Arbor is an autonomous research agent that proposes hypotheses, edits code, runs experiments, and retains improvements that succeed on held-out data in a growing hypothesis tree. Researchers use it to investigate problems and iteratively optimize solutions with real experiments. The catalogue skills and plugin expose Arbor's research-agent workflow to coding agents.
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 RUC-NLPIR/Arbor --skill arbor-agent-orchestratorgit clone --depth 1 https://github.com/RUC-NLPIR/ArborWrote 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/ruc-nlpir/arbor/arbor-agent-orchestrator)<a href="https://agentmods.dev/skills/ruc-nlpir/arbor/arbor-agent-orchestrator"><img src="https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-orchestrator/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/ruc-nlpir/arbor/arbor-agent-orchestrator"><img src="https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 143 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 | $0.00077 | $0.01791 |
| Opus 5 | $0.00039 | $0.00896 |
| Sonnet 5 | $0.00015 | $0.00358 |
| Haiku 4.5 | $0.00008 | $0.00179 |
Grade A, and why
arbor-agent-orchestrator 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arbor Agent Orchestrator
Use this as the first skill for an Arbor-style research run. It is the phase
loader and policy owner; load the smaller skills only when their phase applies.
For normal user-facing use, prefer starting with arbor-research-agent; that
wrapper performs Arbor-style intake and then loads this orchestrator.
Source Model
This suite mirrors the open-source branch of arbor, not the older
single hypothesis-tree extraction. The product entry point is arbor; the run
architecture is:
- Intake/planning agent creates a research contract.
- Coordinator runs one persistent ReAct loop and owns the Idea Tree.
- Executors implement ideas in isolated git worktrees.
- Merge/eval tooling protects B_test and trunk.
- SearchAgent annotates validated nodes with related work.
- Plugins, HITL, budget policy, checkpoint/resume, dashboard, and report are first-class behavior, not optional notes.
Read references/source-map.md when auditing against the source tree or when
you need exact file origins.
Read references/compatibility.md when packaging the suite for another agent
runtime or checking Codex/Claude Code portability.
Phase Loading Order
-
Launch and contract: load
arbor-agent-setup-intake. Establish target cwd, metric, baseline status, budget, scope preference, dev/test discipline, config/plugin choice, and session directory. -
Coordinator loop: load
arbor-agent-coordinator. Run INIT, OBSERVE, IDEATE, SELECT, DISPATCH, DECIDE until the cycle cap, budget limit, or diminishing returns says to stop. -
IDEATE only: load
arbor-agent-ideate. This is a hard gate for novelty/scientific runs. It must followTreeView(format="constraints")and precede everyTreeAddNode. If a plugin disables strict skills for performance-first MLE/Kaggle, use the free-form path described byarbor-agent-plugins-hitl-budgetinstead. -
Executor dispatch: load
arbor-agent-executor. Use forRunExecutor/RunExecutorParallelbehavior, worktree lifecycle, executor prompts, longRunTrainingcommands, report parsing, artifact capture, and tree updates.
What ships with it
3 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.
- 10d ago First seen · 151 lines · 77 tokens per session scan A 9f970b414cbc
arbor-agent-orchestrator is a skill published in the GitHub repository RUC-NLPIR/Arbor (1,060 stars, last pushed 2d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,791 once invoked, about $0.0004 per session on Opus 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
mimic-apsiii-24h-raw
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
clinical-research-analysis-framework
Guided workflow for statistical and ML analysis of clinical data. Use when planning or executing research analyses on MIMIC, eICU, or similar EHR data. Ensures methodological rigor through structured consultation, assumption checking, and stepwise execution with audit trails.
clinical-research-session
Start a structured clinical research session. Use when users describe research goals, want to analyze cohorts, investigate hypotheses, or need a rigorous research plan. Interviews the user, then produces a research protocol.
apache-iv-score
Calculate APACHE IV (Acute Physiology and Chronic Health Evaluation IV) score for ICU mortality prediction. Use for severity assessment, hospital mortality prediction, ICU benchmarking, or case-mix adjustment. eICU has pre-computed scores; MIMIC-IV requires custom implementation with diagnosis mapping challenges.
oasis-score
Calculate OASIS (Oxford Acute Severity of Illness Score) for ICU patients. Use for mortality prediction with fewer variables than APACHE/SAPS, or when lab data is limited.
sapsii-score
Calculate SAPS-II (Simplified Acute Physiology Score II) for ICU patients. Use for mortality prediction, severity assessment, or international ICU benchmarking.