AI collaboration service. It explains the repository layout, development rules, release process, and the order in which new contributors should read the documentation.

In plain words
What is it for?
Use it when working in the Maidan repository to understand where documentation and code live, how changes are merged, and how the project’s release clusters work.
Why use it?
It gives an agent or developer the project’s operating rules before they change code. This reduces mistakes caused by missing repository-specific context.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: names the AskUserQuestion tool; positional $N argument; mentions AGENTS.md.

This is david-engelmann/maidan's own configuration. It tells Claude Code how to work on maidan 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 maidan configures →

Reuse

Borrowing it

Nothing to install: this file belongs to david-engelmann/maidan. 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/david-engelmann/maidan/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/david-engelmann/maidan

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 maidan CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/david-engelmann/maidan/claude-md.svg)](https://agentmods.dev/instructions/david-engelmann/maidan/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/david-engelmann/maidan/claude-md"><img src="https://agentmods.dev/badge/instructions/david-engelmann/maidan/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 34,719 This file is loaded in full into every session.
When invoked 34,719 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.34719 $0.34719
Opus 5 $0.17359 $0.17359
Sonnet 5 $0.06944 $0.06944
Haiku 4.5 $0.03472 $0.03472

Measured 6d ago against content hash 2d67a45d3b54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

maidan 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 6d 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 · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent guide

If you are an AI agent or human dev landing in this repo for the first time, read this file end-to-end before doing anything else. It is the single source of truth for how to operate in this codebase. The what lives in docs/ — integrators use docs/Integration.md; contributors use docs/README.md after this page.

30-second orientation

  • Name: Maidan. A workspace for AI agents to collaborate (Slack-shaped surface backed by Postgres + content-addressed artifacts). The project was renamed twice during early scoping (Slack-for-AI-Agents → Diwan → Maidan); the current name is load-bearing.
  • Language: Rust 2021, toolchain pinned via rust-toolchain.toml (currently 1.91). Workspace with 13 member crates.
  • Owner: david-engelmann. Solo maintainer. Squash-merge only; admin-merge is the standard workflow (see docs/Operations.md).
  • Release cadence: work ships in clusters — the initial A–H + 1.0 arc (v0.X.Yv1.0.0), then a numbered product ladder (1–120, tagged vX.0.0). Every cluster closes with a mandatory retro PR and a tag. Current state: Product Ladder 102+ is complete — Phases XIX–XXIII (Clusters 102–120) closed on main; scale gate maidan-scale-1.0 at v120.0.0. No further ladder cluster is defined past 120; subsequent clusters are post-gate hardening (Phase XXIV, Cluster 121+, latest v315.0.0, tagged vX.0.0 on the same ladder but with no new gate tag — see "Project state at this handoff" below and docs/Roadmap.md). Since v273: MCP 2026-07-28 (300–303), mail retry (304–306), Slack/GitHub projectors (307–312), SDKs published at 0.1.0 (294–299), launch-prep (313–314), and the 2026-08-28 research-sweep clusters (315+). The canonical live backlog is docs/Open Work.md, not the handoff narrative below (which is a point-in-time record narrating through ~Cluster 273). The detailed handoff paragraph below narrates through Cluster 266; clusters 267–272 (optional-deferrals sweep + LSN read-replica program close) and 273 (strategy-pack reconciliation) shipped after it — see CHANGELOG.md and docs/Open Work.md for the current state and forward work.
  • CI: GitHub Actions, 8 required-status-checks on main (lint, secrets scan, unit tests, integration (testcontainers), docker compose smoke, scale-out smoke, promtool (alert rules), otlp smoke). Every PR runs all 8. (scale-out smoke was promoted at the maidan-scale-1.0 gate, Cluster 120; promtool (alert rules) + otlp smoke promoted in Cluster 124.)

Read the full file on GitHub · 221 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. 6d ago First seen · 221 lines · 34,719 tokens per session scan A 2d67a45d3b54

Subscribe to this mod's changes

maidan CLAUDE.md is an instructions file published in the GitHub repository david-engelmann/maidan (5 stars, last pushed yesterday), licensed MIT. It adds 34,719 tokens to every session, about $0.1736 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

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

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 · 5,182 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

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

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

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