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 seolcoding/korean-stat-mcp --skill kosis-apigit clone --depth 1 https://github.com/seolcoding/korean-stat-mcpWrote 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/seolcoding/korean-stat-mcp/kosis-api)<a href="https://agentmods.dev/skills/seolcoding/korean-stat-mcp/kosis-api"><img src="https://agentmods.dev/badge/skills/seolcoding/korean-stat-mcp/kosis-api/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/seolcoding/korean-stat-mcp/kosis-api"><img src="https://agentmods.dev/badge/skills/seolcoding/korean-stat-mcp/kosis-api.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 | $0.00090 | $0.00456 |
| Opus 5.5 | $0.00036 | $0.00182 |
| Sonnet 5.5 | $0.00018 | $0.00091 |
| Haiku 4.5 | $0.00009 | $0.00046 |
Grade A, and why
kosis-api 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 1mo 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.
What it actually says
KOSIS API
Use this skill to work with KOSIS OpenAPI through the local Python client modules in this repository. Prefer direct Python module calls over starting the MCP server.
Default Workflow
- Identify the KOSIS task: search, metadata inspection, data fetch, large data, explanation, key indicator, transform, chart, or report.
- Load only the reference file needed for that task.
- Use
src/kosis_tools/clients directly. - Require
KOSIS_API_KEYbefore live KOSIS calls. - Search or inspect metadata before fetching data.
- Fetch a small bounded slice first, then expand.
- Report table id, organization id, period, unit, endpoint, and limits.
Reference Routing
- For available official API groups, limits, and source URLs, read
references/official-api-index.md. - For ordinary statistics data calls and period/classification parameters, read
references/statistics-data.md. - For which repository module to reuse, read
references/repo-client-map.md.
Add or read more reference files only when the task needs them. Keep official manual details in references, not here.
Scripts
- Use
scripts/kosis_call.pyfor a quick authenticated raw API check. - Prefer repository modules for production work; the script is a smoke-test and debugging helper.
Constraints
- Do not use the MCP server layer unless the user explicitly asks for MCP behavior.
- Do not browser-scrape KOSIS pages when an OpenAPI endpoint or official PDF reference is sufficient.
- Do not load the full official PDF into context. Extract or open only the relevant reference section.
- Treat older deployment URLs and production-status claims in repository docs as stale until verified.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 39 lines · 90 tokens per session scan A cf12c489b43b
kosis-api is a skill published in the GitHub repository seolcoding/korean-stat-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 90 tokens to every session and 456 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
statistical-analysis-and-experiments
Use when designing or analysing an A/B test, computing power or sample size, testing whether a difference is real, or writing any statistical claim — effect sizes with intervals, SRM checks, multiple comparisons and causal caveats.
skills
Generate a complete SVG file from a natural language description using SEP-1577 multi-step sampling.
vault-workflow
Use when the user asks you to search, read, or reason about notes in their markdown vault — guides when to use which vault tool and how to chain them for good results.
pr-alignment-loop
Iterate a PR to its final form by running two opposing reviewer droids (reviewer-robustness and reviewer-minimalist) in a bounded back-and-forth loop. The main orchestrator synthesizes their feedback, makes edits, runs tests, and stops when both approve, on stagnation, or after 3 rounds. Use when the user asks to…
inno-experiment-analysis
This skill should be used when the user asks to "analyze experimental results", "generate results section", "statistical analysis of experiments", "compare model performance", "create results visualization", or mentions connecting experime...