experiment-iteration-loop

experiment-iteration-loop is a skill for Claude Code, Codex from BingHanOfUESTC/open_agent_team. It costs 27 tokens per session (416 once invoked), scanned A, original, MIT.

A structured method for designing, running, recording, diagnosing, and repeating experiments for a research idea.

In plain words
What is it for?
It is for maintaining an experiment queue, running smoke, baseline, main, ablation, robustness, or failure-diagnosis runs, storing logs, and updating a results table.
Why use it?
It ensures experiments start with basic environment and baseline checks, and that commands, settings, results, hardware, and failures remain traceable.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/binghanofuestc/open_agent_team/experiment-iteration-loop
Any agent
npx skills add BingHanOfUESTC/open_agent_team --skill experiment-iteration-loop
Clone the repo
git clone --depth 1 https://github.com/BingHanOfUESTC/open_agent_team

Made for: Claude Code, Codex.

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 experiment-iteration-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/binghanofuestc/open_agent_team/experiment-iteration-loop.svg)](https://agentmods.dev/skills/binghanofuestc/open_agent_team/experiment-iteration-loop)
Your own site
<a href="https://agentmods.dev/skills/binghanofuestc/open_agent_team/experiment-iteration-loop"><img src="https://agentmods.dev/badge/skills/binghanofuestc/open_agent_team/experiment-iteration-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 416 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.00416
Opus 5 $0.00014 $0.00208
Sonnet 5 $0.00005 $0.00083
Haiku 4.5 $0.00003 $0.00042

Measured 5d ago against content hash 49207957c617, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

experiment-iteration-loop 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 5d 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.

teams/auto_research_team/skills/experiment-iteration-loop/SKILL.md · 131 lines

What it actually says

Experiment Iteration Loop

This skill ensures experiments are decisive, logged, and honest about failures.


1. Experiment Queue

Maintain:

research_workspace/experiments/experiment_queue.md

Use this structure:

## EXP-<N>: <name>

- Purpose:
- Hypothesis:
- Baseline or variant:
- Config:
- Command:
- Expected duration:
- Hardware:
- Success criterion:
- Failure criterion:
- Status:

2. Required Experiment Types

Default order:

SMOKE: environment and data sanity
BASE: baseline reproduction or minimum baseline
MAIN: proposed method
ABL: ablation that isolates the change
ROB: robustness/sensitivity if resources allow
FAIL: diagnosis for unexpected failure

Do not run expensive variants before baseline and smoke tests.


3. Logging

For every run, save:

config
command
stdout/stderr
metric output
random seed
hardware
start/end time
git diff or file state
notes

Write summary to:

research_workspace/09_experiment_log.md

Store raw logs under:

research_workspace/experiments/logs/

4. Result Table

Maintain:

research_workspace/experiments/results.csv

Minimum columns:

experiment_id
method
dataset
split
seed
metric
value
runtime
hardware
log_path
notes

Figures and LaTeX tables must be generated from this file or a documented equivalent.


5. Iteration Decision

After each batch of experiments, decide:

continue
debug
ablate
pivot
downgrade
stop_success
stop_negative_result
blocked

Record the decision and evidence in decision_register.md.

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. 5d ago First seen · 131 lines · 27 tokens per session scan A 49207957c617

Subscribe to this mod's changes

experiment-iteration-loop is a skill published in the GitHub repository BingHanOfUESTC/open_agent_team (109 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 416 once invoked, about $0.0001 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

imaging-data-commons

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

synthetic-sciences/openscience · 62 tokens

flow-cytometry-analysis

Complete flow cytometry analysis pipeline. FCS file handling, compensation, manual/automated gating, immunophenotyping, CFSE proliferation analysis, cell cycle analysis (Dean-Jett-Fox), and apoptosis assays. Extends flowio with analytical workflows. For raw FCS parsing only use flowio.

synthetic-sciences/openscience · 67 tokens

scientific-critical-thinking

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…

xintaofei/codeg · 63 tokens

cellxgene-census

Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.

synthetic-sciences/openscience · 67 tokens

rowan

Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve…

synthetic-sciences/openscience · 115 tokens

pathml

Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be…

synthetic-sciences/openscience · 69 tokens