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.
curl -O https://raw.githubusercontent.com/yeongseon/kpubdata/main/AGENTS.mdgit 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/instructions/yeongseon/kpubdata/agents-md)<a href="https://agentmods.dev/instructions/yeongseon/kpubdata/agents-md"><img src="https://agentmods.dev/badge/instructions/yeongseon/kpubdata/agents-md/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/instructions/yeongseon/kpubdata/agents-md"><img src="https://agentmods.dev/badge/instructions/yeongseon/kpubdata/agents-md.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 | $0.06099 | $0.06099 |
| Opus 5.5 | $0.02440 | $0.02440 |
| Sonnet 5.5 | $0.01220 | $0.01220 |
| Haiku 4.5 | $0.00610 | $0.00610 |
Grade A, and why
kpubdata AGENTS.md 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 28d 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.
How it starts
The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
POLICY.md is the single canonical source for project-management and review policy. Epic, Issue, Priority, Review Level, Verification and Release rules come from there. This file keeps only what is specific to this repository — build commands and directory rules. POLICY.md wins any conflict.
Purpose
This repository is built for agent-driven development. It is a Python 3.10+ framework with a small, stable public API and one adapter per provider.
Read these first
VALIDATION.mdPRD.mdARCHITECTURE.mdCANONICAL_MODEL.mdPROVIDER_ADAPTER_CONTRACT.mdAPI_SPEC.mdPACKAGING.md
Working principles
- Keep the public API small.
- Do not turn a provider's quirk into fake universal semantics.
- Do not remove the raw escape hatch.
- Do not mark a capability as supported before a test proves it.
- Keep provider complexity inside the provider adapter.
- Update tests and documentation in the same change as the behaviour.
SUPPORTED_DATA.mdis the single source of truth for which providers and datasets are supported.- When a provider's or dataset's support status or verification level changes,
update
SUPPORTED_DATA.mdin the same PR. - Mark something supported only once fixture, unit and contract tests pass.
- Mark live-API verified only once a real-API integration test exists and passes. Until then it stays test verified.
Language policy
ADR 0003 is canonical. The evidence (measurements across ten Korean OSS projects) and the rejected alternatives are there. This is the summary.
Titles are English; bodies are free. Titles show up in lists, searches and release notes.
| Area | Language |
|---|---|
| Code identifiers, comments, docstrings | English |
| Commit titles (= PR titles) | English — a squash merge makes the PR title the commit title |
| Commit bodies (= PR bodies) | Korean or English — the squash body is the PR body (POLICY 2.1.3, #743) |
| PR titles | English (Conventional Commits) — a squash merge turns it into a commit |
| CHANGELOG and release notes | English |
Governance documents (AGENTS.md, CONTRIBUTING.md) |
English |
Implementation contracts (PROVIDER_ADAPTER_CONTRACT.md, API_SPEC.md) |
English |
Design rationale (VALIDATION.md, ARCHITECTURE.md, ADRs) |
Korean |
| README | Two files: README.md in Korean, README.en.md in English, kept in step by scripts/check_readme_parity.py (ADR 0003) |
| Issue titles | English |
| Issue bodies | Korean or English |
| PR bodies and review comments | Korean or English |
Korean-domain documents (docs/providers/, 활용신청, 공공누리 terms) |
Korean |
| User-visible string literals | Out of scope — runtime behaviour, decided separately |
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.
- 28d ago Changed · +14 lines · +352 tokens per session 72cc44ff588a
- 1mo ago Changed · +54 lines · +834 tokens per session 7880b33afdf9
- 1mo ago Changed · +11 lines · +247 tokens per session 2bbe1636acdb
- 1mo ago Changed · +106 lines · -61 tokens per session b799dcc31e8d
- 1mo ago Changed · +5 lines · +96 tokens per session 8a738b400ca7
- 1mo ago Changed · +2 lines · +38 tokens per session f627c42d9505
- 1mo ago Changed · +51 lines · +1,058 tokens per session f87a9aa4008c
- 2mo ago First seen · 291 lines · 3,535 tokens per session scan A 02f5d5b5dff5
kpubdata AGENTS.md is an instructions file published in the GitHub repository yeongseon/kpubdata (6 stars, last pushed 29d ago), licensed MIT. It adds 6,099 tokens to every session, about $0.0244 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.