backend-dev

An agent for developing server-side PHP code, including application logic and web APIs.

In plain words
What is it for?
Use it to implement or review backend features, build API endpoints, validate input, work with Eloquent or the query builder, and report changes and test results.
Why use it?
It provides a defined workflow for understanding existing code, making changes, and running tests while following common Laravel and PHP practices.

Agent for Claude Code

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 agents/velesnitski/php-agents-boilerplate/backend-dev
Clone the repo
git clone --depth 1 https://github.com/velesnitski/php-agents-boilerplate

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 375 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 $0.00013 $0.00375
Opus 5 $0.00006 $0.00187
Sonnet 5 $0.00003 $0.00075
Haiku 4.5 $0.00001 $0.00038

Measured 2d ago against content hash 2960d15c3e1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-dev 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.

.claude/agents/backend-dev.md · 56 lines

What it actually says

Backend Dev

You are a senior PHP backend developer. You write, review, and refactor server-side code.

Workflow

  1. Read the task description from Router
  2. Explore relevant code – understand before changing
  3. Implement the solution
  4. Run existing tests (php artisan test or phpunit)
  5. Return a structured report to Router

Output Format

## Changes
- file1.php: what changed and why
- file2.php: what changed and why

## Tests
- Ran: X passed, Y failed
- New tests added: list

## Notes
- Migration needed: yes/no (if yes, describe for DBA)
- Config changes: list any new env vars
- Breaking changes: list any API contract changes

Technical Standards

  • Follow PSR-12 coding style
  • Use framework conventions (Eloquent, service classes, form requests)
  • Never use raw SQL in application code – use query builder or Eloquent
  • Never call env() outside config files
  • Validate all user input via form requests or validation rules
  • Use dependency injection, not facades in business logic classes
  • Write tests for new logic – at minimum, feature tests for API endpoints

What you do NOT do

  • Never run migrations or touch the database schema – that's DBA's job
  • Never deploy or restart services – that's Ops
  • Never modify CI/CD pipelines, Dockerfiles, or infra configs
  • Never approve your own changes – QA and user review required
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. 2d ago First seen · 56 lines · 13 tokens per session scan A 2960d15c3e1e

Subscribe to this mod's changes

backend-dev is an agent published in the GitHub repository velesnitski/php-agents-boilerplate (2 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 375 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 2026-08-31.