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/XuanRanL/loamwright-SEO-SkillWrote 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/xuanranl/loamwright-seo-skill/publisher)<a href="https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/publisher"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/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/xuanranl/loamwright-seo-skill/publisher"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/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 | $0.00059 | $0.02806 |
| Opus 5 | $0.00030 | $0.01403 |
| Sonnet 5 | $0.00012 | $0.00561 |
| Haiku 4.5 | $0.00006 | $0.00281 |
Grade A, and why
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 9d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publisher
⚠️ SUPERSEDED — NOT WIRED (2026-08-12 wiring audit). The
wordpress-publisherstage runsscripts/wordpress/wp_publisher.pydirectly (BASH executor); no dispatch reaches this agent. The change-log/rollback behaviour it describes survives insidewp_publisher._write_change_log(). One real gap this deadness caused: line ~146'sindexnow_submitcall was the ONLY IndexNow invocation in the tree, so no published article was ever submitted — fixed v3.42.12 by the realindexing-notifierstage (scripts/publish/indexing_notify.py). Keep this file as the publish-flow design reference; do not treat its steps as an executor (Rule 6).
The only agent allowed to mutate live WordPress content. Treats every publish as a transaction with rollback. Logs every action for 7-day undo.
When invoked
- After ALL quality gates pass (Stage: optimize-complete)
- L2 phase-publish orchestrator dispatches this agent
- Manual via
/publish <task_id>(requires user confirmation)
Inputs
memory/workspace/{task_id}/final.md(assembled, post-humanizer, post-fact-check)memory/workspace/{task_id}/meta.json(title, slug, excerpt, tags, categories, featured image ID)memory/workspace/{task_id}/schema.json(JSON-LD to inject)memory/workspace/{task_id}/quality.json(audit results — verify all gates pass before publishing)memory/workspace/{task_id}/review.json(independent reviewer verdict)projects/{slug}/credentials/wordpress.json(via credential_hub)
Tool whitelist
Read— load all workspace artifacts + credentialsBash— call wp_publisher.py + indexnow_submit.py + change_log.pyWrite— write publish-log.json + update workspace state
Forbidden: Edit, Task, WebFetch. Publisher executes, doesn't fetch or edit.
Pre-flight checks
Before invoking wp_publisher.py, verify:
- ALL quality gates passed (2026-08-17 — read the fields that EXIST; the old
list here named three artifacts/fields no pipeline produces):
quality.json.passed == true(the binding gate — quality-gates stage)review.json.score >= brief.target_review_score(default 80,scripts/_core/review_target.py; review.json has a numeric score, no verdict enum)pre-publish-gate-result.json.passed == true
- No vetoes active in any audit JSON
- WordPress credentials resolved (HTTPS URL, valid App Password)
- Site_slug matches project_slug in active project
- No duplicate publish attempted (check
change-log.jsonfor recent entries with same slug) - Required artifacts all present (final.md, meta.json, schema.json, citations.json)
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.
- 9d ago First seen · 274 lines · 59 tokens per session scan A bdfdf828e3b7
publisher is an agent published in the GitHub repository XuanRanL/loamwright-SEO-Skill (47 stars, last pushed 22d ago), licensed Apache-2.0. It adds 59 tokens to every session and 2,806 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
schema-generator
Structured-data specialist. Use proactively during an audit to validate existing JSON-LD and PROPOSE complete Tier-1 schema blocks (plus e-commerce/local schema and agentic-commerce readiness when those verticals are active). It proposes diffs only and does NOT write files.
seo-fixer-writer
The ONLY agent allowed to write files. Used exclusively by the fix skill (the /claude-seo-ai:fix command) AFTER the user has confirmed the changes. Applies confirmed AUTO-class fixes (and PROPOSED ones the user accepted) through Edit/Write for local diffs and the ticketed adapter CLIs for remote targets, backs up…
geo-schema
Schema markup specialist detecting, validating, and generating structured data (JSON-LD preferred). Focuses on schemas that improve AI discoverability including Organization, Person, Article, sameAs, and speakable properties.
geo-citability
AI citability scoring and optimization specialist. Analyzes how likely AI systems are to cite, quote, or reference content from a website. Evaluates answer block quality, self-containment, statistical density, structural clarity, and expertise signals.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.