What is Hoofy AGENTS.md?

Project-specific instructions for developing Hoofy, a Go-based AI development companion that provides persistent memory and structured change management through an MCP server. They describe its purpose, architecture, folders, and design principles.

Use them when working on Hoofy's command-line program, memory system, configuration, change pipeline, or MCP tools.

They give coding agents the project context needed to make changes that fit Hoofy's existing structure and development approach.

How HendryAvila/Hoofy configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to HendryAvila/Hoofy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/HendryAvila/Hoofy/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/HendryAvila/Hoofy

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hendryavila/hoofy/agents-md/github.svg)](https://agentmods.dev/instructions/hendryavila/hoofy/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hendryavila/hoofy/agents-md"><img src="https://agentmods.dev/badge/instructions/hendryavila/hoofy/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hendryavila/hoofy/agents-md"><img src="https://agentmods.dev/badge/instructions/hendryavila/hoofy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,790 This file is loaded in full into every session.

When invoked 2,790 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02790	$0.02790
Opus 5.5	$0.01116	$0.01116
Sonnet 5.5	$0.00558	$0.00558
Haiku 4.5	$0.00279	$0.00279

Measured 2mo ago against content hash 0a5b6d6229a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Hoofy AGENTS.md 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 2mo 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.

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.

AGENTS.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Hoofy Development Guide

Project Overview

Hoofy is an AI development companion — an MCP server written in Go 1.25 that provides persistent memory, adaptive change management, and spec-driven development. It prevents AI hallucinations by forcing structured requirements before coding, remembers context across sessions, and adapts its workflow to the size and type of each change.

Binary: hoofy (CLI with serve, update, version commands) Transport: stdio (MCP protocol) Dependency: mcp-go v0.44.0 (Mark3Labs MCP SDK)

Architecture

Directory Structure

cmd/hoofy/              Entry point — CLI argument parsing, server startup, graceful shutdown
internal/
├── changes/            Change pipeline — types, flows, store, state machine
├── config/             Project config persistence (hoofy.json) — types, Store interface, FileStore
├── memory/             Persistent memory — SQLite store, FTS5 search, sessions, observations
├── memtools/           MCP memory tool handlers — 19 tools for save, search, context, sessions, relations, progress
├── pipeline/           Pipeline state machine — stage transitions, Clarity Gate thresholds
├── prompts/            MCP prompts — /sdd-start, /sdd-status, /sdd-stage-guide, /sdd-memory-guide, /sdd-change-guide, /sdd-bootstrap-guide
├── resources/          MCP resources — project status resource
├── server/             Composition root — wires all dependencies, registers tools/prompts/resources
├── templates/          Go templates for stage artifacts (guided + expert mode variants)
├── tools/              MCP tool handlers — one file per tool (init, principles, charter, specify, clarify, design, tasks, validate, context, change, adr, audit, bridge, suggest_context, review)
└── updater/            Self-update system — GitHub releases API, binary replacement

Design Principles

SRP: One file = one tool. Config handles persistence, pipeline handles business rules.
DIP: Tools depend on interfaces (config.Store, template renderer), not concretions. server.go is the composition root that wires everything.
OCP: New tools/stages are added without modifying existing ones.
Liskov: Both modes (guided/expert) use the same pipeline interface, differing only in thresholds and templates.

Read the full file on GitHub · 202 lines

Changes

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.

2mo ago First seen · 202 lines · 2,790 tokens per session scan A 0a5b6d6229a3

Subscribe to this mod's changes

Hoofy AGENTS.md is an instructions file published in the GitHub repository HendryAvila/Hoofy (16 stars, last pushed 7mo ago), licensed MIT. It adds 2,790 tokens to every session, about $0.0112 per session on Opus 5.5. 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.

ai developer-tools go mcp mcp-server persistent memory

Hoofy AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Hoofy AGENTS.mdHendryAvila/Hoofy	Instructions file	16	7mo ago	MIT	A	2,790	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Hoofy: Instructions file for Codex