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 yeongseon/kpubdata --skill kpubdata-datasetgit clone --depth 1 https://github.com/yeongseon/kpubdataWrote 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/yeongseon/kpubdata/kpubdata-dataset)<a href="https://agentmods.dev/skills/yeongseon/kpubdata/kpubdata-dataset"><img src="https://agentmods.dev/badge/skills/yeongseon/kpubdata/kpubdata-dataset/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/yeongseon/kpubdata/kpubdata-dataset"><img src="https://agentmods.dev/badge/skills/yeongseon/kpubdata/kpubdata-dataset.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 | $0.00042 | $0.00567 |
| Opus 5.5 | $0.00017 | $0.00227 |
| Sonnet 5.5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
kpubdata-dataset 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
kpubdata 데이터셋 절차
데이터셋 추가 (기본 경로)
완성 여부는 make verify DATASET={provider}.{dataset_key} exit code로 기계 판정한다.
- 이슈의 data.go.kr URL에서 활용가이드 확인
(
docs/sources/{dataset}/는scripts/fetch_guide.py생성물이라 저장소에 없다 — 있으면 우선, 없으면 URL 직접) - 골든 예제 복사 →
src/kpubdata/specs/{provider}/{dataset_key}.yaml- 단순
datago.hospital_info/ 페이지네이션datago.apt_trade/ XMLdatago.village_fcst - 계약
src/kpubdata/specs/schema.json, 검증uv run python scripts/validate_spec.py
- 단순
make record DATASET=<id>— 실API fixture 3종(raw/meta/expected) 기록examples/{provider}/{dataset_key}.py— 파라미터는 spec examples[]와 동일(replay 계약), assert ≥1make verify DATASET=<id>exit 0까지 반복SUPPORTED_DATA.md갱신 +uv run python scripts/gen_docs_examples.py
드리프트 수리
- 재현 → 원인 분류(doc-wrong / schema-unstable / spec-schema-gap / tooling)
- spec 필드 갱신 →
make record재기록 → 예제 확인 →SUPPORTED_DATA.md검증일 갱신 - spec-schema-gap이면 needs-human
공통 규칙
- 수정 허용:
src/kpubdata/specs/,examples/,tests/fixtures/(record로만),docs/sources/(생성물),SUPPORTED_DATA.md - 수정 금지:
src/kpubdata/core/,src/kpubdata/providers/,tests/contract/,tests/unit/,scripts/,Makefile,.github/ - 금지: fixture 수동 작성, 테스트 skip, assert 약화,
status: broken회피 - 3회 실패 →
needs-human+ 원인 요약 후 중단 - 함정 목록: AGENTS.md "흔한 함정" 참조 (영문 필드명, TMP/PCP, base_date 최신성, envelope 4종)
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 Changed · +1 lines e52ec068f314
- 1mo ago First seen · 34 lines · 42 tokens per session scan A c6b213fecffc
kpubdata-dataset is a skill published in the GitHub repository yeongseon/kpubdata (6 stars, last pushed 28d ago), licensed MIT. It adds 42 tokens to every session and 567 once invoked, about $0.0002 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 2026-09-10.
Other skills, from other repositories
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.
api-simulation
Runs your code for real against stand-ins for the HTTP services it calls, served together as one environment on one local port or one deployed URL, whether that code is a service you're changing, a frontend, a test suite or a demo. Use when you add or change code that calls other services and need to run it, test it…
api-mocking
Finds, builds, runs and publishes a stand-in for one API — the owning team's published mock when there is one, otherwise one built from its spec or collection that behaves like the real API, stateful when callers write then read. Use when something needs an API that isn't built or reachable yet (a frontend, client or…
webhook-testing
Capture, forward to localhost, replay, and validate webhook deliveries using a reusable public URL. Keep sender configuration across debugging sessions and record arrivals even while local forwarding is stopped, helping distinguish delivery failures from local connectivity issues. Use for implementing or debugging…
api-testing
Use when testing an endpoint, running collection assertions, or checking real application traffic against an API contract. Reuses saved requests and reports what live, mocked, or captured-traffic results actually establish. Use for requests such as "test this endpoint".
performance-testing
Use when load-testing or benchmarking an API with concurrent virtual users and latency or error thresholds. Reuses a collection to probe a chosen failure mode and distinguishes target limits from load-generator limits. Use for requests such as "load test this API".