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 Dqz00116/skill-lib --skill hexo-blog-updategit clone --depth 1 https://github.com/Dqz00116/skill-libWrote 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/dqz00116/skill-lib/hexo-blog-update)<a href="https://agentmods.dev/skills/dqz00116/skill-lib/hexo-blog-update"><img src="https://agentmods.dev/badge/skills/dqz00116/skill-lib/hexo-blog-update/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/dqz00116/skill-lib/hexo-blog-update"><img src="https://agentmods.dev/badge/skills/dqz00116/skill-lib/hexo-blog-update.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 | $0.00017 | $0.01193 |
| Opus 5 | $0.00009 | $0.00596 |
| Sonnet 5 | $0.00003 | $0.00239 |
| Haiku 4.5 | $0.00002 | $0.00119 |
Grade A, and why
hexo-blog-update 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hexo Blog Update Skill
Overview
Standardized workflow for creating, editing, and publishing Hexo blog posts.
When to Use
Use this skill when you need to:
- Create a new blog post
- Edit existing blog posts
- Preview blog locally before publishing
- Deploy blog to production
Prerequisites
- Node.js installed (>= 14)
- Hexo CLI installed globally (
npm install -g hexo-cli) - Blog repository cloned locally
- Git configured with SSH key for deployment
Workflow
Step 1: Create New Post
# Navigate to blog directory
cd /path/to/blog
# Create new post
hexo new post "post-title"
# Or use npm script
npm run new "post-title"
Post will be created at: source/_posts/post-title.md
Step 2: Edit Post Content
Edit the generated markdown file with the following structure:
---
title: Post Title
date: YYYY-MM-DD HH:MM:SS
categories:
- Category 1
- Category 2
tags:
- Tag 1
- Tag 2
---
Post excerpt content, will be displayed in the homepage list...
<!--more-->
## Body Heading
Body content...
## Another Heading
More content...
Important Rules:
- ✅ Use
<!--more-->to separate excerpt from full content - ✅ Set proper categories and tags
- ✅ Use Chinese for Chinese blogs
- ✅ Keep front matter (YAML between ---) at the top
Step 3: Local Preview
# Start local server
hexo server
# Or with npm
npm run server
Access at: http://localhost:4000
Preview Checklist:
- Post appears in list with correct title
- Excerpt shows correctly (before
<!--more-->) - Full content displays properly
- Categories and tags are correct
- No formatting errors
Step 4: Deploy to Production
# Deploy (clean + generate + deploy)
npm run release-blog
# Or manually
hexo clean && hexo generate && hexo deploy
Deployment Output:
INFO Deploy done: git
To github.com:username/username.github.io.git
xxx...xxx HEAD -> master
Standard Post Template
---
title: Post Title
date: 2026-02-11 17:20:00
categories:
- Category 1
- Category 2
tags:
- Tag 1
- Tag 2
- Tag 3
---
Post excerpt, displayed in the homepage list. Briefly introduce the article content and value.
<!--more-->
## Preface
Detailed background introduction...
## Main Content
### Section 1
Content...
### Section 2
Content...
## Summary
Summary of key points...
---
*Related Links*:
- [Link Description](url)
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 · 246 lines · 17 tokens per session scan A 655deda7e058
hexo-blog-update is a skill published in the GitHub repository Dqz00116/skill-lib (22 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 1,193 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 2026-08-30.
Other skills, from other repositories
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
openclaw-debugger
Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger". Walks through the standard OpenClaw 2026.4 diagnosis checklist and prints a report.
tweetclaw
OpenClaw guide for Twitter search, follower exports, monitoring, media, and approved X automation through Xquik. Not affiliated with X Corp.
rosclaw-embodied
A set of rules for completing robot tasks in ROSClaw, a system for running and checking robot work. It covers approved robot files, acceptance evidence, and separate rules for simulation and real hardware.
git-commit-writer
Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.
meeting-notes
Paste raw meeting notes and get a clean summary with key decisions and action items.