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 dnnyngyen/kimi-agent-internals --skill docxgit clone --depth 1 https://github.com/dnnyngyen/kimi-agent-internalsWrote 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/dnnyngyen/kimi-agent-internals/docx)<a href="https://agentmods.dev/skills/dnnyngyen/kimi-agent-internals/docx"><img src="https://agentmods.dev/badge/skills/dnnyngyen/kimi-agent-internals/docx/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/dnnyngyen/kimi-agent-internals/docx"><img src="https://agentmods.dev/badge/skills/dnnyngyen/kimi-agent-internals/docx.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 | $0.00000 | $0.08233 |
| Opus 5 | $0.00000 | $0.04117 |
| Sonnet 5 | $0.00000 | $0.01647 |
| Haiku 4.5 | $0.00000 | $0.00823 |
Grade A, and why
docx 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 10d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/templates/CJKExample.cs 47 KB
- assets/templates/Example.cs 59 KB
- assets/templates/KimiDocx.csproj 343 B
- assets/templates/Program.cs 342 B
- references/EditingGuide.md 6.2 KB
- scripts/__init__.py 476 B runs code
- scripts/docx 13 KB
- scripts/docx_lib/__init__.py 2.4 KB runs code
- scripts/docx_lib/business_rules.py 9.8 KB runs code
- scripts/docx_lib/constants.py 2.7 KB runs code
- scripts/docx_lib/editing/__init__.py 1.7 KB runs code
- scripts/docx_lib/editing/comments.py 9.7 KB runs code
- scripts/docx_lib/editing/context.py 6.5 KB runs code
- scripts/docx_lib/editing/helpers.py 27 KB runs code
- scripts/docx_lib/editing/revisions.py 9.9 KB runs code
- scripts/docx_lib/editing/tests/test_xml_tolerance.py 5.1 KB runs code
- scripts/docx_lib/editing/xml_tolerance.py 3.6 KB runs code
- scripts/docx_lib/element_order.py 20 KB runs code
- scripts/fix_element_order.py 5.6 KB runs code
- scripts/generate_backgrounds.py 7.6 KB runs code
- scripts/generate_chart.py 8.9 KB runs code
- scripts/generate_inkwash_backgrounds.py 7.7 KB runs code
- scripts/validate_all.py 5.1 KB runs code
- scripts/validate_docx.py 4.2 KB runs code
- validator/Validator.deps.json 2.3 KB
- validator/Validator.runtimeconfig.json 328 B
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.
- 10d ago First seen · 828 lines · 0 tokens per session scan A 25ec4fb03429
docx is a skill published in the GitHub repository dnnyngyen/kimi-agent-internals (336 stars, last pushed 5mo ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 8,233 tokens. 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 2026-08-30.
Other skills, from other repositories
moe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE…
moe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE…
docx
Create and edit Word documents (.docx) — C# + OpenXML SDK for creation, WIR engine for editing/comments/tracked changes. Use for any .docx task including document creation, editing, comments, revisions, footnotes, TOC, and Markdown-to-Word conversion.
commodities-outlook
Produce institutional-grade commodity outlook reports with supply-demand analysis, price forecasts, and trade recommendations, formatted as PDF, DOCX, or PPTX documents. Triggered when users request commodity market reports, ask for trade ideas on energy, metals, or agricultural commodities, or mention keywords like…
longread
Use this skill when an agent (main agent or subagent) encounters a file too large to read in a single pass — e.g. cat, readfile, or Read tool hits size limits or truncates output. First assess whether the file is suitable for chunk-based parallel reading, then proceed accordingly. Supports PDF, DOCX, TXT, MD, PPTX…
moe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE…