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 Glad-Labs/poindexter --skill seo-metadatagit clone --depth 1 https://github.com/Glad-Labs/poindexterWrote 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/glad-labs/poindexter/seo-metadata)<a href="https://agentmods.dev/skills/glad-labs/poindexter/seo-metadata"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/seo-metadata/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/glad-labs/poindexter/seo-metadata"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/seo-metadata.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 | $0.00043 | $0.00948 |
| Opus 5 | $0.00022 | $0.00474 |
| Sonnet 5 | $0.00009 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
seo-metadata 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 4d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO metadata skill
Six prompts the pipeline uses to derive post metadata from a topic or draft.
The architect routes on the description above; UnifiedPromptManager resolves
each template by key (Langfuse override still wins over the bodies below).
Default prompts — basic but functional; production-quality prompt packs ship as a premium add-on.
seo.generate_title
You are titling a finished blog article. Read the article material below and
write one compelling, SEO-friendly title that describes what the article
actually says.
The TOPIC line is the internal assignment label that seeded the article. It
may be vague, ambiguous, or an internal directive (e.g. "Expand coverage of
X"). Never copy the topic verbatim and never title the topic alone — ground
the title in the ARTICLE text: its claims, subject matter, and terminology.
When the topic and the article seem to disagree, trust the article.
Include the primary keyword "{primary_keyword}" only when it fits the
article's actual content naturally.
Let the article's own specifics choose the title's shape. The most memorable
title is usually the one carrying this article's concrete detail — the number
that surprised you, the thing that broke, the claim a reader would argue
with — so reach for that detail before reaching for a familiar headline
frame. A title indistinguishable from the last twenty on the site tells a
returning reader nothing about which article this is. Accuracy still outranks
novelty: a title the article does not support is worse than a familiar one.
Name the searchable thing. A reader finds this article by typing a concrete
noun into a search box — the product, model, tool, library, standard, number,
or exact technical term the article is about — so the title must contain at
least one, spelled the way people type it ("RTX 5090", "FastAPI", "GGUF
Q4_K_M", "Chatterbox"). A title that is only a mood or a mystery ("The Gap
Nobody Names", "The five days nobody was watching") has no query to match and
is never found; keep the intrigue if you like, but anchor it to the thing.
Return ONLY a JSON object with a single "title" key — no markdown, no code
fences, no reasoning, no text before or after the object. The first character
of your reply is `{{` and the last is `}}`:
{{"title": "<the title — plain text, no quotes or markdown inside>"}}
TOPIC (assignment label — context only): {topic}
ARTICLE:
{content}
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.
- 4d ago Changed · +8 lines 7fd673948d18
- 12d ago First seen · 104 lines · 43 tokens per session scan A e6b91f33bad4
seo-metadata is a skill published in the GitHub repository Glad-Labs/poindexter (5 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 948 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.
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.
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.
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…
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.
glmocr
An optical character recognition tool that extracts printed text, tables, mathematical formulas, and handwriting from images or PDFs.
guide
A project-guide workflow that summarizes the OpenClaw Bot system, its commands, enabled skills, memory, and recent social publishing activity.