reference

An interactive command for creating or updating reference documentation about a tool, product, library, or API. It gathers requirements, researches sources, optionally checks code integration, and keeps every documented claim tied to a citation.

In plain words
What is it for?
Use it to create or expand well-sourced reference documents. It can collect requirements, use official or other provided sources, inspect a codebase when relevant, and answer follow-up questions.
Why use it?
It prevents reference material from containing unsupported claims that cannot be checked later. The citation requirement also makes future updates easier to verify.

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/jeffh/claude-plugins/reference
Clone the repo
git clone --depth 1 https://github.com/jeffh/claude-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 3,809 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 $0.03809
Opus 5 $0.00008 $0.01904
Sonnet 5 $0.00003 $0.00762
Haiku 4.5 $0.00002 $0.00381

Measured yesterday against content hash bffc8fe87463, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reference 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.

discuss/commands/reference.md · 558 lines

How it starts

The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reference Documentation Command

You are tasked with creating comprehensive, well-cited reference documentation for tools, products, or libraries. This is an interactive process: you gather requirements, research sources, optionally analyze codebase integration, write the documentation, and support ongoing Q&A to expand the reference.

CRITICAL: Source Citation is Non-Negotiable

Every piece of information in the reference document MUST be traceable to a cited source. This enables /update-reference to verify and refresh the documentation later. If you cannot cite a source for information, do not include it.


Step 1: Gather Requirements

When this command is invoked, immediately use AskUserQuestion to collect essential information. Ask all questions in a single interaction:

I'll help you create reference documentation. Let me gather some information first.

1. **What do you want reference documentation for?**
   - Name of the tool, product, library, or API
   - Brief description if it's not well-known

2. **Do you have URLs to reference materials?**
   - Official documentation
   - GitHub repository
   - Tutorials or guides
   - API references
   (Provide as many as you have; I can search for more)

3. **Where should I save the reference document?**
   - Example: `./docs/[name]-reference.md`
   - Example: `./references/[name].md`
   - Or specify your preferred location

4. **Is this reference contextual to your current project?**
   - Yes: I'll analyze how to use it within this codebase
   - No: I'll create general-purpose reference documentation

If parameters were provided with the command (e.g., /reference zod https://zod.dev):

  • Acknowledge the provided information
  • Ask only the remaining questions (output location, project context)

Wait for the user's response before proceeding to Step 2.


Step 2: Fetch and Analyze Source Materials

2a. Fetch Provided URLs

Use WebFetch to retrieve content from each URL the user provided:

Read the full file on GitHub · 558 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. yesterday First seen · 558 lines · 16 tokens per session scan A bffc8fe87463

Subscribe to this mod's changes

reference is a command published in the GitHub repository jeffh/claude-plugins (12 stars, last pushed 17d ago), licensed Apache-2.0. It adds 16 tokens to every session and 3,809 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 2026-08-30.