Best of Agent Harnesses is a curated directory of agent harnesses, which are runtimes that let AI models act by controlling tools, permissions, context, and saved state around an action loop. It helps people compare harnesses and use related templates, playbooks, and learning resources for building agentic systems. Catalogue entries include agents and other configurations that can query or support the listed harnesses.
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 skills add RyanAlberts/best-of-Agent-Harnesses --skill sandbox-checkgit clone --depth 1 https://github.com/RyanAlberts/best-of-Agent-HarnessesWrote 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/skills/ryanalberts/best-of-agent-harnesses/sandbox-check)<a href="https://agentmods.dev/skills/ryanalberts/best-of-agent-harnesses/sandbox-check"><img src="https://agentmods.dev/badge/skills/ryanalberts/best-of-agent-harnesses/sandbox-check/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/skills/ryanalberts/best-of-agent-harnesses/sandbox-check"><img src="https://agentmods.dev/badge/skills/ryanalberts/best-of-agent-harnesses/sandbox-check.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 | $0.00174 | $0.02987 |
| Opus 5.5 | $0.00070 | $0.01195 |
| Sonnet 5.5 | $0.00035 | $0.00597 |
| Haiku 4.5 | $0.00017 | $0.00299 |
Grade B, and why
sandbox-check scanned grade B with 2 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 6d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **sudo**: `sudo -n true`, the form that fails instead of asking for a password. The system log Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
compatibility: "Python 3.9+ on macOS or Linux; Python 3.11+ to compare Codex settings. Without flags nothing touches the network. The optional --network flag makes DNS lookups and TCP connections (no data sent) to github Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
The source is not reproduced here
Licensed CC-BY-SA-4.0
The repository is licensed CC-BY-SA-4.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 202 lines · 174 tokens per session scan B 83facb3fa792
sandbox-check is a skill published in the GitHub repository RyanAlberts/best-of-Agent-Harnesses (1,232 stars, last pushed 4d ago), licensed CC-BY-SA-4.0. It adds 174 tokens to every session and 2,987 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-10.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
verify-samples-tool
How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.