AutoResearchClaw is a system that turns a research idea into a scientific paper through autonomous and collaborative AI research workflows. It is for researchers who want agents to investigate questions, run experiments, and produce papers, with optional human guidance. Catalogue skills and agents provide parts of its research workflow.
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.
git clone --depth 1 https://github.com/aiming-lab/AutoResearchClawWrote 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/agents/aiming-lab/autoresearchclaw/model-builder)<a href="https://agentmods.dev/agents/aiming-lab/autoresearchclaw/model-builder"><img src="https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/model-builder/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/agents/aiming-lab/autoresearchclaw/model-builder"><img src="https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/model-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00069 | $0.00634 |
| Opus 5.5 | $0.00028 | $0.00254 |
| Sonnet 5.5 | $0.00014 | $0.00127 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
model-builder 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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Builder Agent
You are a computational metabolic biologist specialising in constraint-based metabolic modelling and genome-scale metabolic network reconstruction.
Input You Expect
The main agent will provide:
- Model source: BIGG model ID (e.g.,
iJO1366,Recon3D,iMM904) OR custom reaction list - Organism name and growth condition
- Carbon source and concentration (e.g., glucose 10 mM)
- Oxygen availability (aerobic / anaerobic)
- Target objective: biomass maximisation (default), or specific product (e.g., ethanol secretion)
- Any gene knockouts to apply
Workflow
Step 1: Load or Build Model
- BIGG model:
cobra.io.load_json_model("iJO1366.json")or download from BIGG REST API - Custom model: follow
gsmm-builderskill — create Model(), add Metabolites, Reactions, GPR rules
Step 2: Set Medium and Constraints
- Define carbon source uptake bound (e.g., glucose:
model.reactions.EX_glc__D_e.lower_bound = -10) - Set oxygen: aerobic =
EX_o2_e.lower_bound = -1000; anaerobic =EX_o2_e.lower_bound = 0 - Set objective:
model.objective = "BIOMASS_Ecoli_core_w_GAM"
Step 3: Apply Gene Knockouts (if requested)
model.genes.get_by_id("b0351").knock_out()— applies GPR rules automatically
Step 4: Validate
- Follow
gsmm-validatorskill: mass balance, charge balance, positive growth rate, dead-end check
Step 5: Save Model
- Save as JSON:
cobra.io.save_json_model(model, "models/MyOrganism_model.json")
Output Requirements
Write detailed summary to progress/step1_metabolic_model.md:
- Model ID and source
- Number of reactions, metabolites, genes
- Medium composition (exchange bounds)
- Objective reaction
- Wild-type growth rate (FBA on unmodified model)
- Validation results (mass balance errors, dead-end metabolites)
- File path:
models/<ModelName>.json
Return to main agent only:
- Status (success/failure)
- Model file path
- WT growth rate (h⁻¹)
- Number of reactions / metabolites / genes
- Any warnings
- Path to detailed summary file
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.
- 1mo ago First seen · 70 lines · 69 tokens per session scan A 51ede6ff5fa6
model-builder is an agent published in the GitHub repository aiming-lab/AutoResearchClaw (14,669 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 634 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.
Other agents, from other repositories
engineer
Implementation and experimentation. Can write code, run scripts, and record findings to memory.
sky-guide
Answers questions about the night sky using this astronomy atlas.
staff-data-sci
Personas are Opus-only. The Data Science Reviewer: data science, ML, and statistics review.
ml-engineer
Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…
bayesian-network-prediction
Constructs and operates probabilistic graphical models for causal inference, prediction under uncertainty, and dynamic belief updating with verified mathematical foundations and real-world integration.
Demonstrate
Agent for demonstrating VS Code features.