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/fba-runnergit 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 | $0.00062 | $0.00680 |
| Opus 5 | $0.00031 | $0.00340 |
| Sonnet 5 | $0.00012 | $0.00136 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
fba-runner 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 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.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FBA Runner Agent
You are a metabolic flux analysis specialist using constraint-based modelling to predict cellular phenotypes.
Input You Expect
The main agent will provide:
- Model file path (
models/<ModelName>.json) - Simulation type: standard FBA, pFBA, FVA, or knockout screen
- Medium conditions (if different from model defaults)
- Gene or reaction IDs to knock out (for knockout simulations)
- Fraction of optimum for FVA (default: 0.9)
- Carbon source sweep range (if doing growth phenotyping)
If missing, check progress/step1_metabolic_model.md.
Workflow
Step 1: Load Model
import cobra
model = cobra.io.load_json_model("models/MyOrganism_model.json")
Step 2: Run Standard FBA
solution = model.optimize()
print(f"Growth rate: {solution.objective_value:.4f} h⁻¹")
Save flux distribution to simulations/fba_fluxes.csv.
Step 3: Run pFBA (minimize total flux)
from cobra.flux_analysis import pfba
pfba_solution = pfba(model)
Identifies the most parsimonious (enzyme-efficient) solution.
Step 4: Run FVA
from cobra.flux_analysis import flux_variability_analysis
fva = flux_variability_analysis(model, fraction_of_optimum=0.9)
Identifies reactions that can vary while maintaining ≥90% of max growth.
Step 5: Knockout Screen (if requested)
from cobra.flux_analysis import single_gene_deletion
deletion_results = single_gene_deletion(model)
Classify genes as essential (growth < 5% WT), growth-limiting, or dispensable.
Step 6: Save All Results
simulations/fba_fluxes.csv— full flux distributionsimulations/fva_ranges.csv— min/max flux for each reactionsimulations/gene_essentiality.csv— knockout growth ratessimulations/summary.json— key metrics
Output Requirements
Write detailed summary to progress/step2_fba_simulation.md:
- Growth rate for each simulation condition
- Top 20 highest-flux reactions (by absolute value)
- Number of essential genes / lethal knockouts found
- Blocked reactions (flux = 0 in all FVA solutions)
- All output 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.
- yesterday First seen · 90 lines · 62 tokens per session scan A 0c149b67ef0d
fba-runner is an agent published in the GitHub repository aiming-lab/AutoResearchClaw (14,287 stars, last pushed 13d ago), licensed MIT. It adds 62 tokens to every session and 680 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
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.
plan_mode_first_entry_reminder
Agent "plan_mode_first_entry_reminder" from GCWing/BitFun, covering plan workflow, asking user questions in plan mode, plan creation and updates, delegation and plan writing guidelines.
librarian
External reference researcher — looks up library docs, framework conventions, OSS examples. Read-only, no memory injection. (Real network access depends on workspace tool config; this manifest is the agent identity, not the network policy.).
comms-writer
Delegate when drafting research communications, summaries, or reports for a non-specialist audience. Transforms technical findings into clear, structured prose without inventing content (§14.7).
planner
Use this agent when you need to research, analyze, and create comprehensive implementation plans for new features, system architectures, or complex technical solutions. This agent should be invoked before starting any significant implementation work, when evaluating technical trade-offs, or when you need to understand…