Espalier Engineering
Train your AI coders the way you'd train a vine — discover your codebase's actual patterns, then encode them as Claude Code rules, skills, agents, hooks, and a guided pipeline…
Install
/plugin marketplace add Junhanliu-dev/espalier-engineeringInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →An espalier trains a fruit tree to grow flat along a wall — pruned, wired, productive. Espalier does the same for your AI coding agents: it reads your codebase, discovers the patterns already in it, and encodes them as machine-enforced guardrails. Generated code grows along your conventions on the first try, not the fifth.
Quick start
/plugin marketplace add Junhanliu-dev/espalier-engineering
/plugin install espalier-engineering@espalier-engineering
/espalier-init
That's it. One ~10–15 minute setup per repo, then every future change reuses it.
The problem
AI coders write plausible code that doesn't fit your codebase. They invent helpers you already have, pick libraries you don't use, and throw where your repo standardised on Result<T> years ago. It's not a model-intelligence problem — it's an unwritten rules problem. The model can't read your team's Slack history.
How it works
/espalier-initdiscovers — parallel scout agents read your code and extract the conventions nobody wrote down.- It writes them down — as a per-project
espalier/directory: always-loaded rules, phase-loaded skills, sub-agent definitions, a wiki, and programmatic hooks. - Every change is gated — a coder agent writes, a separate reviewer agent (different tool set) checks against the same rules, and hooks block pushes that skip the gates.
- It stays honest — drift detection flags docs the code has outgrown; refreshes are gated, never silent.
espalier/
├── rules/ # always loaded: coding standards, security, production standards
├── skills/ # the pipelines: /espalier, /espalier-fix, /espalier-ask, …
├── agents/ # harness-coder / harness-reviewer / harness-security
├── wiki/ # architecture, data models, critical paths
├── hooks/ # programmatic gates: layer checks, pre-push, drift detect
├── maps/ # multi-session decision maps
└── changes/ # typed audit trail — one folder per requirement
The commands
| Command | What it does |
|---|---|
/espalier-init |
One-time setup: discover conventions, generate + wire the guardrails |
/espalier <feature> |
Full 10-stage pipeline: grilled requirements → your approval → code → independent review → tests → gated push |
/espalier-fix <bug> |
Slimmer bug-fix lane that auto-links each fix to the change that caused it |
/espalier-ask <question> |
Read-only Q&A — answers from your docs, verified against the code, every claim sourced |
/espalier-audit |
Repo-wide security audit of existing code; findings hand off into fix runs |
/espalier-simplify [scope] |
Evidence-first simplification survey of existing code — proven cuts file as refactor changes the pipeline runs; the docs that described them get flagged for prune |
/espalier-map <idea> |
Plan work bigger than one session (epics, greenfield) as a decision map |
/espalier-maprun |
Execute a cleared map: headless workers in isolated worktrees, reviewable slice PRs |
/espalier-doctor / /espalier-prune |
Detect doc drift / refresh a stale doc (gated) |
/espalier-migrate |
Upgrade an existing install to the current version |
Highlights along the way:
Similar plugs
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro,…
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Devin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini…