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 Lonsdale201/wp-agent-skills --skill wc-action-scheduler-jobsgit clone --depth 1 https://github.com/Lonsdale201/wp-agent-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/skills/lonsdale201/wp-agent-skills/wc-action-scheduler-jobs)<a href="https://agentmods.dev/skills/lonsdale201/wp-agent-skills/wc-action-scheduler-jobs"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/wc-action-scheduler-jobs/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/lonsdale201/wp-agent-skills/wc-action-scheduler-jobs"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/wc-action-scheduler-jobs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 221 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00122 | $0.03582 |
| Opus 5 | $0.00061 | $0.01791 |
| Sonnet 5 | $0.00024 | $0.00716 |
| Haiku 4.5 | $0.00012 | $0.00358 |
Grade A, and why
wc-action-scheduler-jobs 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WooCommerce Action Scheduler jobs
Action Scheduler is bundled with WooCommerce and is the right tool for background work: order sync, product imports, webhooks, retries, batch recalculation, export jobs, and recurring maintenance.
Use it instead of doing slow work during checkout, order status hooks, admin saves, or frontend requests.
Misconception this skill corrects
"I will pass
$unique = true, so this side effect can happen exactly once."
WooCommerce 11.0 bundles Action Scheduler 4.0. Its DB store suppresses a unique insert only when a pending/running action has the same hook + group + encoded args. Jobs for order 10 and order 11 no longer block each other merely because they share a hook and group.
This is queue-entry deduplication, not exactly-once execution. A job can be manually re-created, retried, replayed after a restored backup, or finish its remote side effect before its local state is saved. Keep the callback idempotent and use a durable owned claim/provider idempotency key when duplicate business effects are unacceptable.
Treat $unique identity as active-version/store-specific. Action Scheduler 3.x DBStore used only hook and group; 4.0 adds args. Confirm the loaded version, source, and data store when another plugin can bundle its own copy. For a plugin supporting mixed 3.x/4.x runtimes, use exact as_has_scheduled_action() checks as a compatibility guard and still rely on callback idempotency for correctness.
"Exact args" means the same JSON representation. Associative key insertion order and scalar types matter: array( 'id' => 1, 'mode' => 'full' ) does not match reversed keys, and integer 1 does not match string '1'.
When to use this skill
Trigger when ANY of the following is true:
- Moving slow work out of checkout, webhooks, admin saves, or order status hooks.
- Scheduling order/customer/product sync jobs.
- Running imports, exports, cleanup, reindexing, or recurring maintenance.
- Avoiding duplicate background jobs.
- The diff contains
as_enqueue_async_action,as_schedule_single_action,as_schedule_recurring_action,as_schedule_cron_action,as_has_scheduled_action,as_next_scheduled_action,as_unschedule_action, orActionScheduler.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -1 lines d8f657c148a6
- 9d ago First seen · 263 lines · 122 tokens per session scan A b91161c103e7
wc-action-scheduler-jobs is a skill published in the GitHub repository Lonsdale201/wp-agent-skills (22 stars, last pushed 2d ago), licensed MIT. It adds 122 tokens to every session and 3,582 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
commerce-app-business-config
Manage custom business configuration in an Adobe Commerce app. Use when the user wants to add, modify, or remove merchant-configurable settings (config fields, admin config, store configuration) exposed through Commerce Admin. Creates typed config fields (text, password, email, url, tel, boolean, list) in…
muapi-amazon-product-listing
Generate a complete Amazon product listing image set — hero image, lifestyle shot, infographic with features, and comparison/detail closeups optimized for Amazon standards.
muapi-multi-angle-shots
Generate a complete set of multi-angle product shots — front, side, back, top-down, and 45-degree perspective — for comprehensive product visualization.
menu-engineer
Optimize menu pricing, placement, and item mix to maximize profitability. Uses menu engineering frameworks to analyze item performance by popularity and margin, then recommends pricing tweaks, repositioning, and removals.
price-scout
Track and compare supplier prices across multiple vendors to reduce COGS. Monitors price changes, identifies savings opportunities, calculates total cost of ownership (including delivery fees and minimums), and generates renegotiation briefs.
table-manager
Optimize table turns, manage reservations, and reduce wait times to maximize revenue per seat. Handles booking intake, table assignment strategy, waitlist management, and provides actionable insights for seating efficiency.