gflownet

gflownet is a skill for Codex from plurigrid/asi. It costs 36 tokens per session (1,770 once invoked), scanned A, original, MIT.

A guide to Generative Flow Networks, a machine-learning method that samples many possible solutions with probabilities based on their reward. Unlike a method that seeks only one best answer, it is designed to preserve useful diversity.

In plain words
What is it for?
Use it for diverse sampling in causal discovery, molecule design, and other search problems where each candidate has a reward.
Why use it?
It helps when several high-quality possibilities matter, such as different molecules or possible causes of an observation. This reduces the focus on finding only a single optimum.

Skill for Codex

Written for Codex: installed under .codex/.

Good fit Use it for diverse sampling in causal discovery, molecule design, and other search problems where each candidate has a reward.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/plurigrid/asi/gflownet
Install

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.

Any agent
npx skills add plurigrid/asi --skill gflownet
Clone the repo
git clone --depth 1 https://github.com/plurigrid/asi

Made for: Codex.

Wrote 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.

agentmods badge for gflownet

README.md
[![agentmods](https://agentmods.dev/badge/skills/plurigrid/asi/gflownet/github.svg)](https://agentmods.dev/skills/plurigrid/asi/gflownet)
Your own site
<a href="https://agentmods.dev/skills/plurigrid/asi/gflownet"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/gflownet/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.

agentmods 80×15 button for gflownet

Your own site · 80×15
<a href="https://agentmods.dev/skills/plurigrid/asi/gflownet"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/gflownet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,770 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.01770
Opus 5 $0.00018 $0.00885
Sonnet 5 $0.00007 $0.00354
Haiku 4.5 $0.00004 $0.00177

Measured 6d ago against content hash 3c37a104ee00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gflownet 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.

ies/music-topos/.codex/skills/gflownet/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GFlowNet Skill

"Sample x with probability proportional to R(x), not just maximize R(x)." — Yoshua Bengio

Overview

GFlowNets (Generative Flow Networks) are a new paradigm:

  • RL: Maximize expected reward → single optimal solution
  • MCMC: Sample from distribution → slow mixing
  • GFlowNet: Learn to sample P(x) ∝ R(x) → fast, diverse sampling

Core Concept

GFlowNet Objective:

∀ terminal state x:  P_θ(x) = R(x) / Z

Where:
  P_θ(x) = probability of generating x via forward policy
  R(x) = unnormalized reward function
  Z = partition function (normalizing constant)

Key Insight: We DON'T need to know Z to train!

Architecture

┌─────────────────────────────────────────────────────┐
│                    GFlowNet                         │
├─────────────────────────────────────────────────────┤
│  Initial State s₀                                   │
│        │                                            │
│        ▼                                            │
│  ┌─────────────┐                                    │
│  │ Forward     │  P_F(s' | s) = learned policy      │
│  │ Policy      │                                    │
│  └──────┬──────┘                                    │
│         │ sample action                             │
│         ▼                                            │
│  ┌─────────────┐                                    │
│  │ Transition  │  s → s'                            │
│  └──────┬──────┘                                    │
│         │                                            │
│         ▼                                            │
│  ┌─────────────┐                                    │
│  │ Terminal?   │───No──▶ continue                   │
│  └──────┬──────┘                                    │
│         │ Yes                                        │
│         ▼                                            │
│  ┌─────────────┐                                    │
│  │ R(x)        │  Evaluate reward                   │
│  └─────────────┘                                    │
└─────────────────────────────────────────────────────┘

Read the full file on GitHub · 224 lines

Changes

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.

  1. 6d ago First seen · 224 lines · 36 tokens per session scan A 3c37a104ee00

Subscribe to this mod's changes

gflownet is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 1,770 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens