agentmods.dev

bricks-builder

A working guide for researching, building, changing, and reviewing websites made with Bricks Builder, a WordPress visual site builder. It uses Bricks documentation and an authorized live installation to check version-sensitive behavior.

In plain words
What is it for?
Use it when working with Bricks elements, controls, schemas, hooks, settings, or custom code in a child theme or plugin.
Why use it?
It helps agents follow supported Bricks workflows and avoid changing the parent theme directly.

Skill for Claude CodeCodex

40 10d ago A scan 123 tokens original MIT
View the source file kenming/bricks-builder-skill
Install

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.

agentmods
npx agentmods add skills/kenming/bricks-builder-skill/bricks-builder
Any agent
npx skills add kenming/bricks-builder-skill --skill bricks-builder
Clone the repo
git clone --depth 1 https://github.com/kenming/bricks-builder-skill

Made for: Claude Code, Codex.

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 881 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00123 $0.00881
Opus 5 $0.00062 $0.00441
Sonnet 5 $0.00025 $0.00176
Haiku 4.5 $0.00012 $0.00088

Measured 3d ago against content hash 3a81cae5f8c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bricks-builder 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 3d 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.

skills/bricks-builder/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bricks Builder

Treat the bundled Academy corpus as the public documentation layer, the hand-written references as development guidance, and the user's authorized active installation as the final source for version-sensitive implementation facts.

Never edit the Bricks parent theme. Put custom code in an active child theme or plugin.

Route the task

Documentation lookup

For feature behavior, official setup, public hooks, schemas, and supported workflows:

  1. Run scripts/search_corpus.py "<query>".
  2. Open 1 to 3 high-signal results with scripts/show_doc.py <path-or-doc-id>.
  3. Prefer hook, element, schema, or control results for exact APIs; prefer guide results for concepts and UI workflows.
  4. Browse the official Academy site only when the local corpus is missing, stale, or the user requests current online verification.

Read references/query-workflow.md for search details and references/corpus-layout.md for corpus organization.

Development implementation

For building or modifying Bricks content or code:

  1. Read only the task-relevant development reference below.
  2. Search the Academy corpus for the related public contract.
  3. Detect the active Bricks version before relying on internal keys, signatures, paths, or storage shapes.
  4. Inspect the smallest relevant part of the authorized active theme or live WordPress state when available.
  5. Implement outside the parent theme and validate in both the builder and frontend.

Version-sensitive verification

Treat exact element names, control keys, hook arguments, JSON shapes, option/meta keys, internal classes, and version availability as version-sensitive.

  • Prefer the active installation for claims about that installation.
  • Cross-check the matching Academy schema or guide where possible.
  • State the verified Bricks version when the answer or change depends on it.
  • If no authorized installation is available, use public documentation and clearly identify unverified internal details.
  • Never publish licensed source, credentials, private site data, or a developer's absolute local path.

Read the full file on GitHub · 78 lines

Files

What ships with it

60 files 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.

Changes

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.

  1. 3d ago First seen · 78 lines · 123 tokens per session scan A 3a81cae5f8c3

Subscribe to this mod's changes

bricks-builder is a skill published in the GitHub repository kenming/bricks-builder-skill (40 stars, last pushed 10d ago), licensed MIT. It adds 123 tokens to every session and 881 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 2026-08-30.

Frontendagent-skillai-toolsbricks-builderdocumentationlocal-searchmarkdown
Related

Other skills, from other repositories

format-markdown

Formats Markdown files consistently using project-native tooling first (repo scripts/config), then safe fallback formatters, and verifies the result with lint/check commands. Invoked when the user asks to format markdown, tidy docs, normalize README files, or fix markdown style drift.

soulcodex/agentic · 56 tokens

memory-watchdog

This Skill is the runtime prompt for the repo hygiene auditor. The persona, voice, and aggression-level dial live in architecture/memory/watchdog-persona.md — load that first if you are adopting the Watchdog role. The concept lives in architecture/memory/memory-watchdog.md. This Skill carries the operational pass…

VolcanoEngineering/Bamboo · 43 tokens

memory-context

This Skill is for keeping the project memory usable.

VolcanoEngineering/Bamboo · 45 tokens

repo-cognition

This skill establishes operational rules and retrieval systems for AI-assisted repositories. This skill specifically is part of the Bamboo.md Repository and should adhere to its rules and guidelines. But, can be incorperated into other repositories and systems in part.

VolcanoEngineering/Bamboo · 66 tokens

golden-chat

Use when testing the goldenchat golden build.

yusufkaraaslan/Skill_Seekers · 12 tokens

golden-epub

Use when testing the epub golden build.

yusufkaraaslan/Skill_Seekers · 13 tokens