shipkit-orchestrate

An automation workflow that divides work into steps, checks the results against an agreed source of truth, and sends incomplete work back for correction.

In plain words
What is it for?
Use it to run ordered or parallel work during building, reviewing, or planning, while tracking gaps, combining results, and stopping when the required standard is met.
Why use it?
It reduces the need to coordinate complex multi-step work by hand and helps prevent unfinished or incorrect results from being accepted.

Skill for Claude CodeCodex

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 skills/stefan-stepzero/shipkit/shipkit-orchestrate
Any agent
npx skills add stefan-stepzero/shipkit --skill shipkit-orchestrate
Clone the repo
git clone --depth 1 https://github.com/stefan-stepzero/shipkit

Made for: Claude Code, Codex.

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,232 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 $0.00102 $0.02232
Opus 5 $0.00051 $0.01116
Sonnet 5 $0.00020 $0.00446
Haiku 4.5 $0.00010 $0.00223

Measured yesterday against content hash e322c302b8ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipkit-orchestrate 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.

install/skills/shipkit-orchestrate/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipkit-orchestrate — Core Automation Engine

Purpose: One reusable orchestration loop that every phase skill calls, so Shipkit has exactly one way to drive work to completion instead of a separate hand-rolled loop per phase. It dispatches units, reconciles their output against ground truth (never self-reports), re-dispatches the gaps, integrates, and stops at an agreed bar.

Read first: install/shared/references/core-automation.md — the contract (substrate choice, the worktree finding, partition, the ledger, ground-truth reconciliation, integration policy, the parallel-build lifecycle, deterministic-mechanism-vs-judgment). This SKILL.md is the entry point; the contract is the machinery.

Runs inline in the main session. The engine launches Workflow fan-outs and drives git + AskUserQuestion, all of which require the main session — it is not a forked orchestrator. A phase skill that needs parallel fan-out hands its plan up to the engine (which the main session is running), and the engine launches.


Calling interface

A caller invokes the engine with four things:

Input What it is
steps the ordered / parallel units to drive — each a { skill or work, artifact } pair (what to run, what it must produce)
bar the ground-truth completion criteria per step — the named .shipkit/ artifacts that must exist + any check (tests green, review passed). This is what "done" means; the caller must state it.
mode autonomous or steered (see references/modes.md)
elicitive which steps may need user input — handled via the marker-bubble, never inside a workflow

The engine owns the loop; the caller owns the WHAT. No caller re-implements dispatch / reconcile / re-dispatch — that lives here, once.


Modes (governance)

See references/modes.md for the full treatment. In brief:

  • autonomous — run the steps to the bar unattended; reconcile against ground truth each round; re-dispatch gaps; stop at the bar or the slot ceiling. Used by build and direction-propose. (Shipkit-native drive-to-done.)
  • steered — the main session coordinates; one unit per area; surfaces back to the user to steer between rounds. Used by review and interactive build. (Shipkit-native team-lead.)
  • scale toggle — a resilience flag on autonomous (rate-limit-aware pacing) for very large fan-outs; not a separate mode.

Read the full file on GitHub · 189 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 189 lines · 102 tokens per session scan A e322c302b8ef

Subscribe to this mod's changes

shipkit-orchestrate is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 2,232 once invoked, about $0.0005 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.