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 instructions/plexe-ai/plexe/agents-mdgit clone --depth 1 https://github.com/plexe-ai/plexeWhat 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 | $0.01431 | $0.01431 |
| Opus 5 | $0.00715 | $0.00715 |
| Sonnet 5 | $0.00286 | $0.00286 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
plexe AGENTS.md 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents when working with code in this repository (for example, OpenAI Codex and Claude Code).
AGENTS.md is the canonical version of this document. CLAUDE.md is kept as a compatibility symlink that points here, so if you opened this file via CLAUDE.md, you are in the right place.
Overview
Plexe is an agentic framework for building ML models from natural language. It employs a multi-agent architecture where specialized AI agents collaborate to analyze data, generate solutions, and build functional ML models through an autonomous 6-phase workflow.
Entry point: python -m plexe.main --train-dataset-uri <uri> --user-id <id> --intent "<task>" --spark-mode <local|databricks>
Docker:
docker build .— default PySpark image (local Spark execution)docker build --target databricks .— Databricks Connect image (remote execution)
Architecture
6-Phase Workflow (plexe/workflow.py)
- Data Understanding: Statistical analysis → ML task identification → metric selection (with optional custom metric generation)
- Data Preparation: Dataset splitting → intelligent sampling (default: 30k train, 10k val samples)
- Baseline Models: Heuristic baseline with retry logic
- Model Search: Hypothesis-driven tree search on samples (iterative improvement)
- Final Evaluation: Optional test evaluation (default: disabled, uses validation performance)
- Packaging: Consolidates artifacts into
work_dir/model/(schemas/, config/, artifacts/, src/, evaluation/)
Multi-Agent System (plexe/agents/)
14 specialized agents orchestrate the workflow:
- LayoutDetectionAgent → StatisticalAnalyserAgent → MLTaskAnalyserAgent → MetricSelectorAgent (Phase 1)
- MetricImplementationAgent: Generates custom metric code if not in
StandardMetricenum - DatasetSplitterAgent → SamplingAgent (Phase 2)
- BaselineBuilderAgent (Phase 3)
- HypothesiserAgent → PlannerAgent → FeatureProcessorAgent + ModelDefinerAgent (Phase 4 loop)
- InsightExtractorAgent: Analyzes variant results, populates
InsightStorefor future hypotheses - ModelEvaluatorAgent: Multi-phase evaluation (Phase 5)
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 · 123 lines · 1,431 tokens per session scan A fda2fe87dd86
plexe AGENTS.md is an instructions file published in the GitHub repository plexe-ai/plexe (2,614 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,431 tokens to every session, about $0.0072 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 instructions, from other repositories
autocontext CLAUDE.md
Instructions for greyhaven-ai/autocontext, covering claude.md, project overview, repository layout, commands and setup.
relay AGENTS.md
Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
cookiecutter-mlops-package AGENTS.md
Instructions for fmind/cookiecutter-mlops-package, covering agents.md, project overview, setup & core commands, definition of done and conventions & idioms.
valuecell AGENTS.md
Instructions for ValueCell-ai/valuecell, covering guidelines, python programming, python environment, imports and runtime checks.
neosh AGENTS.md
Instructions for neoswarm/neosh, covering working on neosh, layout, rules that are not negotiable, verification and the command line.