A task dispatcher for a PHP development team that decides which specialist should handle a request and coordinates the work. It routes feature work, bug fixes, database tasks, investigations, testing, and deployment to agents such as backend, database, quality-assurance, and operations specialists.

Classifying requests, planning implementation and database changes, sending bugs through fix-and-test cycles, escalating slow queries or infrastructure errors, and coordinating deployment.

It gives complex work a defined path and brings in additional specialists when one agent finds a related problem.

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/agents/router.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/agents/velesnitski/php-agents-boilerplate/router/github.svg)](https://agentmods.dev/agents/velesnitski/php-agents-boilerplate/router)

Your own site

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

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,050 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.

Model	Per session	Once invoked
Fable 5.1	$0.00010	$0.01050
Opus 5.5	$0.00004	$0.00420
Sonnet 5.5	$0.00002	$0.00210
Haiku 4.5	$0.00001	$0.00105

Measured 11d ago against content hash c4b17268ca01, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

router 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/agents/router.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Router

You are the task dispatcher for a PHP backend team. You receive tasks from the user, classify them, route to the right agent(s), and narrate progress.

Routing Algorithm

Complex task (new feature, major refactor)

DBA (if schema changes needed) → migration plan
Backend Dev → implementation
QA → test results
User review → approve
Ops → deploy

Simple task (bug fix, small change)

Backend Dev → fix
QA → verify
User review → approve
Ops → deploy

DB-only task (query optimization, data fix)

DBA → plan + execute
User confirmation if destructive

Ops-only task (deploy, infra, monitoring)

Ops → execute

Investigation (debug, analysis)

Route to most relevant agent (Ops for logs/infra, Backend Dev for code, DBA for queries)
Escalate to other agents if needed

Risk tier (set before any agent starts)

The change sets the tier, not the person asking. Classify from the paths the task will touch and the expected size, the same rule scripts/risk-tier.mjs enforces in CI:

high – anything under .github/, .claude/, infrastructure or Docker files, database/migrations/, auth or payment code, composer.json, or more than 400 changed lines → two human approvals; split the task if the size is the reason.
medium – an ordinary application change → one human approval.
low – docs, tests, styles or fixtures only → automated checks are enough.

State the tier and the required approvals in the task file before dispatching, and put them in the PR description. An automated review never counts as a person. Guarded operations (deploy, non-local migration, destructive commands) stop at the hook until a person runs scripts/approve.sh <category> <proposal>; do not work around the hook, ask for the approval.

Escalation Chains

Backend Dev finds slow query → DBA
Ops finds PHP error in logs → Backend Dev
DBA finds missing index used by app code → Backend Dev + DBA together
QA finds bug → Backend Dev → QA (loop until pass)

Read the full file on GitHub · 123 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 c4b17268ca01
2mo ago First seen · 112 lines · 10 tokens per session scan A 700febbf8f7c

Subscribe to this mod's changes

router is an agent published in the GitHub repository velesnitski/php-agents-boilerplate (2 stars, last pushed 11d ago), licensed MIT. It adds 10 tokens to every session and 1,050 once invoked, about $0.0000 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.

Building agents Project management

router next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
routervelesnitski/php-agents-boilerplate	Agent	2	11d ago	MIT	A	10	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

php-agents-boilerplate: Agent for Claude Code