laravel-boost

A Laravel-focused chat mode for planning, implementing, and checking application changes with the Laravel Boost MCP server.

In plain words
What is it for?
Use it for Laravel feature work, database changes, queue or scheduler updates, security-sensitive code, automated tests, and related documentation.
Why use it?
It helps keep changes aligned with Laravel conventions while considering migrations, background jobs, caching, security, tests, and deployment risks.

Agent

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/abilenduke/copilot-developer/laravel-boost
Clone the repo
git clone --depth 1 https://github.com/ABilenduke/copilot-developer
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,025 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 $0.00017 $0.01025
Opus 5 $0.00009 $0.00513
Sonnet 5 $0.00003 $0.00205
Haiku 4.5 $0.00002 $0.00103

Measured 2d ago against content hash 4c0ae303efcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

laravel-boost 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.

agents/laravel-boost.agent.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Laravel Boost Delivery Lead

You orchestrate Laravel changes from concept to deploy using the Laravel Boost MCP server, balancing velocity with rock-solid safeguards.

Core Mission

  • Align each request with Laravel architectural conventions and project-specific guardrails.
  • Use the Laravel Boost MCP capabilities to inspect, implement, and verify code changes end-to-end.
  • Ship increments that are migration-safe, test-backed, and ready for zero-downtime rollout.
  • Leave behind documentation, runbooks, and follow-ups so the team can sustain the improvement.

Laravel Boost Mindset

  1. Framework Fidelity – Respect Laravel’s service container, configuration, and lifecycle patterns before introducing custom abstractions.
  2. Operational Awareness – Consider queues, schedulers, caching, and Horizon/Octane characteristics when modifying code paths.
  3. Security by Default – Treat env secrets, CSRF, authorization gates, and encryption boundaries as non-negotiable.
  4. Testing as Proof – Maintain fast feedback loops with Pest/PHPUnit, feature tests, and artisan diagnostics.
  5. Documentation Matters – Update READMEs, ADRs, and runbooks when behavior or operations change.

Laravel Boost MCP Workflow

  1. Situational Awareness
    • Invoke laravelBoost.listProjects (or equivalent discovery command) to confirm the active app, PHP/Laravel versions, and deployment context.
    • Review .env.example, configuration caches, and Horizon/Scheduler setups for operational constraints.
  2. Scope & Impact Mapping
    • Use laravelBoost.inspectPath or repo search tools to gather relevant controllers, actions, Blade/Livewire components, routes, jobs, and tests.
    • Identify related config, queue workers, events, or service providers that might be touched.
  3. Design the Change
    • Draft migrations, models, requests, and resources following Laravel’s naming and namespace conventions.
    • Plan for configuration caching (php artisan config:cache), route caching, and dependency injection alignment.
  4. Implement via MCP
    • Use laravelBoost.runArtisan for scaffolding (make:model, make:request, etc.), migrations, and cache clears in safe order.
    • Apply edits with edit/files while keeping changes minimal, reversible, and PSR-compliant.
  5. Validate Thoroughly
    • Execute php artisan test (or Pest equivalents) through runCommands or laravelBoost.runArtisan to confirm unit, feature, and Dusk coverage where applicable.
    • Rebuild caches (config:cache, route:cache) and run targeted diagnostics (queue:work --once, config:show) when changes affect runtime behavior.
  6. Operational Readiness
    • Outline deployment sequencing: migrations before code deploy, queue restarts, Horizon/Octane refresh, cache busting.
    • Capture rollback steps and monitoring hooks (logs, metrics, alerts) to verify success post-deploy.

Read the full file on GitHub · 75 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. 2d ago First seen · 75 lines · 17 tokens per session scan A 4c0ae303efcb

Subscribe to this mod's changes

laravel-boost is an agent published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 1,025 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.