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 skills/cyanheads/reference-data-mcp-server/design-mcp-servernpx skills add cyanheads/reference-data-mcp-server --skill design-mcp-servergit clone --depth 1 https://github.com/cyanheads/reference-data-mcp-serverWrote 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/skills/cyanheads/reference-data-mcp-server/design-mcp-server)<a href="https://agentmods.dev/skills/cyanheads/reference-data-mcp-server/design-mcp-server"><img src="https://agentmods.dev/badge/skills/cyanheads/reference-data-mcp-server/design-mcp-server.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 5.1 | $0.00062 | $0.15748 |
| Opus 5 | $0.00031 | $0.07874 |
| Sonnet 5 | $0.00012 | $0.03150 |
| Haiku 4.5 | $0.00006 | $0.01575 |
Grade A, and why
design-mcp-server 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 5d 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.
This is a copy
98% identical to design-mcp-server — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 714 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
- User says "I want to build a ___ MCP server"
- User has an API, database, or system they want to expose to LLMs
- User wants to plan tools before scaffolding
- Existing server needs a new capability area (design the addition, not just a single tool)
Do NOT use for single-tool additions — use add-tool directly.
Inputs
Gather before designing. Ask the user if not obvious from context:
- Domain — what system, API, or capability is this server wrapping? Or is the server providing internal capability with no external dependency (computation, text/code utilities, in-memory state)?
- Data sources / source of truth — APIs, databases, file systems, external services? Or is the server itself the source (in-memory state, pure computation, local-only utility, embedded model)?
- Target users — what will the LLM (and its human) be trying to accomplish?
- Scope constraints — read-only? write access? admin operations? what's off-limits?
If the domain has a public API, read its docs before designing. For internal-only servers, skip API research and go straight to user goals. Don't design from vibes either way.
Server scope and audience
Before committing to a server boundary, answer: what workflow does this server serve, and who is the audience?
The unit of a server is a user workflow, not an API. A single rich API can earn its own server when the audience is large and the API surface supports a full workflow (PubMed for literature research, SEC EDGAR for financial analysis, Shodan for internet-wide device intelligence). Multiple APIs should collapse into one server when they serve the same workflow from different angles — a "threat intelligence" server that aggregates VirusTotal, AbuseIPDB, and GreyNoise is more useful than three separate servers because the user's goal is "assess this indicator," not "query VirusTotal."
Don't default to one-API-one-server. That's the right call when the API is deep enough and the audience is large enough, but it's not the starting point. The starting point is the workflow:
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.
- 5d ago First seen · 714 lines · 62 tokens per session scan A 84044a901bd8
design-mcp-server is a skill published in the GitHub repository cyanheads/reference-data-mcp-server (1 stars, last pushed 12d ago), licensed Apache-2.0. It adds 62 tokens to every session and 15,748 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to design-mcp-server, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
verify-task
Verify a work item is actually done by running the V- validation rows its issue cites. Maps V- IDs to the CI step / test command via VALIDATION.md, runs them, reports pass/fail per row.
promote-idea
Promote an Inbox bullet from BACKLOG.md to either a GitHub issue (work commitment) or a briefing (briefings/B-NNNN-.md, research/decision support). Asks which based on whether the work is committed or still needs thinking. Removes the original bullet.
observations
List recent captured session observations (the Haiku-summarized voyage logs). Use when the user wants to see what Captain Memo has logged from past sessions.
wtf-happened
Retrieve a distilled timeline of the current troubleshooting incident and generate a runbook skeleton. Returns a concise summary by default, or the full untruncated timeline on request.
wtf-now
Add a manual observation to the WTF flight recorder journal. The entry is stored as a crafted (intentional) record. Classification of the entry's action type is handled by the background classifier — do not attempt to infer it here.
wtf
Launch the WTF flight recorder for a new troubleshooting incident. Archives any prior incident, prompts for an optional title, then puts Claude into flight recorder mode where significant observations, theories, and corrective actions are journaled automatically.