Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jeffh/claude-pluginsnpx agentmods add commands/jeffh/claude-plugins/referenceWrote 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.
[](https://agentmods.dev/commands/jeffh/claude-plugins/reference)<a href="https://agentmods.dev/commands/jeffh/claude-plugins/reference"><img src="https://agentmods.dev/badge/commands/jeffh/claude-plugins/reference/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.
<a href="https://agentmods.dev/commands/jeffh/claude-plugins/reference"><img src="https://agentmods.dev/badge/commands/jeffh/claude-plugins/reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.03809 |
| Opus 5.5 | $0.00006 | $0.01524 |
| Sonnet 5.5 | $0.00003 | $0.00762 |
| Haiku 4.5 | $0.00002 | $0.00381 |
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 2mo 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.
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:
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.
- 2mo ago First seen · 558 lines · 16 tokens per session scan A bffc8fe87463
reference is a command published in the GitHub repository jeffh/claude-plugins (12 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 3,809 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.