setup

A guided setup command for ASDD, a framework that assigns different agent roles to software-development work. It connects those roles to model names and records which specification checker the project uses.

In plain words
What is it for?
Use it to configure ASDD agents, choose its built-in or OpenSpec readiness check, inspect what is configured, and identify missing settings.
Why use it?
It makes the repository's agent configuration explicit and checks that development and testing agents do not share the same blind spots.

Command for Claude Code

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/onehillai/asdd/setup
Clone the repo
git clone --depth 1 https://github.com/OneHillAI/ASDD

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 259 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 $0.00011 $0.00259
Opus 5 $0.00005 $0.00130
Sonnet 5 $0.00002 $0.00052
Haiku 4.5 $0.00001 $0.00026

Measured yesterday against content hash db8df3ecf8ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 yesterday.

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/commands/asdd/setup.md · 19 lines

What it actually says

Set up ASDD's agents for this repo.

Run asdd setup and walk the maintainer through it in plain language. It reads the roles from .asdd.yml, writes the chosen model names back, and asks which spec tool validates readiness - builtin (ASDD's definition of ready) or openspec (delegate to openspec validate). If they pick OpenSpec, remind them to install it where the gate runs (npm install -g @fission-ai/openspec).

Hold these rules; do not let a convenient answer break them:

  • Model NAMES go in .asdd.yml. A key never does: that file is version-controlled. Credentials belong in Goose's own config (goose configure) or a CI secret (ASDD_RUNTIME_TOKEN).
  • developer is bring-your-own: the contributor's own agent, not something the deployment runs.
  • The test models MUST differ from the developer's, or their blind spots line up and the tests cheerfully confirm the bug. asdd check-models --strict enforces it.

Finish by showing what is set and what is still unset.

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. yesterday First seen · 19 lines · 11 tokens per session scan A db8df3ecf8ad

Subscribe to this mod's changes

setup is a command published in the GitHub repository OneHillAI/ASDD (5 stars, last pushed 20d ago), licensed Apache-2.0. It adds 11 tokens to every session and 259 once invoked, about $0.0001 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.