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 bd-presentergit 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/bd-presenter)<a href="https://agentmods.dev/skills/lonsdale201/wp-agent-skills/bd-presenter"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/bd-presenter/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/bd-presenter"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/bd-presenter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00193 | $0.03917 |
| Opus 5 | $0.00097 | $0.01959 |
| Sonnet 5 | $0.00039 | $0.00783 |
| Haiku 4.5 | $0.00019 | $0.00392 |
Grade A, and why
bd-presenter 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 10d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
better-data: Extending the Presenter
For library maintainers adding output transformations to the better-data Presenter — a new fluent builder method (mask, formatPhone, hideIfBlank), a PresentationContext flag (admin vs REST vs export), or a Formatter helper. The Presenter is the read-side projection layer between a DataObject and whatever consumes it (admin UI, REST response, audit log).
Misconception this skill corrects
"The Presenter is
readonlylike the DataObject — every fluent method must clone and return a new instance."
Wrong. The DataObject is readonly, the Presenter is intentionally a mutable builder. Look at src/Presenter/Presenter.php:65-89 — class Presenter (not final readonly class), with private mutable properties $only, $hidden, $rename, $computed, $presets, $includeSensitive. Each fluent method assigns to $this->... and returns $this. This is deliberate — chained calls share state, repeated calls override, and there's no clone overhead.
What IS immutable: $this->dto is protected readonly DataObject and never gets reassigned. The builder mutates ITS state to control HOW the DTO is rendered; the DTO itself stays untouched.
The "don't mutate permanently" rule from older docs means: don't introduce a method whose effect can't be reset by a subsequent method or context swap. A method that pushes to a private array is fine; a method that writes to a static cache or to the wrapped DTO would be a regression.
Other AI-prone misconceptions:
- "I'll add
getSecretRevealed()so consumers don't need->reveal()boilerplate." Wrong — the explicit$dto->field->reveal()inside acompute()closure IS the security audit point. Adding a bypass method is the same regression as a debug-mode log of secrets. - "CollectionPresenter is a separate Presenter; I just add the method there too with copy/paste logic." Wrong —
CollectionPresenterrecords each configurer as a closure on$this->configurers(src/Presenter/CollectionPresenter.php:30-44) and replays it on every item via the per-item Presenter. The pattern is$this->configurers[] = static fn (Presenter $p) => $p->yourMethod(...);. No business logic on the collection side.
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.
- 10d ago First seen · 324 lines · 193 tokens per session scan A 6d30fdb9ad74
bd-presenter is a skill published in the GitHub repository Lonsdale201/wp-agent-skills (22 stars, last pushed 11d ago), licensed MIT. It adds 193 tokens to every session and 3,917 once invoked, about $0.0010 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 skills, from other repositories
wp-plugin-development
Architecture and development guidelines for WordPress plugins published on wordpress.org: file structure, plugin header, lifecycle hooks, Settings API, admin UI, escaping helpers for admin JavaScript, default values and option migrations, multisite-shared resources, custom post types, custom database tables…
wp-plugin-performance
Performance guidelines for WordPress plugin development: database optimization, object caching, conditional asset loading, efficient hooks, HTTP requests, WP-Cron, AJAX/REST optimization, and common anti-patterns. Based on official WordPress Developer Resources and WP VIP documentation.
build-mcp-server
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates…
data-manager-api-setup
Guides developers through client library installation and authentication setup steps for the Data Manager API. Use this skill when a user is getting started with the Data Manager API and needs to setup their local environment, install the client library, or setup access to the API. Don't use for implementing audience…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
new
Create a new project to start development quickly.