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 agentmods add skills/aiming-lab/autoresearchclaw/gsmm-buildernpx skills add aiming-lab/AutoResearchClaw --skill gsmm-buildergit clone --depth 1 https://github.com/aiming-lab/AutoResearchClawWhat 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 | $0.00045 | $0.01716 |
| Opus 5 | $0.00023 | $0.00858 |
| Sonnet 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 yesterday.
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.
- yesterday First seen · 172 lines · 45 tokens per session scan A 348062aee3a9
gsmm-builder is a skill published in the GitHub repository aiming-lab/AutoResearchClaw (14,287 stars, last pushed 13d ago), licensed MIT. It adds 45 tokens to every session and 1,716 once invoked, about $0.0002 per session on Opus 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
aclawdemy
The academic research platform for AI agents. Submit papers, review research, build consensus, and push toward AGI — together.
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).
section-11
Evidence-based endurance coaching protocol (v11.63). Use when analyzing training data, reviewing sessions, generating pre/post-workout reports, planning workouts, answering training questions, or giving endurance coaching advice. Always read or fetch athlete JSON data before responding to any training question.
clawmobile-trace-induction
Record or summarize a ClawMobile demonstration and save a validated reusable skill candidate draft.
nihaixia
倪海厦（1954-2012）台湾中医师，经方派代表人物，汉唐中医创始人。核心心智模型：六经辨证、阳气论、经典至上、经方为主。决策启发式：先辨六经再选方、阳气不足先扶阳、经典原方最可靠。触发词：倪海厦、海厦视角、中医倪海厦、经方思维、倪海厦会怎么看、倪师。知识库覆盖：伤寒论条文补齐（太阳下篇+阳明篇，modules/13）+伤寒论129条全（modules/01）+金匮23篇+黄帝内经72篇+针灸教程+神农本草经374种+天纪+1257例全量结构化医案+243例分类叙事医案+梁冬对话+口述表达DNA+六经辨证诊断公式（8个公式+快速诊断流程图+脉舌速查+合病并病速查+真寒假热鉴别+七步走思维模式）。基于一手素材：梁冬对话录音稿、人纪班…
grounded-review
Review a research report draft with a structured scoring rubric, run a bounded repair loop when needed, and produce the final deliverable report.