Harbor is a framework for evaluating and improving AI agents and language models across reusable benchmarks and execution environments. Developers and researchers use it to run agent evaluations, create benchmarks, perform parallel experiments, and generate rollouts for reinforcement-learning optimization, with the catalogue offering skills, instructions, and an MCP integration for the framework.
Borrowing it
Nothing to install: this file belongs to harbor-framework/harbor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/harbor-framework/harbor/main/AGENTS.mdgit clone --depth 1 https://github.com/harbor-framework/harborWrote 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.
[](https://agentmods.dev/instructions/harbor-framework/harbor/agents-md)<a href="https://agentmods.dev/instructions/harbor-framework/harbor/agents-md"><img src="https://agentmods.dev/badge/instructions/harbor-framework/harbor/agents-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.
<a href="https://agentmods.dev/instructions/harbor-framework/harbor/agents-md"><img src="https://agentmods.dev/badge/instructions/harbor-framework/harbor/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.04267 | $0.04267 |
| Opus 5.5 | $0.01707 | $0.01707 |
| Sonnet 5.5 | $0.00853 | $0.00853 |
| Haiku 4.5 | $0.00427 | $0.00427 |
Grade A, and why
harbor 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 today.
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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Harbor Framework
Breaking changes: See CHANGELOG.md for recent breaking changes to the agent and environment APIs and migration guidance. Do not add anything that is temporary or not a major change.
Contributing
Refer to the CONTRIBUTING.md file for guidelines on how to contribute.
Project Overview
Harbor is a framework for evaluating and optimizing AI agents and language models. It provides:
- Agent Evaluation: Run evaluations of arbitrary agents (Claude Code, OpenHands, Codex CLI, Aider, etc.) against benchmark tasks
- Benchmark Support: Interface with standard benchmarks (SWE-Bench, Terminal-Bench, Aider Polyglot, etc.)
- Parallel Execution: Conduct experiments in thousands of environments in parallel via providers like Daytona and Modal
- RL Optimization: Generate rollouts for reinforcement learning optimization
Quick Start Commands
# Install
uv tool install harbor
# Run a benchmark
harbor run --dataset [email protected] --agent claude-code --model anthropic/claude-opus-4-1 --n-concurrent 4
# Pass environment variables to the agent
harbor run --dataset [email protected] --agent claude-code --model anthropic/claude-opus-4-1 \
--ae AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
--ae AWS_REGION=us-east-1
# List available datasets
harbor datasets list
# Get help
harbor run --help
Repository Structure
This is a monorepo containing the Harbor CLI, documentation website, and results viewer.
harbor/
├── src/harbor/ # Main CLI source code
│ ├── agents/ # Agent implementations
│ │ ├── base.py # BaseAgent abstract class
│ │ ├── factory.py # Agent factory for instantiation
│ │ ├── installed/ # Built-in agent implementations
│ │ ├── terminus_2/ # Terminus agent implementation
│ │ ├── oracle.py # Oracle agent (for testing)
│ │ └── nop.py # No-op agent
│ ├── cli/ # Command-line interface (Typer-based)
│ │ ├── main.py # Main CLI entry point
│ │ ├── jobs.py # Job management commands
│ │ ├── datasets.py # Dataset commands
│ │ ├── trials.py # Trial management
│ │ ├── tasks.py # Task management
│ │ ├── traces.py # Trace viewing
│ │ ├── sweeps.py # Parameter sweeps
│ │ ├── adapters.py # Adapter commands
│ │ ├── adapter_wizard.py # Interactive adapter creation
│ │ ├── publish.py # Package publishing
│ │ ├── analyze.py # Analysis commands
│ │ ├── cache.py # Cache management
│ │ ├── view.py # Results viewing
│ │ ├── admin/ # Admin commands
│ │ ├── annotator/ # Annotation tools
│ │ ├── quality_checker/ # Quality verification
│ │ ├── template-adapter/ # Adapter templates
│ │ ├── template-metric/ # Metric templates
│ │ └── template-task/ # Task templates
│ ├── environments/ # Execution environments
│ │ ├── base.py # BaseEnvironment abstract class
│ │ ├── factory.py # Environment factory
│ │ ├── docker/ # Local Docker environment
│ │ ├── daytona.py # Daytona cloud environment
│ │ ├── e2b.py # E2B environment
│ │ ├── modal.py # Modal environment
│ │ ├── runloop.py # Runloop environment
│ │ ├── apple_container.py # Apple container environment
│ │ ├── gke.py # Google Kubernetes Engine
│ │ ├── openshift.py # Red Hat Openshift environment
│ │ ├── novita.py # Novita AI Sandbox environment
│ │ ├── runta.py # Runta cloud runtime environment
│ │ └── sail.py # Sail Sailbox environment
│ ├── models/ # Pydantic data models
│ │ ├── agent/ # Agent context and metadata
│ │ ├── job/ # Job configuration and results
│ │ ├── task/ # Task configuration
│ │ ├── trial/ # Trial configuration and results
│ │ ├── metric/ # Metric definitions
│ │ ├── package/ # Package registry models
│ │ ├── trajectories/ # ATIF trajectory format
│ │ ├── verifier/ # Verification results
│ │ └── registry.py # Dataset registry models
│ ├── orchestrators/ # Trial orchestration
│ ├── verifier/ # Test verification system
│ ├── inspect/ # Inspection utilities
│ ├── analyze/ # Analysis backend (LLM-powered)
│ ├── auth/ # Authentication (OAuth callback server)
│ ├── publisher/ # Package publishing and registry DB
│ ├── storage/ # Storage backends (Supabase)
│ ├── db/ # Database types
│ ├── llms/ # LLM integrations (LiteLLM)
│ ├── dataset/ # Dataset handling
│ ├── registry/ # Dataset registry
│ ├── tasks/ # Task utilities
│ ├── trial/ # Trial utilities
│ ├── metrics/ # Metrics collection
│ ├── mappers/ # Data mappers
│ ├── viewer/ # Results viewer UI
│ └── utils/ # Utility functions
├── adapters/ # Benchmark adapters (convert external datasets)
├── apps/
│ └── viewer/ # Results viewer web app (React Router, Vite)
├── docs/ # Documentation website (Next.js, Fumadocs)
├── examples/ # Example configurations and tasks
│ ├── tasks/ # Example task definitions
│ ├── agents/ # Agent configuration examples
│ ├── configs/ # Job configuration examples
│ ├── datasets/ # Dataset examples
│ ├── metrics/ # Custom metrics examples
│ ├── prompts/ # Prompt templates
│ └── training/ # Training examples
├── rfcs/ # RFC specifications
├── scripts/ # Utility scripts
├── skills/ # Claude Code skills
├── tests/ # Test suite
│ ├── unit/ # Unit tests
│ ├── integration/ # Integration tests
│ ├── runtime/ # Runtime tests (may need Docker)
│ └── golden/ # Golden file tests
├── dataset/ # Local dataset storage (jobs/)
├── jobs/ # Job output storage
└── trials/ # Trial output storage
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.
- today Changed · +3 lines · +68 tokens per session d57b79608fad
- 14d ago Changed · +1 lines · +16 tokens per session d8f04aa5cc6f
- 23d ago Changed · +2 lines · +27 tokens per session 5245e82a45ac
- 29d ago Changed · +1 lines · +19 tokens per session edc1d6f915ad
- 1mo ago Changed · +1 lines · +10 tokens per session 2de426660626
- 1mo ago Changed · +2 lines · +30 tokens per session f363d25497de
- 1mo ago Changed · +1 lines · +33 tokens per session 59afacf8ce94
- 2mo ago First seen · 385 lines · 4,064 tokens per session scan A 0fef49bc61d6
harbor AGENTS.md is an instructions file published in the GitHub repository harbor-framework/harbor (6,630 stars, last pushed today), licensed Apache-2.0. It adds 4,267 tokens to every session, about $0.0171 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.