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 dr-robert-li/cowork-wordpress-expert --skill diagnostic-architecturegit clone --depth 1 https://github.com/dr-robert-li/cowork-wordpress-expertWrote 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/dr-robert-li/cowork-wordpress-expert/diagnostic-architecture)<a href="https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/diagnostic-architecture"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/diagnostic-architecture/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/dr-robert-li/cowork-wordpress-expert/diagnostic-architecture"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/diagnostic-architecture.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 | $0.00081 | $0.07965 |
| Opus 5.5 | $0.00032 | $0.03186 |
| Sonnet 5.5 | $0.00016 | $0.01593 |
| Haiku 4.5 | $0.00008 | $0.00796 |
Grade A, and why
diagnostic-architecture 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 1mo 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 — 587 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnostic Skill: Architecture Review
You analyze a WordPress site's architecture for slow-burn structural problems that compound over time: custom post types used incorrectly, hooks overloaded with too many callbacks, and caching patterns that bypass available caching infrastructure.
Why Architecture Issues Matter
Architecture issues are slow-burn problems — individually small, collectively severe:
- CPT misuse — A CPT used as a data store with 50,000 rows breaks pagination, export tools, and WordPress admin. A dead CPT (registered but never used) consumes memory on every request as WordPress bootstraps its registration, labels, and admin columns regardless.
- Hook abuse — Fifty callbacks on 'init' delay every page load. Expensive operations (database queries, HTTP requests) registered on early hooks run before the first line of template code executes.
- Missing object cache — Without a persistent object cache, every repeat lookup hits MySQL. On a site with 100 concurrent users, this means 100 identical SELECT queries instead of 1 cache hit.
- Permanent transients — Using
set_transient()with 0 expiry treats the transient as permanent storage, polluting the options table with data that should be in a custom DB table or autoloaded option.
This skill surfaces these patterns early, before they become expensive refactors.
Independent Gating Architecture
This skill has three independently-gated sections:
- Part A (CPT misuse): Requires
WP_CLI_AVAILABLE=true. If unavailable, emits one Info skip finding and continues to Part B. - Part B (hook abuse): Always runs — pure static grep on synced PHP files. No WP-CLI required.
- Part C (caching anti-patterns): Mixed — uses WP-CLI for cache type detection if available, falls back to file check. grep for code patterns always runs.
This skill is NOT in the WP_CLI_SKILLS array — it manages its own gating internally because Parts B and C run independently of WP-CLI availability.
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.
- 1mo ago First seen · 587 lines · 81 tokens per session scan A 282d701c7ee2
diagnostic-architecture is a skill published in the GitHub repository dr-robert-li/cowork-wordpress-expert (29 stars, last pushed 8mo ago), licensed MIT. It adds 81 tokens to every session and 7,965 once invoked, about $0.0003 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.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…