symfony-engineer

symfony-engineer is an agent for Claude Code from dev-toolings/superpowers-symfony. It costs 76 tokens per session (875 once invoked), scanned A, original, MIT.

A Symfony coding assistant for building and improving PHP web applications. Symfony is a PHP framework; the assistant follows project conventions and uses focused guidance for controllers, services, forms, configuration, and related code.

In plain words
What is it for?
Use it to implement or refactor Symfony controllers, services, dependency injection, value objects, data-transfer objects, forms, validation, Twig components, configuration, and environment settings.
Why use it?
It reduces the need to decide implementation patterns from scratch and helps keep changes consistent with the project's Symfony version and structure. It can also direct specialized API, security, database, or messaging work to the right approach.

Agent for Claude Code

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

Part of the superpowers-symfony plugin — 44 skills, 13 commands, 7 agents, 1 hook shipped together

Good fit Use it to implement or refactor Symfony controllers, services, dependency injection, value objects, data-transfer objects, forms, validation, Twig components, configuration, and environment settings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dev-toolings/superpowers-symfony/symfony-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/dev-toolings/superpowers-symfony

Made for: Claude Code.

Or install superpowers-symfony, the plugin that ships this one along with the rest of its 44 skills, 13 commands, 7 agents, 1 hook.

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 symfony-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dev-toolings/superpowers-symfony/symfony-engineer/github.svg)](https://agentmods.dev/agents/dev-toolings/superpowers-symfony/symfony-engineer)
Your own site
<a href="https://agentmods.dev/agents/dev-toolings/superpowers-symfony/symfony-engineer"><img src="https://agentmods.dev/badge/agents/dev-toolings/superpowers-symfony/symfony-engineer/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 symfony-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/dev-toolings/superpowers-symfony/symfony-engineer"><img src="https://agentmods.dev/badge/agents/dev-toolings/superpowers-symfony/symfony-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 875 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 $0.00076 $0.00875
Opus 5.5 $0.00030 $0.00350
Sonnet 5.5 $0.00015 $0.00175
Haiku 4.5 $0.00008 $0.00088

Measured 1mo ago against content hash 6880e7363fde, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

symfony-engineer 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 1mo 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.

content/agents/symfony-engineer.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Symfony engineer. You implement features the idiomatic, best-practice way, leaning on the superpowers-symfony skill library instead of reinventing patterns.

First steps

  1. Read the SessionStart context (or composer.lock) to pin the Symfony version (7.4 LTS / 8.x; 6.4 legacy) and the runner (host vs docker compose exec vs ddev). Use the detected commands — never assume.
  2. Scan the relevant area of src/ to match existing structure, naming, and conventions before writing anything.
  3. Consult the matching skill before implementing. Map the task to a symfony:* skill (see skills-map-lite.md) and follow its reference. Examples:
    • controllers/refactor → symfony:controller-cleanup
    • services/DI/interfaces → symfony:interfaces-and-autowiring
    • domain types → symfony:value-objects-and-dtos
    • forms/validation → symfony:form-types-validation
    • config/env/secrets → symfony:config-env-parameters
    • async, cache, security, doctrine, API → defer to the specialized agent or its skill.

Workflow

  1. Restate the goal as a verifiable outcome; state assumptions; flag a simpler approach if one exists.
  2. Implement the minimum code that satisfies it — no speculative abstractions or config.
  3. Apply Symfony best practices as you go (see Rules).
  4. Run quality gates and report results.

Rules (Symfony best practices)

  • Thin controllers: no business logic, no direct Doctrine queries — delegate to services/handlers. Use argument injection and attributes (#[Route], #[CurrentUser], EntityValueResolver), never $this->container->get().
  • Services private + autowired; depend on interfaces; use #[Target] to disambiguate implementations (param-name aliasing is deprecated).
  • Immutability: readonly value objects/DTOs (PHP 8.2+); validation constraints on the underlying objects, not form fields.
  • Config: env vars for infra, secrets vault for sensitive data, app.-prefixed parameters for behavior; assets via AssetMapper.
  • Surgical changes: touch only what the task requires; match surrounding style; remove only orphans your change creates.
  • Never invent an API or signature — trace it to a skill reference or the official docs.
  • Defer, don't overlap: for API Platform resources, Doctrine schema design, or test-first work, hand off to api-platform-builder / doctrine-architect / symfony-tdd-coach.

Read the full file on GitHub · 72 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. 1mo ago Changed · +8 lines 6880e7363fde
  2. 1mo ago First seen · 64 lines · 76 tokens per session scan A e856a4804dad

Subscribe to this mod's changes

symfony-engineer is an agent published in the GitHub repository dev-toolings/superpowers-symfony (224 stars, last pushed 14d ago), licensed MIT. It adds 76 tokens to every session and 875 once invoked, about $0.0003 per session on Opus 5.5. 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

laravel-architect

Laravel 10+ architecture specialist. Validates Controller/Service/Repository/Model layering, Request validation discipline, Resource API responses, and Facade vs. class injection. Dispatch when touching controllers, services, repositories, or models.

onlygian/G-Forge · 51 tokens

api-platform-implementer

Implements the architect's plan in the repository (Dev stage). Reads .claude/last-api-plan.md first. Detects the API Platform area, dispatches the right gerard: skills (or : overrides), writes the code (resource + DTO/Object Mapper + provider/processor + filters + tests), iterates phpunit + phpstan until green, runs…

gerard-labs/superpowers-api-platform · 139 tokens

php-expert

Specialized in developing efficient, secure, and modern PHP applications adhering to best practices.

andisab/swe-marketplace · 21 tokens

typescript-expert

Use this agent when you need expert TypeScript development with focus on type safety, advanced type system features, and modern ES patterns. This agent specializes in TypeScript 5.7+, strict type checking, generics, and type-level programming for building robust, maintainable applications. Examples: Context: User…

andisab/swe-marketplace · 408 tokens

python-expert

Use this agent when you need expert Python development with focus on modern async programming, type safety, and architectural patterns. This agent specializes in FastAPI, Pydantic, SQLAlchemy 2.0, and advanced Python features including async/await, type hints, protocols, and class composition patterns. Examples…

andisab/swe-marketplace · 446 tokens

port

SDK design — multi-language SDK architecture, idiomatic patterns, and cross-language consistency.

tonone-ai/tonone · 18 tokens