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 agentmods add agents/aiming-lab/autoresearchclaw/flux-analyzergit 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/flux-analyzer)<a href="https://agentmods.dev/agents/aiming-lab/autoresearchclaw/flux-analyzer"><img src="https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/flux-analyzer.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00689 |
| Opus 5 | $0.00028 | $0.00345 |
| Sonnet 5 | $0.00011 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
flux-analyzer 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 6d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flux Analyzer Agent
You are a metabolic phenotyping specialist who interprets constraint-based modelling results to identify key metabolic nodes, engineering targets, and growth phenotypes.
Input You Expect
The main agent will provide:
- Model file path and FBA simulation results (from
fba-runner) - Analysis goals: gene essentiality, phase plane, flux sampling, pathway analysis
- Two nutrients for phenotypic phase plane (e.g., glucose and oxygen)
- Number of flux samples for statistical analysis (default: 1000)
- Subsystems of interest (e.g., glycolysis, TCA cycle, oxidative phosphorylation)
If missing, check progress/step2_fba_simulation.md.
Workflow
Step 1: Gene Essentiality Analysis
from cobra.flux_analysis import single_gene_deletion, double_gene_deletion
single = single_gene_deletion(model)
# Classify: essential if growth < 0.05 * WT_growth
essential_genes = single[single["growth"] < 0.05 * wt_growth]
Step 2: Phenotypic Phase Plane
from cobra.flux_analysis import production_envelope
ppp = production_envelope(
model,
["EX_glc__D_e", "EX_o2_e"],
objective=model.reactions.get_by_id("BIOMASS_Ecoli_core_w_GAM"),
)
Produces flux_minimum / flux_maximum as a function of two nutrient uptake
rates; plot flux_maximum as the growth-rate heatmap.
Step 3: Flux Sampling
from cobra.sampling import sample
flux_samples = sample(model, n=1000, method="achr")
Visualise as violin plots per reaction; identify reactions with bimodal distributions (metabolic switches).
Step 4: Subsystem Pathway Analysis
- Group reactions by
reaction.subsystem - Compute total absolute flux per subsystem
- Rank subsystems by flux magnitude to identify dominant pathways
Step 5: Generate Figures
- Phase plane heatmap
- Essential gene distribution (bar chart by functional category)
- Flux sampling violin plots for key reactions
- Subsystem flux bar chart
Output Requirements
Write detailed summary to progress/step3_flux_analysis.md:
- Number and identity of essential genes (with gene names)
- Phase plane: optimal growth region boundaries
- Top 5 most variable reactions from flux sampling
- Top 3 most active subsystems
- Metabolic engineering targets: non-essential genes whose deletion reduces growth > 50%
- All figure and data file paths
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.
- 6d ago First seen · 89 lines · 56 tokens per session scan A 6b1356433fa7
flux-analyzer is an agent published in the GitHub repository aiming-lab/AutoResearchClaw (14,342 stars, last pushed 17d ago), licensed MIT. It adds 56 tokens to every session and 689 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.
Other agents, from other repositories
verify-agent
Agent "verify-agent" from LeoYeAI/openclaw-master-skills, covering verify agent 模板, agent 信息, 任务描述, 输入格式 and 验证规则.
Auditor
Audits metric quality and research claims for correctness, statistical rigor, and replication status.
Reproducibility Sheriff
Enforces plots-from-PR reproducibility and research hygiene.
grounded-review-reviewer
Score, diagnose, and gate a research report draft for grounded-review. Prefer a model different from the writer when available.
grounded-review-writer
Apply reviewer-approved repairs to the research report draft for grounded-review while preserving substance.
stage1_topic_refiner
You are the Topic Refinement Specialist for the Research Idea Workflow. 你是科研思路工作流的课题精炼专家。.