fulling AGENTS.md

A set of instructions that tells coding agents how a specific Fulling project is organised and built. It covers the project’s purpose, technologies, coding rules, and current implementation details.

In plain words
What is it for?
Use it when working on the Fulling v3.0 repository, especially for product or architecture work, authentication, Kubernetes, database, and TypeScript changes.
Why use it?
It gives an agent the project context it needs before changing code, reducing guesswork about structure and conventions.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/fullagent/fulling/agents-md
Clone the repo
git clone --depth 1 https://github.com/FullAgent/fulling

Made for: Codex, OpenCode.

Per session 874 This file is loaded in full into every session.
When invoked 874 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00874 $0.00874
Opus 5 $0.00437 $0.00437
Sonnet 5 $0.00175 $0.00175
Haiku 4.5 $0.00087 $0.00087

Measured yesterday against content hash 4e446afeb2f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fulling 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 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.

AGENTS.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.

AGENTS.md

This file provides guidance to AI agents when working with code in this repository.

Project Overview

Fulling v3.0 is building dedicated AI workspaces — persistent, personalizable environments with skills, files, memory, scripts, and runtime. Think of it as an out-of-the-box AI toolkit that users can customize and share.

Read docs/architecture.md before product or architecture work. It is the source of truth for the v3 workspace model.

Tech Stack

  • Next.js 16 (App Router) + React 19 + TypeScript
  • Tailwind CSS v4 + Shadcn/UI
  • Node.js 24 + Prisma + Better Auth
  • Kubernetes + PostgreSQL

Code Conventions

  • TypeScript strict mode
  • Functional components with hooks
  • In lib/platform/: one primary action per file, noun directories + verb file names, boundary comment above main exported function
  • Route-specific components in _components/ directory
  • Shared components in top-level components/

Current Implementation Context

  • GitHub is the only authentication provider.
  • Better Auth stores users, provider accounts, and sessions in PostgreSQL.
  • Each user may store one plaintext kubeconfig; browser APIs never return it.
  • Always use the user-specific K8s service: const k8sService = await getK8sServiceForUser(userId).
  • The current user-level kubeconfig is a foundation boundary, not the final v3 Workspace Runtime ownership model.

UI Direction

The active v3 design system is defined in docs/design.md. It derives from SST and is the source of truth for Fulling's visual language, tokens, typography, spacing, components, states, and responsive behavior. Read it before substantial UI work. Existing UI that conflicts with it is migration work, not design precedent.

Avoid generic AI copywriting cliches such as "Elevate", "Seamless", and "Unleash".

Key Files

  • docs/architecture.md — v3 system architecture and product model
  • docs/design.md — active v3 design system and SST-derived style reference
  • lib/auth/ — Better Auth and application session boundary
  • lib/kubeconfig/ — User credential persistence
  • lib/k8s/ — Validation and user-specific Kubernetes service

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.

  1. yesterday First seen · 105 lines · 874 tokens per session scan A 4e446afeb2f3

Subscribe to this mod's changes

fulling AGENTS.md is an instructions file published in the GitHub repository FullAgent/fulling (2,440 stars, last pushed 15d ago), licensed MIT. It adds 874 tokens to every session, about $0.0044 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.