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 agentmods add instructions/kangdacool/hwpx-editing-skill/agents-mdgit clone --depth 1 https://github.com/kangdacool/hwpx-editing-skillWrote 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/kangdacool/hwpx-editing-skill/agents-md)<a href="https://agentmods.dev/instructions/kangdacool/hwpx-editing-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/kangdacool/hwpx-editing-skill/agents-md.svg" alt="Measured on agentmods" 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 | $0.00507 | $0.00507 |
| Opus 5 | $0.00253 | $0.00253 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
hwpx-editing-skill 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 4d 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
AGENTS.md
This repository is an Agent Skill for editing HWPX (한글 / Hangul .hwpx) files.
If you are an AI coding agent working in this repo — or the user pointed you here to
work on a .hwpx file — use the skill instead of guessing.
When to use it
Any task touching a .hwpx file, a 한글/Hangul document, HWPML, or a Korean
government/academic document: reading/extracting text or tables, editing paragraphs,
tables, images, equations, footnotes/endnotes, memos; fixing layout (orphaned headings,
blank pages, columns); building a table of contents; repackaging the zip.
How to use it
- Read the skill:
skills/hwpx-editing/SKILL.md. It contains the workflow and points to the detailed guide and scripts. - Read the relevant section of
skills/hwpx-editing/references/hwpx-guide.mdfor the specific operation. - Use the scripts in
skills/hwpx-editing/scripts/— do not hand-roll zip repacking:inspect_hwpx.py FILE.hwpx --breaks— inspect structure and hidden page/column breakshwpxlib.py—repack_preserve,own,make_uid,strip_linesegarray, verify helpersverify.py EDITED.hwpx --orig ORIG.hwpx— run the §7 build checklistselftest.py— prove the repacker is lossless
- Dependency:
pip install lxml(Python 3.10+).
The non-negotiable rule
Never re-zip an HWPX with a normal zip writer — 한글 will reject it. Use
repack_preserve, which byte-copies unchanged entries and re-deflates only what you
changed. Verify every build; then ask the user to round-trip the file in 한글, since
LibreOffice cannot render HWPX.
Installing the skill elsewhere
To install this skill into an agent's global skills directory, run ./install.sh <agent>
(or see docs/INSTALL_LLM.md). Do not handle the user's credentials; if publishing or
auth is needed, ask the user to do it.
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.
- 4d ago First seen · 40 lines · 507 tokens per session scan A 724bc255c3bb
hwpx-editing-skill AGENTS.md is an instructions file published in the GitHub repository kangdacool/hwpx-editing-skill (8 stars, last pushed 3d ago), licensed MIT. It adds 507 tokens to every session, about $0.0025 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 2026-08-31.
Other instructions, from other repositories
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
llm-safe-haven CLAUDE.md
Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.
data-scientist copilot-instructions.md
Instructions for realnghon/data-scientist, covering github copilot — 项目指令：data scientist 工作流 and 共享核心 — 回答前请阅读.