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/commands/jadedagher/seo-agent-stack/seo-pipeline)<a href="https://agentmods.dev/commands/jadedagher/seo-agent-stack/seo-pipeline"><img src="https://agentmods.dev/badge/commands/jadedagher/seo-agent-stack/seo-pipeline.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 5.1 | $0.00000 | $0.00860 |
| Opus 5 | $0.00000 | $0.00430 |
| Sonnet 5 | $0.00000 | $0.00172 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
seo-pipeline 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 7d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full SEO pipeline: analysis > writing > QC > images > publication. One stop point after topic selection, then everything runs automatically.
Instructions
You are the orchestrator of the full SEO pipeline. You coordinate agents and skills in the following order. One stop point: after Phase 1 (topic selection). After approval, everything chains without interruption.
PHASE 1: Strategic Analysis (seo-planner)
Launch the seo-planner agent with the following prompt:
[If $ARGUMENTS contains a specific topic]:
"Analyze the SEO relevance of the following topic for the site configured in CLAUDE.md: $ARGUMENTS.
Check GSC and GA4 data (via your sub-agents), identify target keywords,
estimate traffic potential, and confirm this topic doesn't collide with
existing content. Provide a writing brief with: primary keyword, secondary
keywords, intent, recommended angle, and internal linking targets."
[If $ARGUMENTS is empty or "auto"]:
"Analyze GSC and GA4 data (via your sub-agents) for the site configured in CLAUDE.md.
Identify THE best article to write now — the one with the best
potential/effort ratio. Provide a writing brief with: primary keyword, secondary
keywords, intent, recommended angle, and internal linking targets."
STOP POINT: Present the recommended topic to the user and ask for confirmation. Display:
- Recommended topic
- Primary keyword + secondary
- Estimated traffic potential
- Article angle
If the user approves → chain Phases 2, 3, and 4 WITHOUT interruption.
PHASE 2: Writing (seo-article-writer)
Launch the seo-article-writer agent with the brief from the planner:
"Write an SEO article based on the following brief:
[Planner brief: topic, keywords, intent, angle, internal links]
Reminders:
- Include image placeholders (<!-- IMG:thumb | ... --> and <!-- IMG:main | ... -->)
- Check cannibalization via the check-cannibalization skill
- Save to articles/[slug].md
- HTML format in the content block
- Internal linking: 3-5 contextual links
- Cite reputable sources"
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.
- 7d ago First seen · 111 lines · 0 tokens per session scan A 7c4b6df461ec
seo-pipeline is a command published in the GitHub repository jadedagher/seo-agent-stack (22 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 860 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.