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 instructions/xh/hoist-core/claude-mdgit clone --depth 1 https://github.com/xh/hoist-coreWrote 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/instructions/xh/hoist-core/claude-md)<a href="https://agentmods.dev/instructions/xh/hoist-core/claude-md"><img src="https://agentmods.dev/badge/instructions/xh/hoist-core/claude-md.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 5.1 | $0.04877 | $0.04877 |
| Opus 5 | $0.02439 | $0.02439 |
| Sonnet 5 | $0.00975 | $0.00975 |
| Haiku 4.5 | $0.00488 | $0.00488 |
Grade A, and why
hoist-core CLAUDE.md scanned grade A with 1 finding 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 5d ago.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
crafting raw `curl` calls to the GitHub API. How it starts
The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to AI coding assistants — including Claude Code, GitHub Copilot, and similar tools — when working with code in this repository.
Project Overview
Hoist-core is the server-side component of the Hoist web application development toolkit, built
by Extremely Heavy Industries (xh.io). It is a Grails 7 plugin (not a standalone app)
published as io.xh:hoist-core and consumed by Grails application projects. The client-side
counterpart is hoist-react.
- Language: Groovy 4 / Java 17
- Framework: Grails 7.0 (Spring Boot 3.5, Hibernate 5, GORM)
- Clustering: Hazelcast 5.6 for distributed caching, pub/sub, and multi-instance coordination
- Package root:
io.xh.hoist
Hoist Developer Tools and Documentation
IMPORTANT: Do not guess at hoist-core APIs, service patterns, or framework conventions. Hoist-core ships a dedicated MCP server that provides structured access to all framework documentation and Groovy/Java symbol information. You MUST use these tools before modifying or extending hoist-core code to understand existing architecture, configuration patterns, and common pitfalls. The feature docs and concept docs are the authoritative reference for how Hoist Core works -- skipping them risks producing code that conflicts with established patterns or misses built-in functionality.
The MCP server is configured via .mcp.json and is very likely already available. Use the
following tools:
hoist-core-search-docs-- Search all docs by keyword (e.g."BaseService lifecycle","authentication OAuth","clustering Hazelcast")hoist-core-list-docs-- List all available documentation, grouped by categoryhoist-core-search-symbols-- Search for Groovy/Java classes, interfaces, traits, enums, and members of key framework classes (e.g."Cache","createTimer")hoist-core-get-symbol-- Get detailed type info for a specific symbol (signature, Groovydoc, inheritance, annotations)hoist-core-get-members-- List all properties and methods of a class or interface
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.
- 5d ago First seen · 391 lines · 4,877 tokens per session scan A 1a994a495432
hoist-core CLAUDE.md is an instructions file published in the GitHub repository xh/hoist-core (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,877 tokens to every session, about $0.0244 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
Vibe-Research AGENTS.md
AGENTS.md instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).
plugins CLAUDE.md
Claude Code instructions for ihub-pub/plugins, covering project knowledge base, project structure, plugin id 速查表, version compatibility and commands（build / lint / test）.
clawock CLAUDE.md
Claude Code instructions for KCNyu/clawock, covering claude.md, identity & user, required reads (every session, in order), what lives where and cron run loop (what openclaw fires).
jaz-ai AGENTS.md
AGENTS.md instructions for teamtinvio/jaz-ai, covering jaz ai · agent skills, skills, install, auto-detect your ai tool and install all 7 skills and or one skill at a time.
kiasumiles AGENTS.md
Instructions for hosanxiv/kiasumiles, covering project, architecture, commands and agent behavior.
ATF-AI copilot-instructions.md
Instructions for agronetlabs/ATF-AI, covering atf-ai repository instructions for github copilot, governance boundary, core vs. adapter changes, rwa privileged actions and security.