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-security-auditgit 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 | $0.00011 | $0.00494 |
| Opus 5 | $0.00005 | $0.00247 |
| Sonnet 5 | $0.00002 | $0.00099 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
wp-security-audit 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.
What it actually says
/wp-security-audit
Run a comprehensive security audit on the current WordPress project.
Instructions
Load the wordpress-security skill for security patterns and vulnerability identification.
Delegate the audit to the wp-security-auditor agent by using the Task tool with the following prompt:
"Perform a comprehensive WordPress security audit on the current project. Scan all PHP files and check for:
- Unescaped output —
echo $var,<?= $varwithoutesc_html/esc_attr/esc_url/wp_kses - Unsanitized input — Direct
$_GET/$_POST/$_REQUEST/$_SERVERwithoutsanitize_* - Missing nonces — Form/POST handling without
wp_verify_nonce/check_admin_referer - Raw SQL —
$wpdb->query()/$wpdb->get_*()without$wpdb->prepare() - Missing capability checks —
wp_ajax_/admin_post_handlers withoutcurrent_user_can() - Unsafe file operations —
file_get_contents($var)/include $varinstead of WP_Filesystem - Direct redirects —
header('Location:')instead ofwp_safe_redirect() - Direct JSON —
echo json_encode()instead ofwp_send_json_success/error() - Hardcoded credentials — API keys, passwords, secrets in source code
- Debug mode —
WP_DEBUGset totruein production configs - Directory traversal — Path manipulation without
realpath()validation - REST API auth — Endpoints with
__return_trueaspermission_callback
Output a structured report with:
- Severity levels: CRITICAL, WARNING, INFO
- File path and line number for each finding
- Description of the issue
- Suggested fix with code snippet
- Summary statistics (total findings by severity)
Sort findings by severity (CRITICAL first)."
After the agent completes, present the results to the user in a clear, organized format.
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 · 41 lines · 11 tokens per session scan A b6e0d4665f11
wp-security-audit is a command published in the GitHub repository iwritec0de/wp-dev (1 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 494 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.