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 skills/nicepkg/ai-workflow/pre-publish-post-assistantnpx skills add nicepkg/ai-workflow --skill pre-publish-post-assistantgit clone --depth 1 https://github.com/nicepkg/ai-workflowWrote 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/nicepkg/ai-workflow/pre-publish-post-assistant)<a href="https://agentmods.dev/skills/nicepkg/ai-workflow/pre-publish-post-assistant"><img src="https://agentmods.dev/badge/skills/nicepkg/ai-workflow/pre-publish-post-assistant.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 | $0.00073 | $0.01495 |
| Opus 5 | $0.00036 | $0.00747 |
| Sonnet 5 | $0.00015 | $0.00299 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
pre-publish-post-assistant 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 5d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-publish Post Assistant Skill
Purpose
This skill helps prepare blog posts for publication by providing intelligent suggestions for:
- Categories - From existing site categories, with distribution awareness
- Tags - From existing tags, avoiding tag pollution
- SEO Metadata - Title, meta description, and focus keyphrase
All suggestions include rationale explaining the reasoning.
When to Use This Skill
- User says "classify this post" or "suggest categories/tags"
- User asks to "prepare this post for publishing"
- User wants "SEO suggestions" for a draft
- User provides a draft post and asks for taxonomy suggestions
- User mentions "new blog post" and needs categorization help
Key Principles
Category Selection
- Limit to 1-2 categories per post (primary + optional secondary)
- Prefer categories with moderate post counts (avoid over/under-populated)
- Match content theme, not just keywords
- Consider category hierarchy if applicable
Tag Selection
- Limit to 3-5 tags per post
- Only use existing tags (no new tag creation unless explicitly requested)
- Avoid tag pollution (tags with only 1-2 posts are low value)
- Prefer tags that group related content meaningfully
- Consider tag search potential
SEO Metadata
- Title: 50-60 characters, include primary keyword, compelling
- Meta Description: 150-160 characters, summarize value proposition, include CTA
- Focus Keyphrase: 2-4 words, searchable, relevant to content
Input Formats
The skill accepts draft content in multiple formats:
# File path
"Classify this post: /path/to/draft.md"
# URL (for already-published posts needing optimization)
"Suggest tags for https://example.com/my-post/"
# Inline text
"Here's my draft: [content]... What categories fit?"
Data Sources
Categories and Tags
Can be retrieved from:
- WordPress GraphQL - Live data from WP
- Static dist folder - Parse from built site (
/category/,/tag/pages) - Cached taxonomy file - Pre-generated
taxonomy.json
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.
- 5d ago First seen · 212 lines · 73 tokens per session scan A 2684be8f2c09
pre-publish-post-assistant is a skill published in the GitHub repository nicepkg/ai-workflow (283 stars, last pushed 7mo ago), licensed MIT. It adds 73 tokens to every session and 1,495 once invoked, about $0.0004 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
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
lazarus-group
Adversary-emulation profile for Lazarus Group (G0032, aka Hidden Cobra / Diamond Sleet / Labyrinth Chollima), a North Korean RGB-linked actor conducting espionage, destructive, and financially motivated operations.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.