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-plugins-hitl-budgetgit 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-plugins-hitl-budget)<a href="https://agentmods.dev/skills/ruc-nlpir/arbor/arbor-agent-plugins-hitl-budget"><img src="https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-plugins-hitl-budget/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-plugins-hitl-budget"><img src="https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-plugins-hitl-budget.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 | $0.00076 | $0.00914 |
| Opus 5.5 | $0.00030 | $0.00366 |
| Sonnet 5.5 | $0.00015 | $0.00183 |
| Haiku 4.5 | $0.00008 | $0.00091 |
Grade A, and why
arbor-agent-plugins-hitl-budget 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arbor Plugins, HITL, And Budget
Use this when run behavior is modified by configuration rather than by code.
Plugin Contract
A plugin is a YAML domain adapter. It can define:
- Prompt injections:
meta_preamble_inject,meta_init_inject,meta_ideate_inject,meta_decide_inject,sub_preamble_inject,sub_workflow_inject. eval_contract: prefilled metadata such asmetric_direction,eval_cmd,submission_path, andsample_submission_path.protected_paths: globs a branch must not modify.required_outputs: files that must exist for merge.config_overridesand namedprofiles.lifecycle_hooks:on_workspace_setup,after_executor,on_finalize.convergence: early stop policy.
Plugin precedence:
defaults < plugin.config_overrides < active profile < project YAML < CLI
MLE/Kaggle Mode
The built-in mle_kaggle plugin is performance-first:
- Novelty has zero value; only metric improvement matters.
skills_enabledmay be disabled for strict idea drafting because parameter tuning, prompt edits, feature engineering, ensembling, and scaling can be valid.- A valid
submission.csvis a first-class artifact. - Data/eval directories are protected.
- Merge requires required outputs and verified score.
Priority:
- Produce and evaluate a valid baseline submission.
- Establish robust validation.
- Explore diverse approach families.
- Refine promising families.
- Ensemble/blend diverse winners.
- Reserve finalization time for best submission recovery.
Budget Policy
Default Arbor behavior favors long real experiments. Do not invent staged budgets unless configured.
If budget_policy.stages exists, use configured stages such as smoke,
pilot, and full with RunTraining(budget_stage=...).
If require_cost_estimate is true, every idea needs:
- estimated wall time;
- minimal smoke test;
- promotion gate from cheap to expensive fidelity.
Do not launch a new executor when remaining budget cannot cover the executor plus finalization buffer.
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 · 122 lines · 76 tokens per session scan A 5ae23237633d
arbor-agent-plugins-hitl-budget is a skill published in the GitHub repository RUC-NLPIR/Arbor (1,150 stars, last pushed 12d ago), licensed Apache-2.0. It adds 76 tokens to every session and 914 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-plugins-hitl-budget compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| arbor-agent-plugins-hitl-budgetRUC-NLPIR/Arbor | Skill | 1.1k | 12d ago | Apache-2.0 | A | 76 | Claude Code, Codex |
| skill-forgeGodModeAI2025/skill-forge | Skill | 20 | 1mo ago | MIT | A | 276 | Claude Code, Codex |
| reflection-coachpaperclipai/paperclip | Skill | 114k | today | MIT | A | 38 | Claude Code, Codex |
| agents-autogptdavila7/claude-code-templates | Skill | 34k | today | MIT | A | 38 | Claude Code, Codex |
| paperclip-capsulespaperclipai/paperclip | Skill | 114k | today | MIT | A | 41 | Claude Code, Codex |
| refactor-changedzhng/skills | Skill | 1.5k | 2d ago | MIT | A | 80 | Claude Code, Codex |
| write-skillsdzhng/skills | Skill | 1.5k | 2d ago | MIT | A | 50 | Claude Code, Codex |