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.
git 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/commands/kangdacool/hwpx-editing-skill/hwpx)<a href="https://agentmods.dev/commands/kangdacool/hwpx-editing-skill/hwpx"><img src="https://agentmods.dev/badge/commands/kangdacool/hwpx-editing-skill/hwpx/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/commands/kangdacool/hwpx-editing-skill/hwpx"><img src="https://agentmods.dev/badge/commands/kangdacool/hwpx-editing-skill/hwpx.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 | $0.00028 | $0.00294 |
| Opus 5.5 | $0.00011 | $0.00118 |
| Sonnet 5.5 | $0.00006 | $0.00059 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
hwpx 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
Work on the HWPX task described in: $ARGUMENTS
Follow the hwpx-editing skill strictly:
- Read
skills/hwpx-editing/SKILL.md(or the installed copy) and the relevant section ofreferences/hwpx-guide.mdfor this operation before editing anything. - Always start by inspecting the file:
python <skill>/scripts/inspect_hwpx.py <file>.hwpx --breaksIf layout is the problem, check hiddenpageBreak/columnBreakfirst (§6-A). - Edit the XML with lxml. Remove
linesegarrayafter edits; reassign ids on any clone; reuse existing charPr/paraPr. - Repack only with
hwpxlib.repack_preserve(never a normal zip writer). - Verify:
python <skill>/scripts/verify.py <edited>.hwpx --orig <original>.hwpx— all hard checks must pass, and the minimal-change diff should show only intended changes. - Work on a copy, keep the original, and remind the user to round-trip the result in 한글 (LibreOffice can't render HWPX).
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 · 22 lines · 28 tokens per session scan A 0a1cdfd56c31
hwpx is a command published in the GitHub repository kangdacool/hwpx-editing-skill (8 stars, last pushed 15d ago), licensed MIT. It adds 28 tokens to every session and 294 once invoked, about $0.0001 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 commands, from other repositories
convert
Convert a file or URL to Markdown using md-anything.
ingest
Batch-convert all supported files in a folder to Markdown.
extract-foundations-from-screens
Extract canonical foundations docs (color, typography, spacing, radii) from a batch of existing SCREENSPECs. Re-runs only add new tokens and route conflicts to a Review queue. Use when SCREENSPECs already document raw values and need converging into role tokens. Do not use when foundations are already curated and…
start-10-4.en
Lesson 10-4: GmailApp Email Search/Extraction → Sheet Organization!
generate-pdf-document
Specify a generated PDF that survives variable content, with fonts, page breaks, and accessibility handled.
compact
Summarize the requested conversation and upload a Markdown archive named after the working directory to Kireo.