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/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/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/flux-analyzer"><img src="https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/flux-analyzer.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 | $0.00056 | $0.00689 |
| Opus 5.5 | $0.00022 | $0.00276 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo 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 (14,755 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 689 once invoked, about $0.0002 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
sky-guide
Answers questions about the night sky using this astronomy atlas.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.