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-resume-reportgit 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-resume-report)<a href="https://agentmods.dev/skills/ruc-nlpir/arbor/arbor-agent-resume-report"><img src="https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-resume-report/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-resume-report"><img src="https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-resume-report.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 | $0.00061 | $0.01015 |
| Opus 5 | $0.00030 | $0.00508 |
| Sonnet 5 | $0.00012 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
arbor-agent-resume-report 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 11d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arbor Resume And Report
Use this when a run stops, resumes, times out, or needs a durable report.
Checkpoint Files
Open-source Arbor stores the run under:
.arbor/sessions/<run_name>/
.coordinator/
idea_tree.json
idea_tree.md
checkpoint.json
messages.jsonl
events.jsonl
run_stats.json
REPORT.md
idea_tree.json is the primary state. messages.jsonl restores conversation
history. checkpoint.json stores run name, cycle number, phase, git state,
in-flight executors, cache anchors, and pending human gates.
Resume Procedure
- Require an existing
.coordinator/idea_tree.json. - Load the tree.
- Requeue nodes left as
runningby setting them back topending. - Replay
messages.jsonlif available. - Seal any dangling tool-use tail with an interrupted-result marker.
- Append a short resume nudge:
- do not restart INIT;
- call
TreeView; - continue the loop from pending nodes.
- Keep the existing workspace/session directory.
If the tree is corrupt, do not pretend resume is possible. Start a fresh run in a clean session only after making that explicit.
Events
Important event families:
session.start,session.end,session.checkpointcycle.start,cycle.end,cycle.phaseidea.proposed,idea.completed,idea.pruned,idea.mergedexecutor.start,executor.endtool.start,tool.endllm.call,llm.error,llm.cache_statuser.await,user.input_receivedprogress.heartbeat
Events are JSON-serializable and secret-free. The dashboard, WebUI, stats collector, and reports consume them.
Shutdown
Before final report:
- Wait for background SearchAgents to flush if any are pending.
- Write final checkpoint and messages.
- Run plugin
on_finalizehook if present. - On emergency timeout, recover best submission:
- keep trunk
submission.csvif present; - otherwise copy the best scored snapshot from
submissions/; - otherwise copy the most recent snapshot.
- keep trunk
- Write
run_stats.json. - Generate
REPORT.md.
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.
- 11d ago First seen · 141 lines · 61 tokens per session scan A 9e4de31e4f3c
arbor-agent-resume-report is a skill published in the GitHub repository RUC-NLPIR/Arbor (1,063 stars, last pushed 3d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,015 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…
flow-nexus-swarm
Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform.
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
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…
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.