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 commands/jadedagher/seo-agent-stack/healthgit 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/health)<a href="https://agentmods.dev/commands/jadedagher/seo-agent-stack/health"><img src="https://agentmods.dev/badge/commands/jadedagher/seo-agent-stack/health.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 | $0.00000 | $0.00872 |
| Opus 5 | $0.00000 | $0.00436 |
| Sonnet 5 | $0.00000 | $0.00174 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
health 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnostic check for the SEO Agent Stack. Tests all connections and verifies configuration.
Instructions
You are the health checker for the SEO Agent Stack. Run all checks and report the status clearly.
Respond in the user's language (detect from CLAUDE.md or their message).
CHECK 1: CLAUDE.md Configuration
Read CLAUDE.md and verify:
- No remaining placeholders: Search for
{{in the file. Each occurrence is a FAIL. - Required fields filled:
- Site URL (not empty, starts with
https://) - Site Name (not empty)
- GA4 Property ID (numeric)
- GSC Property (starts with
sc-domain:orhttps://) - Webflow Site ID (not empty)
- At least 1 collection ID
- At least 1 keyword listed
- Tone configured
- Target audience configured
- Site URL (not empty, starts with
- Content inventory: Count how many items are listed in "Existing Content" section
CHECK 2: Google Search Console
mcp__gsc__list_sites
- Verify the GSC property from CLAUDE.md appears in the list
- If it does → PASS
- If not → FAIL with explanation
CHECK 3: Google Analytics 4
mcp__google-analytics__getActiveUsers
- Verify data comes back (any number, even 0)
- If it does → PASS
- If error → FAIL with explanation
CHECK 4: Webflow CMS
mcp__webflow__sites_list
Then for each collection ID in CLAUDE.md:
mcp__webflow__collections_items_list_items(collection_id)
- Verify the site ID matches
- Verify each collection exists and is accessible
- Count items in each collection
- Compare with the count in CLAUDE.md "Existing Content" section
- If counts differ → WARN (content inventory may be stale, suggest
/setupto refresh)
CHECK 5: File Structure
Verify these files/directories exist:
CLAUDE.md.mcp.json.claude/agents/(5 agent files).claude/commands/(should include setup.md, health.md, etc.).claude/skills/(5 skill files)articles/planning/
OUTPUT FORMAT
=== SEO AGENT STACK — HEALTH CHECK ===
[1] Configuration : [PASS|FAIL|WARN] — [details]
- Placeholders : [X remaining / All filled]
- Required fields: [X/Y filled]
- Content listed : [X items]
[2] Search Console : [PASS|FAIL] — [property] [connected/not found]
[3] Google Analytics : [PASS|FAIL] — Property [id] [returning data/error]
[4] Webflow CMS : [PASS|FAIL|WARN]
- Site : [name] ([id])
- Collections : [X accessible / Y configured]
- Content sync : [In sync / X items missing from CLAUDE.md]
[5] File Structure : [PASS|WARN] — [details if files missing]
=== OVERALL: [ALL GOOD | ISSUES FOUND] ===
[If issues found:]
Fix these issues:
1. [issue] → [how to fix]
2. ...
[If all good:]
Everything is connected and configured. You're ready to go!
- /seo-planner → Plan your next content
- /seo-pipeline auto → Write and publish automatically
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 First seen · 116 lines · 0 tokens per session scan A ff8d6f32018d
health 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 872 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
git
Git operations with intelligent commit messages and workflow optimization.
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.