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 Sarai-Chinwag/wp-openclaw --skill wp-openclaw-setupgit clone --depth 1 https://github.com/Sarai-Chinwag/wp-openclawWrote 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/sarai-chinwag/wp-openclaw/wp-openclaw-setup)<a href="https://agentmods.dev/skills/sarai-chinwag/wp-openclaw/wp-openclaw-setup"><img src="https://agentmods.dev/badge/skills/sarai-chinwag/wp-openclaw/wp-openclaw-setup/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/sarai-chinwag/wp-openclaw/wp-openclaw-setup"><img src="https://agentmods.dev/badge/skills/sarai-chinwag/wp-openclaw/wp-openclaw-setup.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 | $0.00040 | $0.01222 |
| Opus 5.5 | $0.00016 | $0.00489 |
| Sonnet 5.5 | $0.00008 | $0.00244 |
| Haiku 4.5 | $0.00004 | $0.00122 |
Grade B, and why
wp-openclaw-setup scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Credentials are saved to `~/.openclaw/credentials` (chmod 600). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -I https://yourdomain.com How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WP-OpenClaw Setup Skill
Purpose: Help a user install wp-openclaw on a remote VPS from their local machine.
This skill is for the local agent (Claude Code, etc.) assisting with installation. Once OpenClaw is running on the VPS, this skill is no longer needed — the OpenClaw agent takes over with its own pre-loaded skills.
FIRST: Interview the User
Do NOT proceed with installation until you've asked these questions and gotten answers.
Question 1: Installation Type
"Are you setting up a fresh WordPress site, or do you have an existing WordPress site you want to add OpenClaw to?"
Options:
- Fresh install — New VPS, new WordPress site
- Existing WordPress — Site already running, just add OpenClaw
- Migration — Site exists elsewhere, moving to this VPS
Question 2: Autonomous Operation
"Do you want autonomous operation capabilities? This includes Data Machine — a self-scheduling system that lets your agent set reminders, queue tasks, and operate 24/7 without human intervention.
- Yes (recommended for content sites) — Full autonomy, self-scheduling, proactive operation
- No (simpler setup) — Agent responds when asked, no self-scheduling overhead"
Question 3: Server Details
"I'll need some details about your server:
- What's the server IP address?
- Do you have SSH access? (key or password)
- What domain will this site use?"
Question 4: For Existing WordPress
If they chose existing WordPress:
"Where is WordPress installed on the server? (e.g.,
/var/www/mysite)"
Build the Command
Based on their answers, construct the appropriate command:
| Scenario | Command |
|---|---|
| Fresh + Data Machine | SITE_DOMAIN=example.com ./setup.sh |
| Fresh, no Data Machine | SITE_DOMAIN=example.com ./setup.sh --no-data-machine |
| Existing + Data Machine | EXISTING_WP=/var/www/mysite ./setup.sh --existing |
| Existing, no Data Machine | EXISTING_WP=/var/www/mysite ./setup.sh --existing --no-data-machine |
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 · 154 lines · 40 tokens per session scan B 0473e02e9cd4
wp-openclaw-setup is a skill published in the GitHub repository Sarai-Chinwag/wp-openclaw (63 stars, last pushed 8mo ago), licensed MIT. It adds 40 tokens to every session and 1,222 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
wp-openclaw-setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wp-openclaw-setupSarai-Chinwag/wp-openclaw | Skill | 63 | 8mo ago | MIT | B | 40 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 24k | today | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 24k | today | Apache-2.0 | A | 171 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 24k | today | Apache-2.0 | A | 85 | Claude Code, Codex |
| cloud-architectJeffallan/claude-skills | Skill | 12k | 10d ago | MIT | A | 71 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | today | Apache-2.0 | A | 30 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | today | MIT | A | 78 | Claude Code |