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.
npx skills add aiming-lab/AutoResearchClaw --skill gsmm-buildergit 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/skills/aiming-lab/autoresearchclaw/gsmm-builder)<a href="https://agentmods.dev/skills/aiming-lab/autoresearchclaw/gsmm-builder"><img src="https://agentmods.dev/badge/skills/aiming-lab/autoresearchclaw/gsmm-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/skills/aiming-lab/autoresearchclaw/gsmm-builder"><img src="https://agentmods.dev/badge/skills/aiming-lab/autoresearchclaw/gsmm-builder.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 | $0.00045 | $0.01716 |
| Opus 5.5 | $0.00018 | $0.00686 |
| Sonnet 5.5 | $0.00009 | $0.00343 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
gsmm-builder scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -O "http://bigg.ucsd.edu/static/models/iJO1366.json" How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
The gsmm-builder skill constructs or loads genome-scale metabolic models
(GSMMs) in the COBRApy framework. It is the entry point for every metabolic
flux analysis pipeline. Output is a validated COBRApy Model object
serialized to a JSON file ready for downstream FBA and flux analysis.
GSMMs encode every known metabolic reaction in an organism as a stoichiometric matrix. Constraints (reaction bounds, medium composition, objective function) turn the model into a solvable linear program.
Workflow
Step 1 — Decide: Load Existing or Build from Scratch
Option A: Load a curated BIGG model
import cobra
import cobra.io
# Load E. coli iJO1366 from a local SBML file
model = cobra.io.read_sbml_model("iJO1366.xml")
# Or load from a pre-downloaded JSON file
model = cobra.io.load_json_model("iJO1366.json")
print(f"Loaded {model.id}: {len(model.reactions)} reactions, "
f"{len(model.metabolites)} metabolites, {len(model.genes)} genes")
Key BIGG model IDs:
iJO1366— E. coli K-12 MG1655 (2583 reactions)Recon3D— Homo sapiens (13543 reactions)iMM904— S. cerevisiae (1577 reactions)iNJ661— M. tuberculosis (1049 reactions)
Option B: Build a minimal model from scratch
from cobra import Model, Metabolite, Reaction
model = Model("toy_glycolysis")
# Define metabolites with compartments and formula
glc_e = Metabolite("glc__D_e", formula="C6H12O6", name="D-Glucose",
compartment="e")
glc_c = Metabolite("glc__D_c", formula="C6H12O6", name="D-Glucose",
compartment="c")
atp_c = Metabolite("atp_c", formula="C10H12N5O13P3", name="ATP",
compartment="c")
biomass = Metabolite("biomass", formula="", name="Biomass", compartment="c")
# Build reactions
ex_glc = Reaction("EX_glc__D_e")
ex_glc.lower_bound = -10.0 # uptake (negative = import)
ex_glc.upper_bound = 0.0
ex_glc.add_metabolites({glc_e: 1.0})
transport = Reaction("GLCt")
transport.lower_bound = -1000.0
transport.upper_bound = 1000.0
transport.add_metabolites({glc_e: -1.0, glc_c: 1.0})
# Stoichiometry: 1 glucose + ADP -> 2 ATP (simplified glycolysis)
glycolysis = Reaction("GLYCOLYSIS")
glycolysis.lower_bound = 0.0
glycolysis.upper_bound = 1000.0
glycolysis.add_metabolites({glc_c: -1.0, atp_c: 2.0})
biomass_rxn = Reaction("BIOMASS")
biomass_rxn.lower_bound = 0.0
biomass_rxn.upper_bound = 1000.0
biomass_rxn.add_metabolites({atp_c: -10.0, biomass: 1.0})
model.add_reactions([ex_glc, transport, glycolysis, biomass_rxn])
What ships with it
2 files 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.
- 1mo ago First seen · 172 lines · 45 tokens per session scan A 348062aee3a9
gsmm-builder is a skill published in the GitHub repository aiming-lab/AutoResearchClaw (14,669 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,716 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
nerf-to-3dgs-migrator
Migrate NeRF-based methods to 3DGS via the SLAT unified encode-decode framework. Analyzes component compatibility, provides code templates, identifies issues. Covers encoding, deformation, appearance, geometry. Use when: migrating NeRF method to 3DGS, comparing NeRF vs 3DGS components, designing hybrid NeRF-3DGS…
arxiv-summarizer-orchestrator
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).
eval-design-forensics
Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan…
baseline-comparison-audit
Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent…
proof-derivation-forensics
Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation …
adme-property-predictor
Predict ADME (Absorption, Distribution, Metabolism, Excretion) properties for drug candidates using cheminformatics models and molecular descriptors. Evaluates drug-likeness, bioavailability, and pharmacokinetic profile to guide lead optimization and candidate selection in drug discovery.