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 harbor-execgit 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/harbor-exec)<a href="https://agentmods.dev/skills/harbor-framework/harbor/harbor-exec"><img src="https://agentmods.dev/badge/skills/harbor-framework/harbor/harbor-exec/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/harbor-exec"><img src="https://agentmods.dev/badge/skills/harbor-framework/harbor/harbor-exec.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 | $0.00071 | $0.00779 |
| Opus 5.5 | $0.00028 | $0.00312 |
| Sonnet 5.5 | $0.00014 | $0.00156 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
harbor-exec 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 2mo 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:
- harbor-exec — 100% identical, 0 lines differ
- harbor-exec — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harbor Exec
Overview
Use this skill to operate Harbor's harbor exec command. Treat harbor exec as agentic map-reduce: it turns loose inputs into Harbor tasks, runs Harbor jobs over those tasks, and optionally aggregates the results.
First Checks
Assume the user is running an installed Harbor CLI. Check the installed command surface before making claims:
harbor --version
harbor exec --help
Require Harbor >=0.17.1 for harbor exec. If harbor --version reports an older version, ask the user to upgrade before continuing.
Use --print-config when debugging config resolution, inferred artifacts, task/job directories, or defaults. Do not treat it as a substitute for showing the final launch command.
If the installed harbor command is not available, ask the user how they installed Harbor before guessing a command path.
Run Parameter Questions
Before running a Harbor Exec job, ask the user to confirm any unspecified run parameters:
- Inputs: exact paths/globs and whether to
--scanor--no-scan. - Artifact contract: output file paths the agent must write.
- Artifact schemas: required JSON or structured schema for each artifact.
- Environment provider: recommend cloud sandboxing over local
docker; suggestmodal,daytona, ore2b. - Agent and model for the map step.
- Concurrency count.
- Whether to include a reduce step, and if so which reduce agent and model to use.
- Final command: show the exact launch command before running it.
Usage Workflow
Prefer flags for one-off runs and --config for repeatable or map-reduce workflows.
Make artifacts explicit when correctness depends on generated files:
harbor exec -p ./input -i "Write /app/answer.json" -f /app/answer.json
Prefer explicit artifacts over auto-inferred artifacts. Auto-inference only reads inline instructions, not instruction files.
Do not persist compiled tasks by default. Omit --tasks-dir unless the user wants to inspect or reuse compiled tasks; when omitted, compiled tasks are ephemeral and cleaned up after execution.
What ships with it
1 file 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.
- 2mo ago First seen · 77 lines · 71 tokens per session scan A 7a74b4a046bb
harbor-exec is a skill published in the GitHub repository harbor-framework/harbor (6,630 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 779 once invoked, about $0.0003 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
research-report
Research report on companies, competitors, markets or products: research a company, compare competitors, market landscape, funding, pricing, launches. Also to save a brief, summary or snapshot built from search results.
da-anomaly-analysis
Metric anomaly investigation: DAU, GMV, conversion, retention, revenue, KPI or dashboard metric drop, dropped, fell, spike or spiked. Metric attribution and funnel breakdown.
meeting-prep
Meeting prep: brief me before a meeting, call, standup, 1:1 or pitch — who I'm meeting, background, talking points; prep me, ready.
schedule-meeting
Schedule, book or set up a meeting, call, coffee, lunch, dinner, event or appointment on my calendar.
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
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…