paiml-mcp-agent-toolkit: Instructions file for Claude Code

CLAUDE.md

paiml-mcp-agent-toolkit CLAUDE.md is an instructions file for Claude Code from paiml/paiml-mcp-agent-toolkit. It costs 6,373 tokens per session, scanned A, original, MIT.

Development guidance for PMAT, a Rust toolkit built around the Batuta collection of AI, data, graph, storage, and computing tools. It sets a rule to check those existing tools before adding outside dependencies.

In plain words
What is it for?
Use it when adding functionality involving mathematics, algorithms, data science, machine learning, graphs, databases, compression, or computation, and when deciding which Rust crate to use.
Why use it?
It helps keep the project’s dependency choices consistent and prevents adding an external library when the project’s own toolkit already covers the need.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument; mentions Claude Code.

This is paiml/paiml-mcp-agent-toolkit's own configuration. It tells Claude Code how to work on paiml-mcp-agent-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything paiml-mcp-agent-toolkit configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/noah/src/pmat-book.

Reuse

Borrowing it

Nothing to install: this file belongs to paiml/paiml-mcp-agent-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/paiml/paiml-mcp-agent-toolkit/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/paiml/paiml-mcp-agent-toolkit

Made for: Claude Code.

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 paiml-mcp-agent-toolkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/paiml/paiml-mcp-agent-toolkit/claude-md.svg)](https://agentmods.dev/instructions/paiml/paiml-mcp-agent-toolkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/paiml/paiml-mcp-agent-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/paiml/paiml-mcp-agent-toolkit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,373 This file is loaded in full into every session.
When invoked 6,373 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.06373 $0.06373
Opus 5 $0.03187 $0.03187
Sonnet 5 $0.01275 $0.01275
Haiku 4.5 $0.00637 $0.00637

Measured 4d ago against content hash 1669f2606678, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

paiml-mcp-agent-toolkit CLAUDE.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 4d 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.

CLAUDE.md · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Configuration

CRITICAL: Sovereign AI Dependency Policy (80/20 Batuta Stack)

MANDATORY: Minimize external dependencies - use batuta stack first

PMAT follows the Sovereign AI philosophy: 80% batuta stack, 20% external deps maximum.

Before adding ANY external dependency for math, algorithms, data science, ML, or compute:

  1. CHECK BATUTA STACK FIRST - See if sovereign tools already provide the functionality
  2. BUILD IF CLOSE - If batuta stack is 70%+ there, extend it rather than adding external dep
  3. EXTERNAL ONLY AS LAST RESORT - Document why batuta stack couldn't work

Batuta Stack (Sovereign AI Tools)

Crate Purpose Use Instead Of
aprender ML, stats, graph algorithms, text similarity nalgebra, linfa, smartcore
trueno SIMD/GPU compute, matrix ops ndarray, nalgebra
trueno-graph Graph database, PageRank, Louvain petgraph, graph
trueno-db Columnar storage, analytics polars, datafusion
trueno-rag RAG pipeline, vector search qdrant, milvus
trueno-viz Terminal visualization plotters, textplots
trueno-zram-core SIMD compression lz4, zstd
renacer Golden tracing, chaos testing proptest chaos
certeza Quality validation custom scripts
bashrs Bash/Makefile linting shellcheck
probar Property-based testing quickcheck
pmcp MCP protocol SDK custom MCP
presentar-core TUI framework ratatui

Dependencies Requiring Review

External Dep Status Batuta Alternative
roaring Keep Specialized bitmap (no batuta equivalent yet)
rand Keep Foundational (may add to trueno later)
rayon Keep Foundational parallel iterator

(nalgebra-sparse was removed — see the note at Cargo.toml:251. Do not re-add it.)

Before adding ANY new dependency: check batuta stack first (pmat query "YourFeature" --limit 5 in aprender), build if close, document if external required.

Read the full file on GitHub · 482 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. 4d ago Changed · +15 tokens per session 1669f2606678
  2. 9d ago First seen · 482 lines · 6,358 tokens per session scan A 4978726a3b24

Subscribe to this mod's changes

paiml-mcp-agent-toolkit CLAUDE.md is an instructions file published in the GitHub repository paiml/paiml-mcp-agent-toolkit (164 stars, last pushed today), licensed MIT. It adds 6,373 tokens to every session, about $0.0319 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.

Related

Other instructions, from other repositories

runtm copilot-instructions.md

Copilot instructions for runtm-ai/runtm, covering runtm tool instructions, critical rules, structure, adding endpoints and app/api/v1/myendpoint.py.

runtm-ai/runtm · 297 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens