auto-orchestrator

auto-orchestrator is a skill for Claude Code, Codex from hamza-ali-shahjahan/hamzaish. It costs 63 tokens per session (1,516 once invoked), scanned A, original, MIT.

A workflow coordinator that chooses and connects steps such as planning, building, testing, reviewing, simplifying, and shipping.

In plain words
What is it for?
Use it to drive a coding task from its current state through the appropriate development stages.
Why use it?
It removes the need to decide which development step to run next or start each one manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to drive a coding task from its current state through the appropriate development stages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hamza-ali-shahjahan/hamzaish/auto-orchestrator
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.

Any agent
npx skills add hamza-ali-shahjahan/hamzaish --skill auto-orchestrator
Clone the repo
git clone --depth 1 https://github.com/hamza-ali-shahjahan/hamzaish

Made for: Claude Code, Codex.

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 auto-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/hamza-ali-shahjahan/hamzaish/auto-orchestrator/github.svg)](https://agentmods.dev/skills/hamza-ali-shahjahan/hamzaish/auto-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/hamza-ali-shahjahan/hamzaish/auto-orchestrator"><img src="https://agentmods.dev/badge/skills/hamza-ali-shahjahan/hamzaish/auto-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for auto-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/hamza-ali-shahjahan/hamzaish/auto-orchestrator"><img src="https://agentmods.dev/badge/skills/hamza-ali-shahjahan/hamzaish/auto-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,516 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00063 $0.01516
Opus 5.5 $0.00025 $0.00606
Sonnet 5.5 $0.00013 $0.00303
Haiku 4.5 $0.00006 $0.00152

Measured 2mo ago against content hash 8fdca90e6d69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto-orchestrator 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 2mo 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.

factory/skills/auto-orchestrator/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Orchestrator

Overview

This skill automatically detects where you are in the development lifecycle and invokes the right skills in sequence. Instead of manually calling /spec, then /plan, then /build, etc., you describe what you want and this skill figures out what's needed and drives through each phase with gate checks between them.

When to Use

  • You have a feature, project, or task and want Claude to drive it end-to-end
  • You're not sure which skill to start with
  • You want the full lifecycle: spec -> plan -> build -> test -> review -> simplify -> ship

How It Works

Phase Detection

Before doing anything, assess the current state:

1. Does a spec exist for this work?
   - NO  -> Start at Phase 1 (Spec)
   - YES -> Move to next check

2. Is the work broken into tasks?
   - NO  -> Start at Phase 2 (Plan)
   - YES -> Move to next check

3. Is there code to implement?
   - YES, unfinished tasks remain -> Start at Phase 3 (Build + Test)
   - YES, all tasks done -> Move to next check

4. Has the code been reviewed?
   - NO  -> Start at Phase 4 (Review + Simplify)
   - YES -> Move to next check

5. Is it ready to ship?
   - YES -> Start at Phase 5 (Ship)

Phase 1: Spec (spec-driven-development)

Trigger: No spec exists, requirements are vague or incomplete.

Action: Read ${HAMZAISH_ROOT:-$HOME/Claude/Hamzaish}/factory/skills/spec-driven-development/SKILL.md and follow its full process.

Gate: Present the spec to the user. Do NOT proceed to Phase 2 until the user approves the spec.

Output: A structured spec with acceptance criteria.


Phase 2: Plan (planning-and-task-breakdown)

Trigger: Spec exists but work hasn't been broken into tasks.

Action: Read ${HAMZAISH_ROOT:-$HOME/Claude/Hamzaish}/factory/skills/planning-and-task-breakdown/SKILL.md and follow its full process.

Gate: Present the task breakdown to the user. Do NOT proceed to Phase 3 until the user approves the plan.

Output: Ordered list of tasks with acceptance criteria and dependencies.

Read the full file on GitHub · 172 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. 2mo ago First seen · 172 lines · 63 tokens per session scan A 8fdca90e6d69

Subscribe to this mod's changes

auto-orchestrator is a skill published in the GitHub repository hamza-ali-shahjahan/hamzaish (10 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,516 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.

Related

auto-orchestrator compared with skills from other repositories

auto-orchestrator next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
auto-orchestratorhamza-ali-shahjahan/hamzaishSkill101mo agoMITA63Claude Code, Codex
gingiris-launchGingiris/gingiris-launchSkill2166mo agoMITA326Claude Code, Codex
payments-polaralifanov/ai-garage-launchSkill23mo agoMITA53Claude Code
stack-referencealifanov/ai-garage-launchSkill23mo agoMITA67Claude Code
unit-economicsalifanov/ai-garage-launchSkill23mo agoMITA73Claude Code
traffic-channelsalifanov/ai-garage-launchSkill23mo agoMITA59Claude Code
make-playbooktamdogood/make-playbookSkill54mo agoMITA97Claude Code