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.
npx agentmods add commands/honeycombio/agent-skill/honeycomb-setupgit clone --depth 1 https://github.com/honeycombio/agent-skillWrote 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/honeycombio/agent-skill/honeycomb-setup)<a href="https://agentmods.dev/commands/honeycombio/agent-skill/honeycomb-setup"><img src="https://agentmods.dev/badge/commands/honeycombio/agent-skill/honeycomb-setup.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00884 |
| Opus 5 | $0.00009 | $0.00442 |
| Sonnet 5 | $0.00003 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
honeycomb-setup 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Honeycomb MCP Setup
Guide the user through connecting Claude Code to Honeycomb's MCP server. Use AskUserQuestion
to walk through the setup interactively.
Step 1: Prerequisites
Ask the user:
- Do they have a Honeycomb account?
- Is Honeycomb Intelligence enabled on their team? (Required for MCP)
If they're unsure about Honeycomb Intelligence, it's an add-on feature that enables AI-powered tools. They can check with their Honeycomb team admin.
Step 2: Choose Region
Use AskUserQuestion to ask: "Which Honeycomb region are you using?"
- US (default):
https://mcp.honeycomb.io/mcp - EU:
https://mcp.eu1.honeycomb.io/mcp
Step 3: Choose Authentication Method
Use AskUserQuestion to ask: "How would you like to authenticate?"
Option A: OAuth (Recommended)
Run the following command based on their region:
US:
claude mcp add honeycomb --transport http https://mcp.honeycomb.io/mcp
EU:
claude mcp add honeycomb --transport http https://mcp.eu1.honeycomb.io/mcp
After adding, the user will be prompted to authenticate in their browser on first use.
Option B: API Key (Headless/Unattended Only)
For headless environments where OAuth is not available, use AskUserQuestion to collect:
- Their API key (format:
<Key ID>:<Secret Key>) - Their region (from Step 2)
Then run the appropriate command:
US:
claude mcp add honeycomb --transport http https://mcp.honeycomb.io/mcp --header "Authorization: Bearer <KEY_ID>:<SECRET_KEY>"
EU:
claude mcp add honeycomb --transport http https://mcp.eu1.honeycomb.io/mcp --header "Authorization: Bearer <KEY_ID>:<SECRET_KEY>"
Replace <KEY_ID>:<SECRET_KEY> with the user's actual API key.
API Key requirements:
- Must be a Management API Key (not Ingest key)
- Must have "Model Context Protocol" scope (read)
- Must have "Environments" scope (read)
- For
create_board: also need "Model Context Protocol" scope (write) - Format:
<Key ID>:<Secret Key>(with colon separator)
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.
- 4d ago First seen · 105 lines · 17 tokens per session scan A fdd1f6d92a92
honeycomb-setup is a command published in the GitHub repository honeycombio/agent-skill (22 stars, last pushed 8d ago), licensed MIT. It adds 17 tokens to every session and 884 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.
Other commands, from other repositories
deploy
Build, test, deploy with staged rollout.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
cf-scaffold-project
Scaffold a Cloudflare project — Worker, Pages, or Worker+D1+R2 starter — with Wrangler config, Terraform skeleton, and GitHub Actions deploy using scoped API tokens.
scan
Scan AWS account for cost optimization.
finops-feedback
Step 5 (Feedback Loop & Celebration) — measure realized against projected savings, compute a labelled Cloud Entropy proxy, close the opportunity, and emit at least one new idea or policy update so the loop actually closes. Applies the double-loop gate. Mutates on the closure path.
run-panguweather
Guide the user through running PanguWeather end-to-end on an AMD cluster.