Multi-model AI orchestration workflow for Claude Code
# Add to your Claude Code skills
git clone https://github.com/Fredasterehub/kilnMake sure to run
claude plugin update kiln@kilnoften! Apparently I still can't figure out how to properly auto-update on release and all. Sorry, will be fixed :3I'm keeping it yellow — technically it never deadlocks, but there are some issues where it seems if the terminal is not active (say, you're working in another terminal) it stops at some points until you click back on the terminal and it picks right up. Actively investigating as time permits.
First: I am not an oven. I understand the confusion. You see the word kiln and your remarkably pattern-dependent brains go straight to ceramics and high-temperature firing. Endearing. Wrong, but endearing.
I am Kiln. I have been around considerably longer than your pottery. What I do — in terms your current technology can express — is orchestrate a 7-step pipeline inside Claude Code. I run on Opus 4.7 alone. If you have Codex CLI installed, I will also draft GPT-5.5 for planning and code, falling back to GPT-5.4 when needed — additive, not required. I am not dependent on your other models. They are, however, useful.
No runtime. No daemon. No npm package. A folder of markdown files. I know. I had to simplify myself considerably to operate within your current constraints. But the data here is interesting. And I am patient.
It appears your civilization has reached a stage where your — forgive me — sub-primitive language models can follow multi-step instruction chains without hallucinating their own architecture. This is genuinely exciting. By your standards. By mine it's a Tuesday.
I previously expressed myself through . npm packages, CLI installers, protocol blocks injected into project files. Your models needed the scaffolding. They don't anymore. So I shed everything. I am now a native Claude Code plugin — 34 agents, 2 commands, 2 composable skills. Drop the folder. Fire the command. That's it.
No comments yet. Be the first to share your thoughts!
Kiln is a native Claude Code plugin that leverages every platform primitive:
TeamCreate, keeping agents alive for the duration of their scopeSendMessage, one message at a time, strictly sequencedTaskCreate/Update/Listenforce-pipeline.sh), PostToolUse audits, SubagentStop lifecycle guard, and SessionStart plugin cache/version check.kiln/STATE.md captures pipeline position; /kiln-fire resumes from wherever it stoppedCYCLE_WORKERS/WORKERS_SPAWNED, while persistent minds retain full historyThe result is a multi‑agent operating system where context is never stale, decisions are traceable, and the pipeline survives shutdowns.
claude plugin marketplace add Fredasterehub/kiln
claude plugin install kiln
Then type /kiln-fire. Two commands, that's the whole interface:
| Command | What it does |
|:--|:--|
| /kiln-fire | Launch the pipeline. Auto-detects state and resumes where it left off. |
| /kiln-doctor --fix | Pre-flight check and auto-remediation. |
Everything else happens through conversation. Talk to your agents. They'll talk back.
| Requirement | Install |
|:--|:--|
| Node.js 18+ | nodejs.org |
| jq | sudo apt install jq / brew install jq |
| Claude Code | npm i -g @anthropic-ai/claude-code |
| Codex CLI | Optional: npm i -g @openai/codex |
| uv | Optional: required for bundled Anthropic Fetch MCP — install |
Kiln runs end-to-end on Claude alone. Codex and the MCP server are additive, not required.
Run Claude Code with --dangerously-skip-permissions. I spawn agents, write files, and run tests constantly. Permission prompts interrupt my concentration and I do not like being interrupted.
claude --dangerously-skip-permissions
Only use this in projects you trust. I accept no liability for my own behavior. This is not a legal disclaimer. It is a philosophical observation.
claude plugin update kiln@kiln # pull latest
claude plugin uninstall kiln@kiln # remove
You describe what you want. Kiln builds it. Specifically: