DQIII8: Skill for Claude Code

.claude/skills/dispatch-agent/SKILL.md

dispatch-agent is a skill for Claude Code from senda-labs/DQIII8. It costs 72 tokens per session (2,002 once invoked), scanned A, original, MIT.

A dormant skill for sending tasks to external coding agents and coordinating their work from one session. Its current instructions say not to use that multi-agent routing system while the Anthropic-only directive remains active.

In plain words
What is it for?
When reactivated, it is intended for delegating coding, research, data analysis, safety checks, reviews, and parallel subtasks to other agents.
Why use it?
The provided information describes its intended mechanism but says it is currently inactive, so it should not be relied on for live task dispatch.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 bin/core/dispatch.py --agent <agente> --prompt "<tarea>".

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. 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/senda-labs/DQIII8/main/.claude/skills/dispatch-agent/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

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 dispatch-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/senda-labs/dqiii8/dispatch-agent/github.svg)](https://agentmods.dev/skills/senda-labs/dqiii8/dispatch-agent)
Your own site
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/dispatch-agent"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/dispatch-agent/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 dispatch-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/dispatch-agent"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/dispatch-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,002 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 $0.00072 $0.02002
Opus 5 $0.00036 $0.01001
Sonnet 5 $0.00014 $0.00400
Haiku 4.5 $0.00007 $0.00200

Measured 9d ago against content hash b73ffff4ae66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dispatch-agent 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.

.claude/skills/dispatch-agent/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dispatch Agent — Despachar tareas al routing system de dqiii8

DORMANTE bajo Anthropic-only (directiva usuario 2026-08-18). Este skill despacha a NIM/Groq/Ollama — ninguno operativo hoy (NIM confirmado 403 desde 2026-08-16). No usar dispatch.py para trabajo real mientras la directiva siga vigente; usa el Agent tool nativo (Sonnet por defecto) o claude -p directo. El resto de este fichero describe la mecánica completa para cuando se reactive — ver checklist de reactivación en .claude/rules_db/archive/multi-tier-dormant-2026-08.md.

Cuándo usar este skill (una vez reactivado el multi-tier)

Siempre que necesites ejecutar trabajo en NIM/Groq/Ollama en lugar de gastar tokens de Anthropic:

  • Generar código desde pseudocódigo o spec → python-specialist o algo-specialist
  • Investigación de dominio → research-analyst
  • Múltiples subtareas paralelas independientes → dispatch_parallel
  • Análisis de datos → data-specialist
  • Safety check → safety-checker
  • Revisión/validación de código → code-reviewer (Opus)

Herramienta principal

cd /root/dqiii8

# Despacho único (sync, respuesta directa)
python3 bin/core/dispatch.py --agent <agente> --prompt "<tarea>"

# Con contexto de fichero
python3 bin/core/dispatch.py --agent python-specialist --context-file specs/impl.md --prompt "Implementa esto"

# Async (devuelve task_id, continúa en background)
python3 bin/core/dispatch.py --agent research-analyst --prompt "..." --async

# Leer resultado async
python3 bin/core/dispatch.py --read <task_id>

# Ver todos los agentes disponibles
python3 bin/core/dispatch.py --list-agents

Hermes Work Loop — Patrón de orquestación

El Hermes Loop es el patrón estándar para trabajo multi-agente desde CC:

[CC: PLANIFICACIÓN]
       ↓
[dispatch_parallel → N agentes NIM/Groq]   ← Costo ~$0, 40 RPM NIM
       ↓
[CC: RECOLECTAR + FILTRAR resultados]
       ↓
[dispatch → code-reviewer (Opus)]          ← Solo si hay código crítico
       ↓
[CC: SINTETIZAR + ENTREGAR]

Read the full file on GitHub · 189 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. 9d ago First seen · 189 lines · 72 tokens per session scan A b73ffff4ae66

Subscribe to this mod's changes

dispatch-agent is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 20d ago), licensed MIT. It adds 72 tokens to every session and 2,002 once invoked, about $0.0004 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.