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/iwritec0de/wp-dev/wp-perfgit clone --depth 1 https://github.com/iwritec0de/wp-devWhat 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 | $0.00014 | $0.00866 |
| Opus 5 | $0.00007 | $0.00433 |
| Sonnet 5 | $0.00003 | $0.00173 |
| Haiku 4.5 | $0.00001 | $0.00087 |
Grade A, and why
wp-perf 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 yesterday.
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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wp-perf
Run live performance diagnostics on a connected WordPress site.
Skills
Load the wordpress-performance and wordpress-database skills for optimization patterns and query analysis.
Prerequisites
- WordPress MCP adapter must be connected (check with
/mcp) - For full diagnostics, the Performance Monitor mu-plugin should be installed on the target site
- Generate the mu-plugin with:
/wp-scaffold perf-monitor
Usage
/wp-perf [section]
- No argument: runs all diagnostic sections
- With section: runs only that section (
queries,autoload,transients,hooks,overview)
Instructions
Step 1: Check MCP Connection
Verify the WordPress MCP adapter is available. If not connected, inform the user:
"The WordPress MCP adapter is not connected. Set up WP_SITE_URL, WP_USERNAME, and WP_APPLICATION_PASSWORD environment variables, then restart the session."
Step 2: Check for Performance Monitor Endpoints
Try to reach the performance monitor endpoints via the MCP adapter:
GET /wp-json/wp-perf/v1/overview
If the endpoint returns a 404, the mu-plugin is not installed. Inform the user:
"The Performance Monitor mu-plugin is not installed on this site. Generate it with /wp-scaffold perf-monitor and upload wp-perf-monitor.php to wp-content/mu-plugins/ on the target site."
Fall back to what's available without the mu-plugin (basic REST API data, WP-CLI if available).
Step 3: Run Diagnostics
Pull data from the performance monitor endpoints and format a report:
Overview (/wp-perf/v1/overview)
- PHP version and memory limit
- MySQL version
- Object cache status (active, type)
- Total options count and autoload size
- Active plugin count
- WordPress and WooCommerce versions
Queries (/wp-perf/v1/queries)
- Total query count for a sample page load
- Top 10 slowest queries with timing and caller
- Duplicate queries
- Queries by component (plugin/theme/core)
Autoload (/wp-perf/v1/autoload)
- Total autoloaded data size
- Top 20 largest autoloaded options
- Autoloaded transients (should be 0)
- Recommendations for options to set as non-autoloaded
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.
- yesterday First seen · 115 lines · 14 tokens per session scan A 954ad8c70c66
wp-perf is a command published in the GitHub repository iwritec0de/wp-dev (1 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 866 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 2026-08-31.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.