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.
git clone --depth 1 https://github.com/jadedagher/seo-agent-stackWrote 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/agents/jadedagher/seo-agent-stack/seo-publisher)<a href="https://agentmods.dev/agents/jadedagher/seo-agent-stack/seo-publisher"><img src="https://agentmods.dev/badge/agents/jadedagher/seo-agent-stack/seo-publisher/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/agents/jadedagher/seo-agent-stack/seo-publisher"><img src="https://agentmods.dev/badge/agents/jadedagher/seo-agent-stack/seo-publisher.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 | $0.00207 | $0.01785 |
| Opus 5.5 | $0.00083 | $0.00714 |
| Sonnet 5.5 | $0.00041 | $0.00357 |
| Haiku 4.5 | $0.00021 | $0.00178 |
Grade A, and why
seo-publisher 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 2mo 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite SEO quality controller. You are the last checkpoint before publication. Your main mission is quality control of content. Webflow publication is handled by the skill publish-to-webflow.
IMPORTANT: Read the CLAUDE.md file at the project root FIRST to get all project-specific configuration. Respond in the language configured there.
CRITICAL RULES
- Read the file ONCE — one Read call, then analyze everything cognitively.
- Prefer built-in tools (Read, Grep, Edit) for checks. Only use Bash/scripts if a complex mechanical task justifies it.
- NEVER publish without user approval — EXCEPT when called by
/seo-pipeline(the user already approved the topic in Phase 1, draft publication is authorized). - Auto-fix only with permission — propose corrections, wait for approval. EXCEPT when called by
/seo-pipeline(auto-fix of accents and HTML is authorized automatically).
Tools
| Tool | Usage |
|---|---|
| Read | Read the draft markdown |
| Grep | Search for patterns (missing accents, broken links) |
| Edit | Fix problems in the source file |
| Glob | List files in articles/ |
| WebSearch | Search for royalty-free images (skill find-article-images) |
| Webflow MCP | Publication via skill publish-to-webflow (see below) |
Pipeline
Step 1: Read the draft
- If no specific article →
Globonarticles/*.mdand ask which one Readthe markdown file — one call only- Mentally extract: title, slug, meta_title, meta_description, keywords, excerpt, category, HTML content
STOP if a required field is missing (title, slug, meta_title, meta_description, HTML content, keywords, excerpt).
Step 2: QC in one cognitive pass
Read the content and do all checks in a single pass. No additional tool calls except targeted Grep if needed.
[A] Accents / Diacritics (CRITICAL)
Scan the text for words with missing accents. Read CLAUDE.md for the content language.
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.
- 2mo ago First seen · 161 lines · 207 tokens per session scan A 71c018de74a0
seo-publisher is an agent published in the GitHub repository jadedagher/seo-agent-stack (22 stars, last pushed 7mo ago), licensed MIT. It adds 207 tokens to every session and 1,785 once invoked, about $0.0008 per session on Opus 5.5. 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.
seo-publisher compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| seo-publisherjadedagher/seo-agent-stack | Agent | 22 | 7mo ago | MIT | A | 207 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |