onboard

A command that converts an existing Markdown math paper into a validated document with Python checks for its equations. It reviews the paper section by section and asks for approval of each check.

In plain words
What is it for?
Use it to locate a math paper, inspect its sections and equations, and create validation blocks interactively.
Why use it?
It helps find and confirm mathematical or validation problems before you treat the paper as complete. It also prevents accidentally processing a document that is already validated or contains no display equations.

Command

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.

agentmods
npx agentmods add commands/reggiechan74/cc-plugins/onboard
Clone the repo
git clone --depth 1 https://github.com/reggiechan74/cc-plugins
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,274 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00016 $0.02274
Opus 5 $0.00008 $0.01137
Sonnet 5 $0.00003 $0.00455
Haiku 4.5 $0.00002 $0.00227

Measured 2d ago against content hash 5e1fe1a5c8f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onboard 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 2d 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.

math-paper-creator/commands/onboard.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Onboard a Math Paper

Convert an existing markdown math paper into a fully validated .model.md document with working python:validate blocks. This is an interactive, section-by-section process — you will approve each validation block before moving on.

Step 1: Locate the file

Use the provided path argument. If no path is given, search with Glob for **/*.md (excluding *.model.md files). If multiple results are found:

  • Show at most 20 matches and ask the user which one to onboard.
  • If more than 20 matches exist, ask the user to provide a path directly.

Step 2: Guard rails

Before proceeding, check two conditions:

  1. Already a .model.md file? If the file ends in .model.md, tell the user: "This file is already a .model.md document. Use /math-paper-creator:check to validate it or /math-paper-creator:status to see its current state." Stop here.

  2. No math blocks? Read the file and check for $$...$$ display math blocks. If none are found, tell the user: "No display math blocks ($$...$$) were found in this file. There is nothing to onboard." Stop here.

Step 3: Read and analyze

Read the entire document. Identify:

  • All sections (by heading level: #, ##, ###, etc.)
  • All $$...$$ display math blocks and which section each belongs to
  • The mathematical model being described: sets, parameters, variables, expressions, constraints, objectives

Build a mental model of the paper's structure and mathematical content.

Step 4: Present overview

Show the user a summary:

  • Number of sections containing math blocks
  • Total number of display math blocks
  • A high-level interpretation of the model, e.g.: "This paper describes a linear program for workforce scheduling with 3 sets, 5 parameters, 2 variables, and 4 constraints."

Ask the user to confirm or correct this interpretation. The user may respond with free-form corrections. If they do, re-interpret and re-present until the user confirms.

Do not proceed until the user explicitly confirms.

Read the full file on GitHub · 191 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. 2d ago First seen · 191 lines · 16 tokens per session scan A 5e1fe1a5c8f3

Subscribe to this mod's changes

onboard is a command published in the GitHub repository reggiechan74/cc-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 2,274 once invoked, about $0.0001 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 2026-08-31.