arbor-agent-coordinator

arbor-agent-coordinator is a skill for Codex from RUC-NLPIR/Arbor. It costs 70 tokens per session (1,289 once invoked), scanned A, original, Apache-2.0.

A coordinator guide for Arbor's research loop, where an agent maintains an idea tree and sends selected ideas to code-writing workers. It defines stages such as observing, generating ideas, selecting, testing, and deciding.

In plain words
What is it for?
Use it to inspect a project, record evaluation metadata, choose experiments, dispatch workers, update the idea tree, learn from results, merge winners, and stop when more cycles are not justified.
Why use it?
It keeps research work organized across repeated experiments instead of letting an agent make untracked changes or lose earlier findings.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Part of the arbor plugin — 11 skills shipped together

Good fit Use it to inspect a project, record evaluation metadata, choose experiments, dispatch workers, update the idea tree, learn from results, merge winners, and stop when more cycles are not justified.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ruc-nlpir/arbor/arbor-agent-coordinator
About the project

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.

RUC-NLPIR/Arbor · 1,059 stars · on GitHub · ruc-nlpir.github.io

Install

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.

Any agent
npx skills add RUC-NLPIR/Arbor --skill arbor-agent-coordinator
Clone the repo
git clone --depth 1 https://github.com/RUC-NLPIR/Arbor

Made for: Codex.

Or install arbor, the plugin that ships this one along with the rest of its 11 skills.

Wrote 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.

agentmods badge for arbor-agent-coordinator

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-coordinator.svg)](https://agentmods.dev/skills/ruc-nlpir/arbor/arbor-agent-coordinator)
Your own site
<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>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,289 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash a0cc16d415a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

skills/arbor-agent-coordinator/SKILL.md · 160 lines

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.

  1. Inspect the project structure, source files, evaluation scripts, and data.
  2. Identify B_dev and B_test.
  3. Run or locate the unmodified baseline on B_dev.
  4. Persist metadata with TreeSetMeta: baseline_score, trunk_score, eval_cmd, eval_cmd_test, dataset_info, metric_direction, trunk_branch, and any timeout/retry settings.
  5. 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

  1. Call TreeView(format="constraints") first.
  2. If strict skills are enabled, immediately load arbor-agent-ideate.
  3. 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

Read the full file on GitHub · 160 lines

Files

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.

Changes

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.

  1. 8d ago First seen · 160 lines · 70 tokens per session scan A a0cc16d415a3

Subscribe to this mod's changes

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.

Related

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…

GodModeAI2025/skill-forge · 276 tokens

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.

davila7/claude-code-templates · 39 tokens

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.

greyhaven-ai/autocontext · 67 tokens

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.

greyhaven-ai/autocontext · 57 tokens

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…

greyhaven-ai/autocontext · 60 tokens

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.

TheGreenCedar/codex-autoresearch · 55 tokens