What is gru-ai CLAUDE.md?

Repository instructions for gruai, an autonomous AI company framework that organizes work into directives, projects, tasks, reports, and shared context.

Use it when working on gruai features, navigating its context files, or managing directive and project tasks.

It gives coding agents a consistent way to find instructions, understand project state, and follow the framework's work structure.

How andrew-yangy/gru-ai configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to andrew-yangy/gru-ai. 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/andrew-yangy/gru-ai/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/andrew-yangy/gru-ai

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/andrew-yangy/gru-ai/claude-md/github.svg)](https://agentmods.dev/instructions/andrew-yangy/gru-ai/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/andrew-yangy/gru-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/andrew-yangy/gru-ai/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/andrew-yangy/gru-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/andrew-yangy/gru-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,254 This file is loaded in full into every session.

When invoked 1,254 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	$0.01254	$0.01254
Opus 5	$0.00627	$0.00627
Sonnet 5	$0.00251	$0.00251
Haiku 4.5	$0.00125	$0.00125

Measured 10d ago against content hash 09d3e4ceb9a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gru-ai 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 10d 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gruai — Claude Code Rules

What This Is

An autonomous AI company framework. See .context/vision.md for the full vision.

Context Tree Structure

.context/
|-- vision.md                           # System vision (read first)
|
|-- directives/                         # ALL work lives here: Directive > Project > Task
|   |-- {id}/
|   |   |-- directive.json              # Pipeline state, weight, references
|   |   |-- directive.md                # CEO brief
|   |   |-- brainstorm.md              # OPTIONAL: pre-planning (strategic/heavyweight)
|   |   |-- audit.md                   # OPTIONAL: technical audit
|   |   +-- projects/
|   |       |-- {project-id}/
|   |       |   +-- project.json       # Tasks[], DOD, agents -- THE source of truth
|   |       +-- ...
|   +-- ...
|
|-- intel/                              # Scout outputs
|   |-- latest/                         # Overwritten each /scout run
|   +-- archive/{YYYY-MM-DD}/           # Previous runs
|
|-- reports/                            # CEO dashboard reports
|   |-- daily-{date}.md
|   |-- weekly-{date}.md
|   +-- walkthrough-{date}.md
|
|-- design/                             # System design rationale (WHY the system works this way)
|   |-- context-flow.md                 # How context reaches agents, progressive disclosure
|   |-- pipeline-architecture.md        # Why these steps, this order, weight adaptation
|   |-- agent-model.md                  # Sub-agent scoping, isolation, constraints
|   |-- verification.md                 # Reviews, DOD, trust boundaries
|   +-- state-and-recovery.md           # Persistence, checkpoints, crash recovery
|
|-- lessons/                            # Flat, topic-based knowledge (reactive — what went wrong)
|   |-- orchestration.md
|   |-- agent-behavior.md
|   |-- review-quality.md
|   |-- skill-design.md
|   +-- state-management.md

How to Read the Context Tree

"What should we do now?" -> Read directives/*/directive.json for active directives, check directives/*/projects/*/project.json for active projects
Planning a feature: -> Read vision.md + relevant directive context + design/ + lessons/ + relevant project context.md files
Building a feature: -> Read project.json for tasks (at directives/{id}/projects/{project}/project.json), relevant design/ + lessons/ files
After completing work: -> Update project.json tasks, create report.md in project dir, update design/ if new patterns established, update lessons/ if new patterns discovered

Read the full file on GitHub · 105 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.

10d ago First seen · 105 lines · 1,254 tokens per session scan A 09d3e4ceb9a6

Subscribe to this mod's changes

gru-ai CLAUDE.md is an instructions file published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 1,254 tokens to every session, about $0.0063 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.

Autonomous Agents ai-agents context-engineering harness-engineering

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

gru-ai: Instructions file for Claude Code