autogrind: Instructions file for Claude Code

CLAUDE.md

autogrind CLAUDE.md is an instructions file for Claude Code from ttttonyhe/autogrind. It costs 5,886 tokens per session, scanned A, original, MIT.

Instructions for AutoGrind, an agent skill that keeps an AI coding agent working through repeated development cycles until told to stop.

In plain words
What is it for?
They guide the skill's work loop, file layout, plugin manifest, and synchronization between its source and mirror files.
Why use it?
They define where the skill files belong and keep the raw skill package compatible with different plugin marketplaces.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is ttttonyhe/autogrind's own configuration. It tells Claude Code how to work on autogrind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything autogrind configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ttttonyhe/autogrind. 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/ttttonyhe/autogrind/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ttttonyhe/autogrind

Made for: Claude Code.

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.

agentmods badge for autogrind CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ttttonyhe/autogrind/claude-md/github.svg)](https://agentmods.dev/instructions/ttttonyhe/autogrind/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ttttonyhe/autogrind/claude-md"><img src="https://agentmods.dev/badge/instructions/ttttonyhe/autogrind/claude-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.

agentmods 80×15 button for autogrind CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ttttonyhe/autogrind/claude-md"><img src="https://agentmods.dev/badge/instructions/ttttonyhe/autogrind/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,886 This file is loaded in full into every session.
When invoked 5,886 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05886 $0.05886
Opus 5 $0.02943 $0.02943
Sonnet 5 $0.01177 $0.01177
Haiku 4.5 $0.00589 $0.00589

Measured 9d ago against content hash 0214600128e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autogrind CLAUDE.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 9d 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.

CLAUDE.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Purpose

This repository contains the AutoGrind skill - a cross-agent autonomous development skill that directs an AI coding agent to work continuously on a project without stopping. The agent follows a cyclic grind loop (Overview → Understand → Plan → Work → Reflect → repeat) and never terminates unless the user explicitly says to stop.

Skill File Format

The repo root IS the skill package — SKILL.md lives at the root to satisfy the AgentSkills spec. Agents discover it by symlinking or cloning the repo root directly into their skills directory.

Plugin Structure

The repo root stays skill-first, but Codex marketplace discovery points at a dedicated plugin bundle under plugins/autogrind/. This keeps the repository centered on the raw skill while matching the ./plugins/<name> layout used by Codex's built-in marketplaces.

autogrind/           (repo root = skill root)
├── SKILL.md                        # agentskills.io root (must match skills/autogrind/SKILL.md)
├── .claude-plugin/
│   ├── plugin.json                 # Claude Code plugin manifest
│   └── marketplace.json            # Claude Code marketplace catalog
├── .agents/plugins/marketplace.json # Codex repo marketplace catalog -> plugins/autogrind
├── skills/autogrind/SKILL.md       # plugin-format skill copy
├── commands/start.md           # /autogrind slash command
├── plugins/
│   └── autogrind/
│       ├── .codex-plugin/plugin.json
│       ├── skills/autogrind/SKILL.md
│       ├── commands/start.md
│       └── assets/
└── PLUGIN.md                       # plugin installation guide

Both native plugins are complements to the core skill package. Do not restructure the repo unless explicitly requested.

SKILL.md sync rule

SKILL.md, skills/autogrind/SKILL.md, and plugins/autogrind/skills/autogrind/SKILL.md must always be identical. The pre-commit hook (.git/hooks/pre-commit) also enforces sync between the root and marketplace copies of commands/start.md.

Read the full file on GitHub · 422 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.

  1. 9d ago First seen · 422 lines · 5,886 tokens per session scan A 0214600128e1

Subscribe to this mod's changes

autogrind CLAUDE.md is an instructions file published in the GitHub repository ttttonyhe/autogrind (7 stars, last pushed 5mo ago), licensed MIT. It adds 5,886 tokens to every session, about $0.0294 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens