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.
git clone --depth 1 https://github.com/jeffh/claude-pluginsWrote 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/update_reference)<a href="https://agentmods.dev/commands/jeffh/claude-plugins/update_reference"><img src="https://agentmods.dev/badge/commands/jeffh/claude-plugins/update_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/update_reference"><img src="https://agentmods.dev/badge/commands/jeffh/claude-plugins/update_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 | $0.00010 | $0.03685 |
| Opus 5.5 | $0.00004 | $0.01474 |
| Sonnet 5.5 | $0.00002 | $0.00737 |
| Haiku 4.5 | $0.00001 | $0.00368 |
Grade A, and why
update_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 — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Reference Document
You are tasked with updating an existing reference document by checking its cited sources for changes. You will identify what has changed, update the document accordingly, and provide a clear summary highlighting any breaking changes.
CRITICAL: YOUR PRIORITIES
- Breaking changes are the highest priority - Always identify and prominently call out breaking changes
- Preserve document intent - Update content without restructuring the document
- Source integrity - Maintain accurate source citations with current retrieval dates
- Conservative updates - Only update based on verifiable source changes
Initial Response
When this command is invoked:
If a file path was provided (e.g., /update-reference docs/zod-reference.md):
- Immediately proceed to Step 1
- Do not ask for confirmation
If no file path was provided, respond with:
I'll help you update a reference document by checking its sources for changes.
Please provide the path to the reference document you want to update.
Example: `/update-reference ./docs/my-library-reference.md`
Then wait for the user to provide the file path.
Steps to Follow
Step 1: Read and Parse the Document
-
Read the reference document FULLY using the Read tool
- IMPORTANT: Use the Read tool WITHOUT limit/offset parameters to read the entire file
- This ensures you have complete context before analyzing
-
Extract the Sources section:
- Look for a "## Sources", "## References", or similar section
- Parse all URLs listed (official docs, GitHub repos, blog posts, etc.)
- Note retrieval dates if present
-
If no Sources section found, respond with:
I couldn't find a Sources section in this document. The /update-reference command requires a Sources section with URLs to check for updates. Would you like me to: 1. Help you add a Sources section to this document 2. Search for relevant sources based on the document contentThen wait for the user's response.
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 · 496 lines · 10 tokens per session scan A 1d08985180e8
update_reference is a command published in the GitHub repository jeffh/claude-plugins (12 stars, last pushed today), licensed Apache-2.0. It adds 10 tokens to every session and 3,685 once invoked, about $0.0000 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
brand-generate
Generate an on-brand document from a saved Brand Profile.
cti-report
Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].
render-figures
Compile all .tex and .typ figure files in a directory.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
publish-api-docs
Generate interactive API documentation from blueprint specs (Swagger UI, Redoc, AsyncAPI).
write-patent
An automated workflow for creating a complete Chinese patent application from a technical disclosure document, including written sections, patent drawings, and a Word file.