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/fullagent/fulling/agents-mdgit clone --depth 1 https://github.com/FullAgent/fullingWhat 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 | $0.00874 | $0.00874 |
| Opus 5 | $0.00437 | $0.00437 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00087 | $0.00087 |
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.
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 boundarylib/kubeconfig/— User credential persistencelib/k8s/— Validation and user-specific Kubernetes service
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.
- yesterday First seen · 105 lines · 874 tokens per session scan A 4e446afeb2f3
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.
Other instructions, from other repositories
next-shadcn-dashboard-starter AGENTS.md
Instructions for Kiranism/next-shadcn-dashboard-starter, covering agents.md - ai coding agent reference, project overview, technology stack details, core framework & runtime and styling & ui.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, mandatory development principles and sow system.
full-stack-ai-agent-template CLAUDE.md
Instructions for vstorm-co/full-stack-ai-agent-template, covering claude.md, project overview, commands, install dependencies and run tests.
next-shadcn-dashboard-starter CLAUDE.md
Instructions for Kiranism/next-shadcn-dashboard-starter, covering claude.md, key references and critical conventions.
full-stack-ai-agent-template AGENTS.md
Instructions for vstorm-co/full-stack-ai-agent-template, covering agents.md, project overview, commands, cli and architecture.
netdata CLAUDE.md
Claude Code instructions for netdata/netdata, a project described as: The fastest path to AI-powered full stack observability, even for lean teams.