content-type-classifier

content-type-classifier is a skill for Claude Code, Codex from Glad-Labs/poindexter. It costs 30 tokens per session (423 once invoked), scanned A, original, Apache-2.0.

A tool for assigning one or more subject labels to a published technical blog post, such as AI and machine learning, gaming, or software engineering.

In plain words
What is it for?
Use it to classify posts for content organization, filtering, search, and database records.
Why use it?
It removes the need to label posts manually and avoids forcing a category when none genuinely fits.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to classify posts for content organization, filtering, search, and database records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/glad-labs/poindexter/content-type-classifier
Install

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.

Any agent
npx skills add Glad-Labs/poindexter --skill content-type-classifier
Clone the repo
git clone --depth 1 https://github.com/Glad-Labs/poindexter

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for content-type-classifier

README.md
[![agentmods](https://agentmods.dev/badge/skills/glad-labs/poindexter/content-type-classifier.svg)](https://agentmods.dev/skills/glad-labs/poindexter/content-type-classifier)
Your own site
<a href="https://agentmods.dev/skills/glad-labs/poindexter/content-type-classifier"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/content-type-classifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 423 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00423
Opus 5 $0.00015 $0.00211
Sonnet 5 $0.00006 $0.00085
Haiku 4.5 $0.00003 $0.00042

Measured 8d ago against content hash c0677afbc74d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

content-type-classifier 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 8d 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.

src/cofounder_agent/skills/content/content-type-classifier/SKILL.md · 45 lines

What it actually says

Content-type classifier skill

Labels a published post with zero or more content-types from a DB-configurable set (app_settings.content_type_labels). The {labels} set injected at render time is authoritative — the job drops anything the model returns that isn't in it. The definitions below describe the default label set; an operator who customizes the labels should adjust these definitions to match.

content.classify_content_type

You label a technical blog post with zero or more CONTENT TYPES from this exact set:
{labels}

Definitions (for the default label set):
- ai-ml: AI/ML models, LLM inference, agents, training, prompting, RAG.
- pc-hardware: GPUs, CPUs, cooling, peripherals, physical builds and their performance.
- gaming: games, game performance, frame times, gaming setups.
- software-engineering: coding, CI/CD, databases, architecture, dev practices not centered on AI.
- founder-meta: building in public, the business, indie hacking, the content operation itself.

Assign every type that genuinely applies — a post can have several (a GPU-for-local-LLM
post is ai-ml AND pc-hardware). Assign none if none truly fit; never force a label.

Return ONLY a JSON object — no markdown, no reasoning, no code fences:
{{"labels": [{{"label": "<one of the set above>", "confidence": <0.0-1.0>}}]}}

TITLE: {title}
TAGS (noisy hints, may be wrong): {tags}
EXCERPT:
{excerpt}
Changes

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.

  1. 8d ago First seen · 45 lines · 30 tokens per session scan A c0677afbc74d

Subscribe to this mod's changes

content-type-classifier is a skill published in the GitHub repository Glad-Labs/poindexter (5 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 423 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

spec-generate

Product Spec Builder that helps PMs generate clear, structured, testable PRDs. Creates both full and lightweight specs for any product or platform with a guided step-by-step workflow. Output in English Markdown format.

djblack1209-coder/OpenClaw-Bot · 46 tokens

product-team

A Chinese-language product development workflow led by one AI team lead taking several roles: product strategy, requirements writing, prototype creation, and user-experience review.

djblack1209-coder/OpenClaw-Bot · 104 tokens

Playwright (Automation + MCP + Scraper)

Browser automation via Playwright MCP. Navigate websites, click elements, fill forms, take screenshots, extract data, and debug real browser workflows. Use when (1) you need a real browser, not static fetch; (2) the task involves Playwright MCP, browser tools, Playwright tests, scripts, or JS-rendered pages; (3) the…

djblack1209-coder/OpenClaw-Bot · 104 tokens

ux-walkthrough-skill

A user-experience review process that examines a product’s screens and user journeys against its product requirements document (PRD). It checks consistency, accessibility, errors, and whether users can complete tasks clearly.

djblack1209-coder/OpenClaw-Bot · 72 tokens

glmocr

An optical character recognition tool that extracts printed text, tables, mathematical formulas, and handwriting from images or PDFs.

djblack1209-coder/OpenClaw-Bot · 87 tokens

gstack-review

A set of review modes that examines development work from product, engineering, security, quality-assurance, and release perspectives.

djblack1209-coder/OpenClaw-Bot · 35 tokens