What is php-agents-boilerplate CLAUDE.md?

A set of instructions for a team of coding agents that handles PHP backend work, databases, operations, and testing.

Use it for PHP code and APIs, database schemas and migrations, deployment and monitoring, and quality checks.

It routes each request to the appropriate specialist and records their work in shared task files, reducing the need to coordinate every step yourself.

How velesnitski/php-agents-boilerplate configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to velesnitski/php-agents-boilerplate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/velesnitski/php-agents-boilerplate/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/velesnitski/php-agents-boilerplate

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/velesnitski/php-agents-boilerplate/claude-md/github.svg)](https://agentmods.dev/instructions/velesnitski/php-agents-boilerplate/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/velesnitski/php-agents-boilerplate/claude-md"><img src="https://agentmods.dev/badge/instructions/velesnitski/php-agents-boilerplate/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/velesnitski/php-agents-boilerplate/claude-md"><img src="https://agentmods.dev/badge/instructions/velesnitski/php-agents-boilerplate/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 896 This file is loaded in full into every session.

When invoked 896 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00896	$0.00896
Opus 5.5	$0.00358	$0.00358
Sonnet 5.5	$0.00179	$0.00179
Haiku 4.5	$0.00090	$0.00090

Measured 11d ago against content hash f6936d0272d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

php-agents-boilerplate CLAUDE.md 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 11d 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.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PHP Team Agent System

Multi-agent system for PHP backend development, database management, and operations.

Default Behavior

Always use the router agent to handle user tasks. Do not work on tasks directly – dispatch everything via Router. The Router will classify the task and chain the right specialist agents.

Quick Start

Just describe your task naturally:

> Add a paginated endpoint for user activity logs

The Router will automatically classify it, pick the workflow, and dispatch to the right agents.

Agents

Agent	Model	Role
`router`	haiku	Task dispatcher and orchestrator
`backend-dev`	opus	PHP code, APIs, business logic
`dba`	opus	Schema, migrations, query optimization
`ops`	sonnet	Deploy, infra, monitoring
`qa`	haiku	Testing and verification

Routing Paths

Complex: DBA (if schema) → Backend Dev → QA → User review → Ops (deploy)
Simple: Backend Dev → QA → User review → Ops
DB-only: DBA → User confirmation
Ops-only: Ops → Verify

Task State Files

Each task creates .tasks/YYMMDD-HHMM-slug.md – agents append their sections sequentially. This preserves original outputs and avoids information loss.

Rules

Destructive operations, deploys and non-local migrations are blocked by .claude/hooks/guard.sh until a person runs scripts/approve.sh <category> <proposal> (15-minute approval, one category)
Every change gets a risk tier (scripts/risk-tier.mjs): high needs two human approvals, medium one, low none; an automated review never counts as a person
Edits are formatted by Pint through the PostToolUse hook; agents do not spend turns on style
Agents stay within their scope – see "What you do NOT do" in each agent
All bash commands should use rtk proxy when available for token savings
Every architectural decision must include an ADR in docs/adr/

Skills

Skill	Used by	Purpose
`work-conventions`	all agents	Git, code style, ADR, sensitive data rules
`php-stack`	backend-dev	Laravel 11 / PHP 8.2 structure, patterns, tooling
`testing-strategy`	backend-dev, qa	PHPUnit conventions, feature vs unit, coverage
`db-operations`	dba	Migration safety, optimization, backups
`docker-workflow`	ops	Docker Compose, Makefile, deploy, rollback
`server-infra`	ops	Docker services, logs, health checks
`adr-documentation`	all agents	When and how to write ADRs
`repository-pattern`	on-demand	Contracts + repositories (loaded when needed)

Read the full file on GitHub · 80 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.

11d ago Changed · +11 lines · +256 tokens per session f6936d0272d1
2mo ago First seen · 69 lines · 640 tokens per session scan A fc1c9c7785bb

Subscribe to this mod's changes

php-agents-boilerplate CLAUDE.md is an instructions file published in the GitHub repository velesnitski/php-agents-boilerplate (2 stars, last pushed 11d ago), licensed MIT. It adds 896 tokens to every session, about $0.0036 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 2026-08-31.

Backend and APIs Languages PHP

php-agents-boilerplate CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
php-agents-boilerplate CLAUDE.mdvelesnitski/php-agents-boilerplate	Instructions file	2	11d ago	MIT	A	896	Claude Code
graftcode graftcode-php.instructions.mdgrft-dev/graftcode	Instructions file	967	1mo ago	none	A	4,619	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot

php-agents-boilerplate: Instructions file for Claude Code