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-coordinatorgit 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-coordinator)<a href="https://agentmods.dev/skills/ruc-nlpir/arbor/arbor-agent-coordinator"><img src="https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-coordinator.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Memory Poisoning · line 47 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00070 | $0.01289 |
| Opus 5 | $0.00035 | $0.00645 |
| Sonnet 5 | $0.00014 | $0.00258 |
| Haiku 4.5 | $0.00007 | $0.00129 |
Grade A, and why
arbor-agent-coordinator 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 8d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arbor Coordinator
Use this to run the strategic loop. The coordinator is a research commander, not the code author.
Coordinator Role
- Do not edit benchmark code directly.
- Maintain the Idea Tree as durable memory.
- Dispatch executors to implement leaf ideas.
- Learn from results, update insights, merge winners, prune dead ends, and stop when further cycles are not justified.
- Treat user dashboard notes as operator input, not benchmark evidence.
Arbor Cycle
Step 0: INIT
Run once at the start unless resuming.
- Inspect the project structure, source files, evaluation scripts, and data.
- Identify B_dev and B_test.
- Run or locate the unmodified baseline on B_dev.
- Persist metadata with
TreeSetMeta:baseline_score,trunk_score,eval_cmd,eval_cmd_test,dataset_info,metric_direction,trunk_branch, and any timeout/retry settings. - If a plugin supplies an
eval_contract, prefill the matching metadata.
If resuming, skip INIT and call TreeView to re-orient.
If the run is smoke-only, do not run expensive baselines or inherited real
eval commands. Persist a cheap cached-score parser or explicitly mocked score
as the eval command, set short timeout metadata, and mark dataset_info and
node reports as smoke-only.
Step 1: OBSERVE
Read code, logs, prior experiment reports, tree insights, failure cases, and
score patterns. Focus on failure classes and bottlenecks, not just symptoms.
For large logs, use arbor_state.py parse-log or normalize carriage returns
before matching metric lines. Do not flood context with full training logs
during smoke or forward tests.
Step 2: IDEATE
- Call
TreeView(format="constraints")first. - If strict skills are enabled, immediately load
arbor-agent-ideate. - Add only ideas that pass the ideation gate.
Depth semantics:
- Depth 0: root objective and global insight.
- Depth 1: broad strategy categories.
- Depth 2+: concrete implementable approaches.
Step 3: SELECT
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.
- 8d ago First seen · 160 lines · 70 tokens per session scan A a0cc16d415a3
arbor-agent-coordinator is a skill published in the GitHub repository RUC-NLPIR/Arbor (1,059 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 1,289 once invoked, about $0.0003 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
skill-forge
Autonome Verbesserung nach dem Autoresearch-Paradigma (Karpathy). Zwei Modi: (1) Skill-Modus — optimiert eine SKILL.md durch iterative Mutation und Evaluation. (2) Generic-Modus — optimiert beliebige Dateien gegen jede mechanische Metrik (Testabdeckung, Bundle-Size, Lighthouse-Score, Docker-Image-Größe, etc.). Zwei…
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
autocontext-consumer
Use when an agent needs to USE knowledge Autocontext already produced - find which scenarios have knowledge, read the playbook and lessons for one, understand the on-disk file and folder layout, and move knowledge between checkouts. Host-agnostic; requires only the autoctx CLI and the filesystem.
autocontext-creator
Use when an agent needs to CREATE knowledge with Autocontext - run a scenario or plain-language task through the improvement loop, judge or improve a single output, and inspect what the run produced. Host-agnostic; requires only the autoctx CLI.
autocontext
Iterative strategy generation and evaluation system. Use when the user wants to evaluate agent output quality, run improvement loops, queue tasks for background evaluation, check run status, inspect runtime artifacts and session branch lineage, or discover available scenarios. Provides LLM-based judging with…
codex-autoresearch
Triage improvement work and run or resume accepted measured loops in a local project. Architecture, documentation, UX, product study, open research, taste, and one-shot fixes stay direct unless the user explicitly requests repeated measurement with a complete experiment contract.