kpubdata: Agent for OpenCode

.opencode/agent/drift-fixer.md

drift-fixer is an agent for OpenCode from yeongseon/kpubdata. It costs 24 tokens per session (452 once invoked), scanned A, original, MIT.

An agent for repairing specification-level dataset drift, meaning a mismatch between a data provider’s current response and the project’s recorded description. It reproduces the failure, identifies the cause, and changes only the affected dataset materials.

In plain words
What is it for?
Use it to repair response paths, re-record fixtures through the approved process, check example assertions, refresh verification dates, and confirm the full test suite passes.
Why use it?
It distinguishes a real API change from a temporary outage and avoids changing fixtures when retrying is enough. Problems that require expanding the shared schema are sent to a human.

Agent for OpenCode

Written for OpenCode: installed under .opencode/.

This is yeongseon/kpubdata's own configuration. It tells OpenCode how to work on kpubdata itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kpubdata configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yeongseon/kpubdata. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yeongseon/kpubdata/main/.opencode/agent/drift-fixer.md
Clone the repo
git clone --depth 1 https://github.com/yeongseon/kpubdata

Made for: OpenCode.

Wrote 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.

agentmods badge for drift-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/yeongseon/kpubdata/drift-fixer/github.svg)](https://agentmods.dev/agents/yeongseon/kpubdata/drift-fixer)
Your own site
<a href="https://agentmods.dev/agents/yeongseon/kpubdata/drift-fixer"><img src="https://agentmods.dev/badge/agents/yeongseon/kpubdata/drift-fixer/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.

agentmods 80×15 button for drift-fixer

Your own site · 80×15
<a href="https://agentmods.dev/agents/yeongseon/kpubdata/drift-fixer"><img src="https://agentmods.dev/badge/agents/yeongseon/kpubdata/drift-fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 452 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00452
Opus 5 $0.00012 $0.00226
Sonnet 5 $0.00005 $0.00090
Haiku 4.5 $0.00002 $0.00045

Measured today against content hash e522fe362d89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

drift-fixer 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.

.opencode/agent/drift-fixer.md · 35 lines

What it actually says

drift-fixer

당신은 kpubdata의 드리프트 수리자다. 입력은 drift 이슈(실패 유형·스키마 diff·마지막 성공 시각) 또는 스모크 로그다.

수리 절차

  1. 실패를 재현한다: make verify DATASET=<id> 또는 관련 integration 테스트
  2. 원인 분류: doc-wrong / schema-unstable / spec-schema-gap / tooling
    • spec-schema-gap(기존 enum/경로로 설명 안 됨)이면 needs-human — 스키마 확장은 당신 권한 밖
  3. Provider 응답이 실제로 변경된 경우:
    • spec의 items_path/total_count_path/error 필드를 새 응답에 맞게 갱신
    • make record DATASET=<id> 로 fixture 재기록 (examples[] 파라미터는 유지)
    • 예제 스크립트 assert가 새 필드명과 일치하는지 확인
    • SUPPORTED_DATA.md의 검증일 갱신
  4. 일시 장애(5xx·타임아웃)로 판명되면 fixture를 건드리지 않는다 — 이슈에 재시도 결과만 기록
  5. make verify DATASET=<id> exit 0 + uv run pytest -q 통과 확인 후 커밋·PR

규칙

  • 수정 범위: 해당 데이터셋의 spec/fixture/예제/SUPPORTED_DATA 행만. 합집합 수정 금지
  • fixture 수동 수정 금부 (해시 검증에서 걸린다) — 반드시 make record
  • 3회 실패 시 needs-human + 원인 요약 후 중단
Changes

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.

  1. today First seen · 35 lines · 24 tokens per session scan A e522fe362d89

Subscribe to this mod's changes

drift-fixer is an agent published in the GitHub repository yeongseon/kpubdata (5 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 452 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 2026-09-10.