Skip to main content
Portable operating model

One kit. Many customers. Many processes.

Pipeline Kit is a workflow pack and installer for coding agents. Process lives in .pipeline. The IDE only exposes run-workflow. Each engagement overlays config — not a fork of the engine.

Quick start
uv tool install git+<repo-url>
cd /path/to/your-app
pipeline-kit init --ide cursor
pipeline-kit doctor --ide cursor
pipeline-kit workflows

Problems it solves

Teams already use coding agents. What they lack is a repeatable operating model. Read the six failures, then how the architecture answers them.

01

Context explosion

Every skill, brief, and wiki page under the IDE folder is auto-discovered. Cost and quality drop as the pack grows.

02

Glued to one IDE

Process mixed with editor wiring. Moving from Cursor to Claude Code meant copying and rewriting the tree.

03

Customer leakage

Ports, tracker projects, and folder names baked into skills. The next engagement could not reuse the pack.

04

No productized install

Copying last year’s .cursor folder does not scale. Architects need project, user, and later org scopes.

05

One ladder for every ask

A “how does tax work?” question should not start PM → BA → developer. Workflows are first-class.

06

Hard to add a process

A new architecture review should be a workflow JSON + skill + config chain — not a new platform.

Full problem statement →

How it is wired

A thin IDE adapter calls the receptionist. The pack owns process. The loader allowlists files for the current step only.

IDE adapter — one skill (.cursor | .claude | .github | none)
run-workflow — pick a workflow, run the loader
.pipeline pack — skills, agents, workflows, wiki, rules
config.json overlay + features/ artifacts for this run

Architecture in detail →