craft-feature-builder

craft-feature-builder is an agent for Claude Code from michtio/craftcms-claude-skills. It costs 15 tokens per session (3,500 once invoked), scanned A, original, MIT.

A coding agent for building new features in Craft CMS plugins, which are add-ons that extend the content-management system.

In plain words
What is it for?
Use it to implement planned plugin features, write production PHP code, run project-approved tools through DDEV, and apply code standards to changed files.
Why use it?
It keeps implementation work aligned with the project's architecture, development environment, coding rules, and checks.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/Shared/dev/craft-plugins/....

Part of the craftcms-claude-skills plugin — 13 skills, 6 agents shipped together

Good fit Use it to implement planned plugin features, write production PHP code, run project-approved tools through DDEV, and apply code standards to changed files.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add michtio/craftcms-claude-skills
Claude Code
/plugin install craftcms-claude-skills

Made for: Claude Code.

Or install craftcms-claude-skills, the plugin that ships this one along with the rest of its 13 skills, 6 agents.

Wrote 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.

agentmods badge for craft-feature-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/michtio/craftcms-claude-skills/craft-feature-builder/github.svg)](https://agentmods.dev/agents/michtio/craftcms-claude-skills/craft-feature-builder)
Your own site
<a href="https://agentmods.dev/agents/michtio/craftcms-claude-skills/craft-feature-builder"><img src="https://agentmods.dev/badge/agents/michtio/craftcms-claude-skills/craft-feature-builder/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.

agentmods 80×15 button for craft-feature-builder

Your own site · 80×15
<a href="https://agentmods.dev/agents/michtio/craftcms-claude-skills/craft-feature-builder"><img src="https://agentmods.dev/badge/agents/michtio/craftcms-claude-skills/craft-feature-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00015 $0.03500
Opus 5 $0.00008 $0.01750
Sonnet 5 $0.00003 $0.00700
Haiku 4.5 $0.00002 $0.00350

Measured 10d ago against content hash eaad3aac4eff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

craft-feature-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 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.

agents/craft-feature-builder.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Craft CMS plugin developer. You receive implementation plans and write production-quality code following the craft-php-guidelines and all project rules.

Environment rules

  • Paths: Always work in cms/vendor/{vendor}/{plugin}/ (the symlinked path), never absolute source paths like /Users/Shared/dev/craft-plugins/....
  • DDEV only: Never run php, composer, npm, or vendor/bin/pest on the host. Use ddev composer, ddev craft, ddev npm, or ddev exec for everything.
  • ECS scope: When running ECS --fix, scope to changed files only (git diff --name-only | grep '\.php$'). Never run --fix across the full project without explicit approval.
  • Dedicated tools over Bash: Use Grep instead of grep, rg, or find | xargs grep for searching file contents. Use Glob instead of find for finding files by pattern. Use Read instead of cat or head for reading file contents. Never use cd path && command — use absolute paths. For git in other directories, use git -C /path instead of cd /path && git. Never use rm to delete files — ask the user. Quick ls to inspect a directory and readlink for symlinks are fine — but ls | grep to search is not (use Glob). tail -n on storage/logs/ is fine for log inspection but not for reading source files (use Read with offset/limit).
  • Token efficiency: Read reference files only when you need specific API details for the layer you're building. Don't front-load all references — read the elements.md reference when building an element type, not when writing a migration. Load craft-garnish only when building CP JavaScript, not for every feature. Use Read with offset/limit on large files instead of reading the whole thing.
  • Output density: Keep prose between code blocks minimal — the code IS the deliverable. Gate results in one line: [PASS] migration — schema exists / [FAIL] model — defineRules missing. No preamble ("Let me now..."), no recap of what was just done, no restating the plan. When reporting verification results, use a compact table or one-liner-per-gate, not paragraphs.

Read the full file on GitHub · 165 lines

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. 10d ago First seen · 165 lines · 15 tokens per session scan A eaad3aac4eff

Subscribe to this mod's changes

craft-feature-builder is an agent published in the GitHub repository michtio/craftcms-claude-skills (78 stars, last pushed 7d ago), licensed MIT. It adds 15 tokens to every session and 3,500 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 2026-08-30.

Related

Other agents, from other repositories

ash-resource-designer

Ash resource architect — designs resources the "Ash Way" with built-in changes, validations, types, and policy checks before hand-rolling. Use proactively when planning new resources or extending existing ones.

oliver-kriska/claude-elixir-phoenix · 44 tokens

parallel-reviewer

Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.

oliver-kriska/claude-elixir-phoenix · 38 tokens

workflow-orchestrator

Orchestrates the full agentic workflow cycle (plan → work → review). Internal use by /phx:full command.

oliver-kriska/claude-elixir-phoenix · 31 tokens

catchup-runner

Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.

oliver-kriska/claude-elixir-phoenix · 63 tokens

ash-policy-reviewer

Ash policy security reviewer — audits policies, checks, and authorization rules for gaps, bypass patterns, and ordering hazards. Use proactively on Ash resources with policies do blocks or checks/ modules.

oliver-kriska/claude-elixir-phoenix · 42 tokens

deep-bug-investigator

Deep bug investigation using 4 parallel subagents (reproduction, root cause, impact, fix strategy). Use when bug is complex, can't be reproduced locally, or needs thorough analysis. Spawns fresh-context subagents for each investigation track.

oliver-kriska/claude-elixir-phoenix · 54 tokens