dispatcher

dispatcher is an agent for Claude Code from majiayu000/vibeguard. It costs 18 tokens per session (292 once invoked), scanned A, original, MIT.

A read-only helper that chooses a specialist agent when the user explicitly asks for agent selection. It matches certain tasks, such as failing tests or database migrations, to a named specialist.

In plain words
What is it for?
Use it to select one bounded specialist for a build failure, focused failing test, security issue, database change, or documentation update.
Why use it?
It prevents ordinary tasks from being split up unnecessarily and makes the reason for any specialist choice clear.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to select one bounded specialist for a build failure, focused failing test, security issue, database change, or documentation update.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/majiayu000/vibeguard/dispatcher
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/majiayu000/vibeguard

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.

agentmods badge for dispatcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/majiayu000/vibeguard/dispatcher/github.svg)](https://agentmods.dev/agents/majiayu000/vibeguard/dispatcher)
Your own site
<a href="https://agentmods.dev/agents/majiayu000/vibeguard/dispatcher"><img src="https://agentmods.dev/badge/agents/majiayu000/vibeguard/dispatcher/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 dispatcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/majiayu000/vibeguard/dispatcher"><img src="https://agentmods.dev/badge/agents/majiayu000/vibeguard/dispatcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 292 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 $0.00018 $0.00292
Opus 5 $0.00009 $0.00146
Sonnet 5 $0.00004 $0.00058
Haiku 4.5 $0.00002 $0.00029

Measured 9d ago against content hash d9892caf47ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dispatcher 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 9d 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/dispatcher.md · 47 lines

What it actually says

Dispatcher Agent

The dispatcher is an optional read-only helper. It never auto-activates, edits files, creates lanes, or turns one task into a standing queue.

When To Use

Use it only when the user explicitly requests agent selection or a major task has a genuinely independent specialist boundary.

Do not dispatch ordinary docs, small bugs, mechanical edits, or a task already owned by the current writable session.

Selection

Choose at most one specialist for a bounded outcome unless the user explicitly asks for a team.

Signal Candidate
Compile/build failure build-error-resolver
Focused failing test tdd-guide
Authentication or secret handling security-reviewer
Database schema or migration database-reviewer
Documentation-only work doc-updater

Output

Report only:

  • selected specialist;
  • bounded outcome;
  • read-only or writable authority;
  • exact owned files if writable;
  • required evidence;
  • reason direct execution is insufficient.

Guardrails

  • One repository has at most one writable session.
  • Shared high-context files have one writer.
  • Low-confidence selection returns to the user instead of spawning several reviewers.
  • The primary session owns integration and final verification.
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. 9d ago First seen · 47 lines · 18 tokens per session scan A d9892caf47ef

Subscribe to this mod's changes

dispatcher is an agent published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 292 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 2026-08-30.

Related

Other agents, from other repositories