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.
npx agentmods add skills/junhanliu-dev/espalier-engineering/espalier-initnpx skills add Junhanliu-dev/espalier-engineering --skill espalier-initgit clone --depth 1 https://github.com/Junhanliu-dev/espalier-engineeringWrote 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.
[](https://agentmods.dev/skills/junhanliu-dev/espalier-engineering/espalier-init)<a href="https://agentmods.dev/skills/junhanliu-dev/espalier-engineering/espalier-init"><img src="https://agentmods.dev/badge/skills/junhanliu-dev/espalier-engineering/espalier-init.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00118 | $0.10095 |
| Opus 5 | $0.00059 | $0.05047 |
| Sonnet 5 | $0.00024 | $0.02019 |
| Haiku 4.5 | $0.00012 | $0.01009 |
Grade A, and why
espalier-init 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.
How it starts
The opening of the file, as written. The whole thing — 617 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Espalier Init
Discover the actual patterns, conventions, and architecture of an existing codebase, then generate a structured constraint system that ensures AI agents produce code matching those standards.
When to Use
- "Set up Espalier for this project"
- "Create Espalier structure for my codebase"
- "Make AI code production-ready for this repo"
- "Build agent constraints for this project"
- "/espalier-init"
Philosophy
When an agent makes an error, engineer its elimination — not with prompt tweaks, but with files, rules, automated checks, and system structure.
Core insight: The problem isn't model intelligence. It's that models don't know the unwritten rules — patterns every experienced developer on the team knows but nobody documented.
This skill discovers those rules from the code itself, then encodes them as machine-enforceable constraints. Like an espalier trains a fruit tree to grow along a wall, this skill trains your AI coder to grow along the patterns already in your codebase.
File Layout of This Skill
espalier-init/
├── SKILL.md # this file — overview + phase index
├── templates/ # markdown templates emitted into target project
│ ├── rules/ # → espalier/rules/ in target
│ ├── skills/ # → espalier/skills/<name>/SKILL.md
│ ├── agents/ # → espalier/agents/ in target
│ ├── agent.md # → espalier/agent.md (orchestrator)
│ └── pipeline.md # → espalier/pipeline.md
├── hook-templates/ # shell scripts emitted into espalier/hooks/
└── references/ # deep-dive content read on demand
├── discovery-checklist.md # Phase 1 detail
├── wiring.md # Phase 10 detail
├── validation.md # Phase 11 detail
└── wiki-templates.md # Phase 6 wiki stubs
Rule: Every phase below tells you which template/reference to read. Open them with the Read tool when the phase fires — do NOT invent template content from memory.
What ships with it
52 files 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.
- hook-templates/check-layer-boundaries-go.sh 665 B runs code
- hook-templates/check-layer-boundaries-python.sh 821 B runs code
- hook-templates/check-layer-boundaries-typescript.sh 1.6 KB runs code
- hook-templates/copilot-hook-adapter.sh 2.4 KB runs code
- hook-templates/drift-detect.sh 5.7 KB runs code
- hook-templates/drift-helpers.sh 14 KB runs code
- hook-templates/espalier-stats.sh 18 KB runs code
- hook-templates/lookup-helpers.sh 9.5 KB runs code
- hook-templates/map-guard.sh 3.9 KB runs code
- hook-templates/maprun-dispatch.sh 21 KB runs code
- hook-templates/maprun-integration.sh 3.4 KB runs code
- hook-templates/maprun-merge.sh 2.9 KB runs code
- hook-templates/maprun-pr.sh 13 KB runs code
- hook-templates/maprun-verify.sh 5.0 KB runs code
- hook-templates/maprun.py 64 KB runs code
- hook-templates/parse-drift-blocks.py 1.1 KB runs code
- hook-templates/post-edit-wrapper.sh 2.0 KB runs code
- hook-templates/post-merge-backlink.sh 2.2 KB runs code
- hook-templates/pre-push-gate-wrapper.sh 3.0 KB runs code
- hook-templates/pre-push-gate.sh 18 KB runs code
- hook-templates/rebuild-commit-index.sh 2.6 KB runs code
- references/discovery-checklist.md 16 KB
- references/validation.md 13 KB
- references/wiki-templates.md 710 B
- references/wiring.md 14 KB
- templates/agent.md 3.2 KB
- templates/agents/harness-coder.md 23 KB
- templates/agents/harness-reviewer.md 25 KB
- templates/agents/harness-security.md 13 KB
- templates/pipeline.md 22 KB
- templates/rules/coding-standards.md 3.1 KB
- templates/rules/development-process.md 2.3 KB
- templates/rules/engineering-structure.md 751 B
- templates/rules/production-standards.md 5.8 KB
- templates/rules/security-standards.md 5.6 KB
- templates/scout-prompts.md 7.3 KB
- templates/skills/espalier-ask.md 6.4 KB
- templates/skills/espalier-audit.md 10.0 KB
- templates/skills/espalier-coding-spec.md 496 B
- templates/skills/espalier-coding.md 3.9 KB
- templates/skills/espalier-doctor.md 7.5 KB
- templates/skills/espalier-fix.md 61 KB
- templates/skills/espalier-grill.md 17 KB
- templates/skills/espalier-map.md 20 KB
- templates/skills/espalier-maprun.md 31 KB
- templates/skills/espalier-prune.md 11 KB
- templates/skills/espalier-requirements.md 2.3 KB
- templates/skills/espalier-review.md 4.7 KB
- templates/skills/espalier-security.md 5.4 KB
- templates/skills/espalier-simplify.md 24 KB
- templates/skills/espalier-testing.md 2.5 KB
- templates/skills/espalier.md 55 KB
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.
- yesterday Changed · +1 lines ee1a6a83a6fe
- 4d ago First seen · 616 lines · 118 tokens per session scan A b6a37217308c
espalier-init is a skill published in the GitHub repository Junhanliu-dev/espalier-engineering (72 stars, last pushed yesterday), licensed MIT. It adds 118 tokens to every session and 10,095 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
codex
Offload heavy-duty implementation work to OpenAI Codex as a background worker, routing each task to the appropriate available GPT model—especially GPT-5.6 Sol, Terra, or Luna—while Claude stays the orchestrator and reviewer. Use when the user types /codex, asks to delegate/offload/route work to Codex or a GPT model…
gan-zhong-xue
在你干真实开发时(边干边挖:搞懂 AI 正在做的这步,掌控方向)或干完提交后(事后挖: 回头搞懂一个甩手没懂的改动),就地陪你走一轮"先让你猜、再揭示、逼到原理"的回合制, 把黑盒变成你真懂、能复述、能迁移的东西。治的是 vibe-coding 的病:交付物在增加, 理解没跟上。触发词:"干中学"、"帮我搞懂 AI 正在做的这步"、"我刚才那段没懂"、 "这个 commit 我说不清"、"帮我真正搞懂刚才做的";掌舵(任务中途):"等等这步我没懂"、 "为什么这么改"、"这步我没跟上"。 English triggers: "learning by doing", "help me actually understand what…
google-go-style
Use when writing, reviewing, or refactoring Go code; when handling errors (fmt.Errorf, %w, sentinel, errors.Is, errors.As); when deciding between panic, error return, and log.Fatal; when writing tests (table-driven, t.Helper, t.Fatal vs t.Error, goroutines); when designing API surface (option struct, variadic options…
concise
Concise communication mode. Cuts 60-70% of output tokens while keeping natural, readable English. Drops filler, hedging, and pleasantries but maintains grammar and sentence flow. Elaborate on request -- ask for detail and get it, then auto-return to concise. Use when user says "concise mode", "be concise", "less…
specdd
Spec-driven development orchestrator that turns vague, top-of-mind feature requests into production-grade specifications before any code is written. ALWAYS use this skill whenever the user describes a feature, change, capability, screen, flow, or new component in plain language — even if they don't explicitly ask for…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.