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 skills add cyanheads/oecd-mcp-server --skill oecd-guidegit clone --depth 1 https://github.com/cyanheads/oecd-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/oecd-mcp-server/oecd-guide)<a href="https://agentmods.dev/skills/cyanheads/oecd-mcp-server/oecd-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/oecd-mcp-server/oecd-guide/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/skills/cyanheads/oecd-mcp-server/oecd-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/oecd-mcp-server/oecd-guide.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 | $0.00078 | $0.02119 |
| Opus 5.5 | $0.00031 | $0.00848 |
| Sonnet 5.5 | $0.00016 | $0.00424 |
| Haiku 4.5 | $0.00008 | $0.00212 |
Grade A, and why
oecd-guide 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 today.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
OECD statistics on harmonised definitions, keyless: OECD members, partner economies (Brazil, China, India, South Africa and others), and group aggregates such as G7, G20, OECD, Euro area, and European Union. Use it for cross-country comparison. Each dataflow is a fixed slice of the catalog, so near-identical flows often differ only in their country set or measures. Search results show this: one national-accounts structure underlies many quarterly flows.
Identifiers
| Identifier | Shape | Comes from |
|---|---|---|
| agency id | OECD.SDD.NAD |
oecd_list_agencies, or the part of a flow ref before the comma |
| flow ref | OECD.SDD.NAD,DSD_NAMAIN1@DF_QNA_EXPENDITURE_GROWTH_OECD |
oecd_search_datasets — pass through unchanged |
| dimension id and position | REF_AREA, position 3 |
oecd_get_dataset_info — order differs per structure (FREQ is first in quarterly national accounts, ninth in monthly unemployment) |
| code | USA, B1GQ, G1 |
oecd_get_dimension_values; its search matches code or label, case-insensitive, so gross domestic product finds B1GQ |
| key | Q..USA...B1GQ......G1. |
you build it: one segment per dimension in position order |
| canvas id, table name | Bw5nAvopBg, spilled_54593839 |
oecd_query_dataset, only when the result spills |
Flows whose refs share a dsd_id normally share a key layout. A key built for DF_QNA_EXPENDITURE_GROWTH_OECD also runs against DF_QNA_EXPENDITURE_GROWTH_G20. If a reused key fails with invalid_key, check that flow with oecd_get_dataset_info.
Gates
A codelist is not a coverage list. oecd_get_dimension_values returns the whole shared codelist. A transformation codelist lists 59 codes, but the quarterly growth flow carries three of them. A listed code the flow doesn't carry returns no_results. Before you trust a code, probe:
- Pin only the segments you are sure of, usually frequency and one country. Leave every other segment empty.
- Set
start_periodandend_periodto the same recent period. - Read the returned rows. Each one is a series the flow actually has, and its labels show the codes worth looking up.
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.
- today First seen · 70 lines · 78 tokens per session scan A e40cdb311882
oecd-guide is a skill published in the GitHub repository cyanheads/oecd-mcp-server (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 78 tokens to every session and 2,119 once invoked, about $0.0003 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 2026-10-29.
Other skills, from other repositories
internet-archive-guide
Use ia tools to investigate historical web pages or Internet Archive books and documents. Resolve capture and item identities, compare the captures actually served, and check coverage before claiming content absent or fully read.
national-parks-guide
Build NPS visit plans with nps tools when a trip involves camping, dated events, ambiguous park names, or nearby destinations. Check identity, access, and reservation evidence before turning discovery results into an itinerary.
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.clientCapabilities, ctx.enrich, ctx.content), and when to use each.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.