ao-run

ao-run is a command for Claude Code from kaze-jp/kusa. It costs 0 tokens per session (882 once invoked), scanned A, original, MIT.

A command that starts an automated software-development workflow from approved requirements, design, and task documents.

In plain words
What is it for?
Use it to run an end-to-end feature workflow according to the project’s automation, Git, quality-check, and review settings.
Why use it?
It checks that the necessary specifications and project settings exist before coordinating implementation, integration, review, and merging.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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/kaze-jp/kusa/ao-run
Clone the repo
git clone --depth 1 https://github.com/kaze-jp/kusa

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 ao-run

README.md
[![agentmods](https://agentmods.dev/badge/commands/kaze-jp/kusa/ao-run.svg)](https://agentmods.dev/commands/kaze-jp/kusa/ao-run)
Your own site
<a href="https://agentmods.dev/commands/kaze-jp/kusa/ao-run"><img src="https://agentmods.dev/badge/commands/kaze-jp/kusa/ao-run.svg" alt="Measured on agentmods" height="20"></a>
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 882 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 5.1 $0.00000 $0.00882
Opus 5 $0.00000 $0.00441
Sonnet 5 $0.00000 $0.00176
Haiku 4.5 $0.00000 $0.00088

Measured 5d ago against content hash 05f474cccf77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ao-run 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 5d 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/commands/kiro/ao-run.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AO Autonomous Execution

Launch the Agent Orchestrator for fully autonomous feature development. The orchestrator takes approved specs and drives the entire pipeline: implementation → integration → PR → review → merge.

Usage

/kiro:ao-run <feature-name>

Instructions

  1. Validate prerequisites: Verify all required spec documents exist:

    • .kiro/specs/$FEATURE_NAME/requirements.md (required, R1 approved)
    • .kiro/specs/$FEATURE_NAME/design.md (required, R2 approved)
    • .kiro/specs/$FEATURE_NAME/tasks.md (required, R3 approved)

    If any are missing, report which documents are absent and which commands to run:

    • /kiro:spec-init/kiro:spec-requirements/kiro:spec-design/kiro:spec-tasks
  2. Read configuration from .ao/ao.yaml:

    • preset and autonomy.downstream — determines how much human intervention is needed
    • git.strategy and git.base_branch — worktree vs branch strategy
    • quality_gates.commands — project-specific test/lint/build commands
    • reviews.* — which review points require human vs AI actors
  3. Read steering documents for implementation constraints:

    • .ao/steering/product.md — product vision and priorities
    • .ao/steering/tech.md — tech stack and coding conventions
    • .ao/steering/structure.md — directory structure and naming rules
  4. Launch the orchestrator agent (orchestrator.md) with the feature name. The orchestrator autonomously executes the full pipeline:

    Phase 1: Task analysis + worktree branch creation
    Phase 2: Context generation for implementation workers
    Phase 3: Parallel implementation (TDD + Team Agents + quality gates)
    Phase 4: Integration (merge worktrees) + Simplify
    Phase 5: Ship-Before Checkpoint
    Phase 6: PR creation + Multi-specialist code review (GH comments)
    Phase 7: Fix loop (address review feedback until approved)
    Phase 8: Pre-merge review (human/ai per downstream setting)
    Merge:   Merge to base branch + cleanup
    

Read the full file on GitHub · 78 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. 5d ago First seen · 78 lines · 0 tokens per session scan A 05f474cccf77

Subscribe to this mod's changes

ao-run is a command published in the GitHub repository kaze-jp/kusa (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 882 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.