darq CLAUDE.md

darq CLAUDE.md is an instructions file for coding agents from dark-builders/darq. It costs 1,461 tokens per session, scanned A, original, MIT.

Repository instructions for darq, a Rust command-line and text-interface application that turns GitHub issues into software through an automated planning, coding, review, testing, and learning process.

In plain words
What is it for?
Use them when changing darq, including running full or targeted Cargo tests, checking formatting, linting the workspace, and working with its integration tests.
Why use it?
They give a coding agent the project’s structure and the commands needed to build, format, lint, and test the code correctly.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/dark-builders/darq/claude-md
Clone the repo
git clone --depth 1 https://github.com/dark-builders/darq

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 darq CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dark-builders/darq/claude-md.svg)](https://agentmods.dev/instructions/dark-builders/darq/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dark-builders/darq/claude-md"><img src="https://agentmods.dev/badge/instructions/dark-builders/darq/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,461 This file is loaded in full into every session.
When invoked 1,461 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 $0.01461 $0.01461
Opus 5 $0.00731 $0.00731
Sonnet 5 $0.00292 $0.00292
Haiku 4.5 $0.00146 $0.00146

Measured 4d ago against content hash 89504a3cefb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

darq 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 4d 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 · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 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

darq is a Rust CLI + TUI that orchestrates spec-to-app software generation through an autonomous pipeline. It takes a GitHub issue, plans implementation via ACP-compatible AI agents, validates output through SAT (Scenario-driven AI Testing) with persona-based scoring, and feeds results back into a learning loop. Core loop: spec → plan → implement → review → merge → test → learn → repeat.

Build & Test Commands

cargo build                          # Build all crates (debug)
cargo build --release                # Release build
cargo test                           # All unit tests (both crates)
cargo test -p darq-core              # Core library tests only
cargo test -p darq                   # CLI binary tests only
cargo test test_workflow_registry    # Single test by name
cargo test -p darq-core workflow::   # Tests in a module
cargo clippy --workspace             # Lint
cargo fmt --check                    # Format check

Integration tests live in tests/ at the workspace root:

cargo test --test spine_integration
cargo test --test sweep_integration
cargo test --test workflow_integration

The binary and package are both named darq:

cargo run -- sat run --target /path/to/project
cargo run -- run issue 42 --full

Workspace Structure

Two-crate workspace:

  • crates/darq-core — All logic. Library crate. Uses thiserror for typed errors.
  • crates/darq — Thin binary wrapper (package name darq). Uses anyhow for error context. Never use anyhow in darq-core.

Architecture

Daemon Model

darq uses a daemon architecture. Most CLI commands are thin clients that connect to a background daemon via Unix socket (~/.darq/daemon.sock).

  • darq daemon start launches the daemon (owns DB, event broadcaster, workflow engine)
  • CLI commands auto-start the daemon if not running (DaemonClient::connect_or_start)
  • JSON-lines protocol over Unix socket for IPC
  • darq tui connects to the daemon for real-time event streaming

Read the full file on GitHub · 120 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. 4d ago First seen · 120 lines · 1,461 tokens per session scan A 89504a3cefb2

Subscribe to this mod's changes

darq CLAUDE.md is an instructions file published in the GitHub repository dark-builders/darq (10 stars, last pushed 4mo ago), licensed MIT. It adds 1,461 tokens to every session, about $0.0073 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.