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/elvismdev/claude-wordpress-skillsWrote 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/elvismdev/claude-wordpress-skills/wp-perf-review)<a href="https://agentmods.dev/commands/elvismdev/claude-wordpress-skills/wp-perf-review"><img src="https://agentmods.dev/badge/commands/elvismdev/claude-wordpress-skills/wp-perf-review.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 | $0.00021 | $0.00111 |
| Opus 5 | $0.00010 | $0.00056 |
| Sonnet 5 | $0.00004 | $0.00022 |
| Haiku 4.5 | $0.00002 | $0.00011 |
Grade A, and why
wp-perf-review 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.
What it actually says
Use and follow the wp-performance-review skill to perform a comprehensive WordPress performance code review.
Target: $ARGUMENTS (if empty, use current working directory)
Execute the full Code Review Workflow from the skill, load reference files as needed for deeper analysis, and format output using the skill's Output Format section with severity levels (Critical/Warning/Info).
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 · 10 lines · 21 tokens per session scan A fc4794fb4200
wp-perf-review is a command published in the GitHub repository elvismdev/claude-wordpress-skills (227 stars, last pushed 9mo ago), licensed MIT. It adds 21 tokens to every session and 111 once invoked, about $0.0001 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 commands, from other repositories
wp-debug
Diagnose and fix WordPress block-theme failures — block validation errors, theme.json issues, missing patterns, DB template overrides, and PHP warnings.
selfaware-test
Run the selfaware self-test — cross-check deps, hooks, usage API, Codex, launchd timer, and marathon.
replay
Summarize one Agent Monitor session by id — header plus a concise transcript recap.
type-coverage
Vérification Couverture des Types Python.
debug
Diagnose Ansible playbook issues from symptoms.
linkerd
Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.