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/agent-field/agentfield/claude-mdgit clone --depth 1 https://github.com/Agent-Field/agentfieldWhat 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 | $0.03675 | $0.03675 |
| Opus 5 | $0.01837 | $0.01837 |
| Sonnet 5 | $0.00735 | $0.00735 |
| Haiku 4.5 | $0.00367 | $0.00367 |
Grade A, and why
agentfield 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 344 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.
Project Overview
AgentField is a Kubernetes-style control plane for AI agents. It provides production infrastructure for deploying, orchestrating, and observing multi-agent systems with cryptographic identity and audit trails.
Architecture: Three-tier monorepo
- Control Plane (Go): Orchestration server providing REST/gRPC APIs, workflow execution, observability, and cryptographic identity
- SDKs (Python & Go): Libraries for building agents that communicate with the control plane
- Web UI (React/TypeScript): Embedded admin interface for monitoring workflows and managing agents
Development Setup
Prerequisites
- Go 1.23+
- Python 3.8+
- Node.js 20+
- PostgreSQL 15+ (for PostgreSQL storage mode)
Initial Setup
# Install all dependencies
make install
# Or install components individually:
./scripts/install.sh
# Build everything
make build
Running the Control Plane
Local mode (uses SQLite + BoltDB, no external dependencies):
cd control-plane
go run ./cmd/af dev
# Or: go run ./cmd/agentfield-server
PostgreSQL storage mode:
# Run migrations first
cd control-plane
export AGENTFIELD_DATABASE_URL="postgres://agentfield:agentfield@localhost:5432/agentfield?sslmode=disable"
goose -dir ./migrations postgres "$AGENTFIELD_DATABASE_URL" up
# Start server
AGENTFIELD_STORAGE_MODE=postgres \
AGENTFIELD_DATABASE_URL="postgres://agentfield:agentfield@localhost:5432/agentfield?sslmode=disable" \
go run ./cmd/agentfield-server
Docker Compose (includes PostgreSQL):
cd deployments/docker
docker compose up
Control plane runs at http://localhost:8080
Web UI accessible at http://localhost:8080/ui/
Common Commands
Building
make build # Build all components
make control-plane # Build control plane only
make sdk-go # Build Go SDK
make sdk-python # Build Python SDK
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.
- 3d ago First seen · 344 lines · 3,675 tokens per session scan A 0751c9544e2e
agentfield CLAUDE.md is an instructions file published in the GitHub repository Agent-Field/agentfield (2,545 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,675 tokens to every session, about $0.0184 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
optillm CLAUDE.md
Instructions for algorithmicsuperintelligence/optillm, covering claude.md, project overview, core architecture, main components and development commands.
mini-swe-agent copilot-instructions.md
Copilot instructions for SWE-agent/mini-swe-agent, covering style guide, test style, bad and good.
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
thinkrail AGENTS.md
Instructions for JetBrains/thinkrail, covering thinkrail, module structure & boundaries (top-priority requirement), engine: pi only, in-process, architecture (three rings) and repo layout.
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).