AGENTS

A command reference for the dark-builders/darq project. It explains available CLI commands, where their code lives, and the project's local coding rules.

In plain words
What is it for?
Use it when working on Darq CLI commands, workflows, issues, pull requests, milestones, or system-status operations.
Why use it?
It helps an agent find the right files and follow project conventions before changing command-line code.

Command

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 commands/dark-builders/darq/agents
Clone the repo
git clone --depth 1 https://github.com/dark-builders/darq
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 329 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00329
Opus 5 $0.00000 $0.00164
Sonnet 5 $0.00000 $0.00066
Haiku 4.5 $0.00000 $0.00033

Measured 2d ago against content hash b79537efa7ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AGENTS 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 2d 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.

crates/darq/src/commands/AGENTS.md · 24 lines

What it actually says

CLI Commands

For project-wide conventions and anti-patterns, see CLAUDE.md and agent-rules.md.

WHERE TO LOOK

File What it does
mod.rs Common commands: status, run_list, run_show, run_approve, run_cancel, run_workflow_chain, stats
issue.rs IssueCommands enum — plan, build
pr.rs PrCommands enum — review, fix, merge
sat.rs SatCommands enum — run (daemon mode + standalone mode)
milestone.rs handle_sweep — milestone sweep operations

LOCAL CONVENTIONS

  • Each subcommand module defines its own #[derive(Subcommand)] enum and handle() function
  • handle() in submodules delegates to run_workflow_chain() or direct client.send() calls in mod.rs
  • run_workflow_chain() (mod.rs:202) sends a workflow request, subscribes to daemon events, and waits for completion
  • client.call() for one-shot responses; client.send() for daemon-initiated workflows
  • Output formatting lives here — daemon returns raw JSON, commands format for terminal
  • No direct Api access — CLI must go through daemon
  • No business logic — commands are pure serialization/deserialization layers
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. 2d ago First seen · 24 lines · 0 tokens per session scan A b79537efa7ce

Subscribe to this mod's changes

AGENTS is a command published in the GitHub repository dark-builders/darq (10 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 329 tokens. 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.