AGENTS.md@people/harrison-chase/harborA

AGENTS.md@people/harrison-chase/harbor from marco-trotta1/awesome-agents-md is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add marco-trotta1/awesome-agents-md/people/harrison-chase/harbor/AGENTS.md@git:20260803.d8f40f1

Pins git:20260803.d8f40f1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
marco-trotta1/awesome-agents-md
Path
people/harrison-chase/harbor/AGENTS.md
Versions recorded
1
Latest version
git:20260803.d8f40f1, committed Aug 3, 2026
Size
15,544 bytes
Repository stars
5
License
a license file GitHub does not identify

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# CLAUDE.md - Harbor Framework

> **Breaking changes**: See [CHANGELOG.md](CHANGELOG.md) for recent breaking changes to the agent and environment APIs and migration guidance.

## 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

```bash
# Install
uv tool install harbor

# Run a benchmark
harbor run --dataset terminal-bench@2.0 --agent claude-code --model anthropic/claude-opus-4-1 --n-concurrent 4

# Pass environment variables to the agent
harbor run --dataset terminal-bench@2.0 --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
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add marco-trotta1/awesome-agents-md/people/harrison-chase/harbor/AGENTS.md@sha256:1ebaacc714b1c8b6

The line at the top of this page pins the label git:20260803.d8f40f1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6imqyflrzzrz2in4.svg)](https://markdownregistry.com/a/art_6imqyflrzzrz2in4)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in marco-trotta1/awesome-agents-md/people/harrison-chase/harbor/AGENTS.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of AGENTS.md from somewhere else? Ask it: where did my AGENTS.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Aug 3, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260803.d8f40f1 latest2026-08-03 d8f40f1 15,544 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (15544 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

marco-trotta1/awesome-agents-md · 5 stars · license a license file GitHub does not identify · pushed 2026-08-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6imqyflrzzrz2in4
GET https://markdownregistry.com/api/v1/resolve?ref=marco-trotta1/awesome-agents-md/people/harrison-chase/harbor/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/1ebaacc714b1c8b6f28bf7a4d8adfe49feb70ff377bfed680bfb7f45ba683214

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from marco-trotta1/awesome-agents-md

CLAUDE.md@derived/andrej-karpathy/forrestchang CLAUDE.md file
marco-trotta1/awesome-agents-md · derived/andrej-karpathy/forrestchang/CLAUDE.md
git:20260803.d8f40f1 · audit A · 5 stars
skill-creator SKILL.md skill
marco-trotta1/awesome-agents-md · labs/anthropic/skills/skill-creator/SKILL.md · Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a…
git:20260803.d7e8942 · audit A · 5 stars
AGENTS.md@labs/openai/codex AGENTS.md file
marco-trotta1/awesome-agents-md · labs/openai/codex/AGENTS.md
git:20260803.d7e8942 · audit A · 5 stars
AGENTS.md@labs/openai/openai-agents-python AGENTS.md file
marco-trotta1/awesome-agents-md · labs/openai/openai-agents-python/AGENTS.md
git:20260803.d7e8942 · audit A · 5 stars
AGENTS.md@people/addy-osmani/agent-skills AGENTS.md file
marco-trotta1/awesome-agents-md · people/addy-osmani/agent-skills/AGENTS.md
git:20260803.4947fb2 · audit A · 5 stars
CLAUDE.md@people/addy-osmani/agent-skills CLAUDE.md file
marco-trotta1/awesome-agents-md · people/addy-osmani/agent-skills/CLAUDE.md
git:20260803.4947fb2 · audit A · 5 stars
AGENTS.md@people/affaan-hussein/everything-claude-code AGENTS.md file
marco-trotta1/awesome-agents-md · people/affaan-hussein/everything-claude-code/AGENTS.md
git:20260803.d8f40f1 · audit A · 5 stars
CLAUDE.md@people/affaan-hussein/everything-claude-code CLAUDE.md file
marco-trotta1/awesome-agents-md · people/affaan-hussein/everything-claude-code/CLAUDE.md
git:20260803.d8f40f1 · audit A · 5 stars
read-arxiv-paper SKILL.md skill
marco-trotta1/awesome-agents-md · people/andrej-karpathy/nanochat/.claude/skills/read-arxiv-paper/SKILL.md · Use this skill when asked to read an arxiv paper given an arxiv URL
git:20260803.d8f40f1 · audit A · 5 stars
CLAUDE.md@people/ashwin-bhat/claude-code-action CLAUDE.md file
marco-trotta1/awesome-agents-md · people/ashwin-bhat/claude-code-action/CLAUDE.md
git:20260803.fc07574 · audit A · 5 stars
AGENTS.md@people/boris-cherny/openclaw AGENTS.md file
marco-trotta1/awesome-agents-md · people/boris-cherny/openclaw/AGENTS.md
git:20260803.d8f40f1 · audit A · 5 stars
CLAUDE.md@people/boris-cherny/openclaw CLAUDE.md file
marco-trotta1/awesome-agents-md · people/boris-cherny/openclaw/CLAUDE.md
git:20260803.d8f40f1 · audit B · 5 stars

Every file in marco-trotta1/awesome-agents-md

Browse by kind, by grade A, or by owner.