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 wp-batch-mutation-auditgit 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/wp-batch-mutation-audit)<a href="https://agentmods.dev/skills/lonsdale201/wp-agent-skills/wp-batch-mutation-audit"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/wp-batch-mutation-audit/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/wp-batch-mutation-audit"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/wp-batch-mutation-audit.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 | $0.00116 | $0.01890 |
| Opus 5 | $0.00058 | $0.00945 |
| Sonnet 5 | $0.00023 | $0.00378 |
| Haiku 4.5 | $0.00012 | $0.00189 |
Grade A, and why
wp-batch-mutation-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 2d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WordPress batch mutation audit
Review the correctness boundary of work split across requests or workers. Treat "the request returned success" and "the intended dataset reached the intended state exactly once" as different claims. Do not use this skill for read-only pagination; use it when rows, files, remote systems, or durable state change.
Audit workflow
- Identify the unit of work: object ID, meta ID, custom-table primary key, file, remote delivery, or immutable snapshot row.
- Trace selection, mutation, progress persistence, response, retry, and cleanup.
- Model a timeout before commit, after commit but before response, and halfway through a batch.
- Model two tabs, two admins, cron overlap, and a manual retry running together.
- Verify every mutation result and distinguish no-op from failure.
- Report the final-state invariant, not only individual code smells.
Critical checks
1. Lost-response ambiguity
Assume the server can commit a batch while the client receives a timeout. A browser-local offset does not prove whether that batch ran.
Flag a multi-request mutation when retry starts from zero and the operation is
not naturally idempotent. Search/replace is not idempotent when replacement can
match the search again: a -> aa becomes a -> aa -> aaaa on replay.
Require a durable operation record containing:
- immutable parameters and initiator;
- status (
pending,running,completed,failed,cancelled); - cursor or target snapshot;
- processed/failed counts and last error;
- timestamps and a lease/heartbeat when workers can die.
An idempotency key deduplicates operation creation. It does not by itself make each row mutation replay-safe.
2. Cursor stability
Flag mutation loops that page with increasing OFFSET over a set whose
membership can change:
SELECT id FROM table
WHERE status = 'pending'
ORDER BY id
LIMIT 100 OFFSET 500;
Deleting or changing an earlier matching row shifts later offsets and can skip work. Concurrent inserts can repeat work. Prefer keyset pagination:
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.
- 2d ago First seen · 214 lines · 116 tokens per session scan A 59ebf2301564
wp-batch-mutation-audit is a skill published in the GitHub repository Lonsdale201/wp-agent-skills (22 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 1,890 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 2026-09-11.
Other skills, from other repositories
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
comet-hotfix
A quick workflow for fixing an existing bug in Comet, a tool that manages structured code changes. It moves through opening the change, building, checking, and archiving it.
comet-hotfix
Comet preset path: Bug fix / hotfix. Skip brainstorming, directly open → build → verify → archive. Applicable for behavior fixes, scenarios not involving new capability design.
comet-github-issue-fix
A workflow for fixing a confirmed Comet-related GitHub issue or review blocker within an isolated scope. It covers matching the work to the relevant workflow, testing the change, checking runtime results, and preparing a careful handoff.