arbor-agent-merge-eval

arbor-agent-merge-eval is a skill for Claude Code, Codex from RUC-NLPIR/Arbor. It costs 63 tokens per session (1,143 once invoked), scanned A, original, Apache-2.0.

A set of Arbor rules for evaluating experiments and deciding whether code changes should be merged. It distinguishes development data from test data and records scores, commands, dataset details, and merge metadata.

In plain words
What is it for?
Use it to track baseline and current scores, run milestone checks, parse evaluation results, protect files, verify required outputs, and perform final validation.
Why use it?
It reduces misleading conclusions caused by overfitting, inconsistent data splits, contaminated evaluations, or undocumented merge decisions.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the arbor plugin — 11 skills shipped together

Good fit Use it to track baseline and current scores, run milestone checks, parse evaluation results, protect files, verify required outputs, and perform final validation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ruc-nlpir/arbor/arbor-agent-merge-eval
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 · 1,060 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-merge-eval
Clone the repo
git clone --depth 1 https://github.com/RUC-NLPIR/Arbor

Made for: Claude Code, 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-merge-eval

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-merge-eval/github.svg)](https://agentmods.dev/skills/ruc-nlpir/arbor/arbor-agent-merge-eval)
Your own site
<a href="https://agentmods.dev/skills/ruc-nlpir/arbor/arbor-agent-merge-eval"><img src="https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-merge-eval/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.

agentmods 80×15 button for arbor-agent-merge-eval

Your own site · 80×15
<a href="https://agentmods.dev/skills/ruc-nlpir/arbor/arbor-agent-merge-eval"><img src="https://agentmods.dev/badge/skills/ruc-nlpir/arbor/arbor-agent-merge-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,143 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 pass 7 Sept 2026
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 $0.00063 $0.01143
Opus 5 $0.00032 $0.00571
Sonnet 5 $0.00013 $0.00229
Haiku 4.5 $0.00006 $0.00114

Measured 11d ago against content hash d0ba4902fd6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

arbor-agent-merge-eval 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.

skills/arbor-agent-merge-eval/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arbor Merge And Eval

Use this whenever scores, metadata, merge decisions, or final validation are involved.

Dataset Discipline

  • B_dev is for routine iteration, executor experiments, score tracking, and idea selection.
  • B_test is for milestone checks only: before merging a branch and at final report time.
  • If B_test diverges from B_dev, do not hand-wave it. Investigate overfitting, noise, data split mismatch, or eval contamination.

Tree Metadata

Persist evaluation metadata early and update it after merges:

  • baseline_score: unmodified B_dev score.
  • trunk_score: current trunk B_dev score.
  • test_baseline_score: unmodified B_test score.
  • test_trunk_score: current trunk B_test score.
  • eval_cmd: B_dev command.
  • eval_cmd_test: B_test command.
  • eval_timeout, eval_retries, eval_retry_base_delay, eval_retry_max_delay.
  • dataset_info: paths and split descriptions.
  • metric_direction: maximize or minimize.
  • trunk_branch: non-protected branch that receives verified merges.
  • submission_path, sample_submission_path.

Use {cwd} and {node_id} placeholders. Example:

cd {cwd} && uv run python run_eval.py --split dev --run-name {node_id}

Score Semantics

  • Tree node score is an absolute B_dev metric value.
  • Merge verification uses B_test.
  • metric_direction controls improvement:
    • maximize: higher is better.
    • minimize: lower is better.
  • Do not compare deltas with absolutes.
  • If output has JSON with score, prefer it. Otherwise extract the primary metric from text (primary_score, score, accuracy, acc, etc.).

Merge Procedure

Native GitMergeBranch:

  1. Refuses target main or master.
  2. Resolves target to configured trunk_branch. main/master are base branches, not merge targets.
  3. Creates an isolated worktree at source_branch.
  4. Runs eval_cmd_test with {cwd} and {node_id} substituted.
  5. Retries transient failures if configured.
  6. Extracts verified B_test score.
  7. Rejects the merge if B_test does not improve over test_trunk_score or test_baseline_score.
  8. Checks plugin protected paths and required outputs.
  9. Merges source into trunk with --no-ff.
  10. Reports the verified test score and instructs the coordinator to update tree metadata and node status.

Read the full file on GitHub · 129 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. 11d ago First seen · 129 lines · 63 tokens per session scan A d0ba4902fd6f

Subscribe to this mod's changes

arbor-agent-merge-eval is a skill published in the GitHub repository RUC-NLPIR/Arbor (1,060 stars, last pushed 2d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,143 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

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

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

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

skill-release-gate

Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.

rohitg00/ai-engineering-from-scratch · 36 tokens

workflow-patterns

Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.

wshobson/agents · 35 tokens