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.
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 harbor-framework/harbor --skill create-adaptergit 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/skills/harbor-framework/harbor/create-adapter)<a href="https://agentmods.dev/skills/harbor-framework/harbor/create-adapter"><img src="https://agentmods.dev/badge/skills/harbor-framework/harbor/create-adapter/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/harbor-framework/harbor/create-adapter"><img src="https://agentmods.dev/badge/skills/harbor-framework/harbor/create-adapter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.01676 |
| Opus 5.5 | $0.00014 | $0.00670 |
| Sonnet 5.5 | $0.00007 | $0.00335 |
| Haiku 4.5 | $0.00003 | $0.00168 |
Grade A, and why
create-adapter 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 1mo 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- create-adapter — 100% identical, 4 lines differ
- create-adapter — 92% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Adapter
Bootstrap a new benchmark adapter in the Harbor repository. This skill scaffolds the adapter directory with harbor adapter init and then defers to the adapter tutorial for every implementation decision.
Authoritative reference
The adapter tutorial is the authoritative specification for this skill. Read it in full before taking any action beyond scaffolding:
adapters/ADAPTER_CONTRIBUTING.md
That path is relative to the Harbor repo root (a skill prerequisite — see below). The tutorial contains:
- Required directory structures for the generated tasks and the adapter code package.
- Step-by-step process (steps 1-9) covering benchmark analysis, oracle verification, parity experiments, dataset registration, and submission.
- Schemas for
task.toml,parity_experiment.json,adapter_metadata.json, anddataset.toml. - Parity matching criterion, pre-flight checklist, and debug playbook.
- README format rules (machine-parsed; deviations break automation).
Do not substitute prior knowledge for the contents of that file. Treat it as the contract.
Prerequisites
- Harbor CLI is installed and available on
PATH(harbor --versionsucceeds). - Working directory is the Harbor repository root.
- Harbor checkout is current: run
git fetch origin && git statusand pullmainif behind. Stale checkouts miss recent adapter and agent fixes and are a common source of spurious parity failures later on.
Workflow
1. Read the tutorial
Before any filesystem or CLI action, Read adapters/ADAPTER_CONTRIBUTING.md in full. Pay particular attention to:
- Required Directory Structures — the contract for generated task and adapter layouts.
- Step 1. Understand the Original Benchmark — what to identify upstream before coding.
- Step 8. Register the Dataset → Naming rules — the
namefield and<org>/<task>format requirements.
2. Gather benchmark context from the user
Collect the following before scaffolding. If the user has not provided an item, ask before proceeding — these inputs shape the scaffold and the tutorial steps that follow.
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.
- 1mo ago Changed a15e47e80b13
- 2mo ago First seen · 116 lines · 34 tokens per session scan A e9e912e237f1
create-adapter is a skill published in the GitHub repository harbor-framework/harbor (6,630 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 1,676 once invoked, about $0.0001 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 skills, from other repositories
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
evaluate-skill
Run, read, and diagnose a skill's Caliper eval — its success rate over k attempts, whether it fires, and whether it beats the agent without it. Use when the user wants to run, validate, interpret, or compare a skill's eval, or write an .eval.yaml spec whose tasks they have already decided.
writing-skills
Use when creating a new skill, editing an existing skill, or verifying skills work before deployment.
evals-implement
Use when a published goldset is ready to become executable graders and configs — Python graders and metrics with auto-run unit tests verifying grader correctness.
evals-clarify
Use when draft eval criteria need refining, clustering, and acceptance into the published goldset with an isolated holdout split (goldset.md + goldset.json).
evals-init
Use when standing up evals/{system}/ for the first time — scaffolds the EDD directory structure, picks PromptFoo or DeepEval by tech stack, and generates a security baseline.