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-executorgit 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-executor)<a href="https://agentmods.dev/skills/ruc-nlpir/arbor/arbor-agent-executor"><img src="https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-executor/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-executor"><img src="https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-executor.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 | $0.00063 | $0.01362 |
| Opus 5.5 | $0.00025 | $0.00545 |
| Sonnet 5.5 | $0.00013 | $0.00272 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
arbor-agent-executor 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arbor Executor
Use this when a pending Idea Tree leaf is selected for implementation.
Dispatch Contract
The executor receives:
- Isolated worktree path and experiment branch.
- Node id and exact hypothesis.
- Evaluation info from tree metadata with
{cwd}and{node_id}substituted. - Ancestor insights.
- Additional context from the coordinator.
The executor must implement the assigned idea faithfully. It may choose how to implement the idea, but it must not silently switch to a different direction.
Worktree Lifecycle
Native RunExecutor does this automatically:
- Validate node exists and is
pendingorrunning. - Enforce leaf-only dispatch when
max_tree_depthis set. - Mark node
running. - Create a git worktree from current trunk.
- Run the executor agent in that worktree.
- Finalize useful code changes with a commit.
- Snapshot plugin outputs such as
submission.csvif configured. - Remove the worktree but preserve the experiment branch.
- Parse the executor report.
- Update the node as
donewithscore,insight,result, andcode_ref. - Save experiment artifacts under
experiments/<node_id>/. - Propagate insights upward.
When emulating manually, do the same sequence. Use arbor-agent-tools for
prompt generation and tree updates.
Executor Workflow
The executor follows this loop:
- Understand: read relevant files before editing.
- Implement: make the idea active in code.
- Validate implementation: run 2-3 small representative checks.
- Iterate until solid: fix bugs and integration misses before judging the idea.
- Evaluate: run the full B_dev eval once implementation is credible.
- Report: include changes, baseline vs result, absolute score, and insight.
A bad score is useful only if the implementation was correct. Do not conclude an idea failed from broken code.
Evaluation Rules
- Use B_dev only. Never run B_test during routine executor work.
- Use the eval command injected from metadata. It should already target the
executor worktree after
{cwd}substitution. - Save results to
results/<node_id>-<brief-description>/. - Report absolute score, not delta.
- If full eval is expensive, run smoke/subset checks first, then full eval when code is correct.
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 · 159 lines · 63 tokens per session scan A 54f445fb2591
arbor-agent-executor is a skill published in the GitHub repository RUC-NLPIR/Arbor (1,150 stars, last pushed 12d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,362 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.
arbor-agent-executor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| arbor-agent-executorRUC-NLPIR/Arbor | Skill | 1.1k | 12d ago | Apache-2.0 | A | 63 | Claude Code, Codex |
| ratchet-filesdzhng/skills | Skill | 1.5k | 2d ago | MIT | A | 118 | Claude Code, Codex |
| port-featuresdzhng/skills | Skill | 1.5k | 2d ago | MIT | A | 77 | Claude Code, Codex |
| handoff-specdzhng/skills | Skill | 1.5k | 2d ago | MIT | A | 19 | Claude Code |
| shipevo-hq/evo | Skill | 1.5k | 1mo ago | Apache-2.0 | A | 114 | Claude Code |
| skill-forgeGodModeAI2025/skill-forge | Skill | 20 | 1mo ago | MIT | A | 276 | Claude Code, Codex |
| release-announcementpaperclipai/paperclip | Skill | 114k | today | MIT | A | 42 | Claude Code, Codex |