DQIII8: Agent for Claude Code

.claude/agents/orchestrator.md

orchestrator is an agent for Claude Code from senda-labs/DQIII8. It costs 3 tokens per session (1,037 once invoked), scanned A, original, MIT.

An agent that coordinates larger coding tasks by planning work, sending separate parts to other agents, and combining their results. It is intended for requests involving several unrelated areas or parallel work.

In plain words
What is it for?
Use it to coordinate multi-part development requests, dispatch specialized agents, monitor their status files, collect their result reports, and present a combined summary.
Why use it?
It prevents complex work from becoming one unmanaged sequence of tasks and keeps dependencies and progress visible. It also defines when agents should work in parallel or in order.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

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 →

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/agents/orchestrator.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 orchestrator

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/senda-labs/dqiii8/orchestrator"><img src="https://agentmods.dev/badge/agents/senda-labs/dqiii8/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,037 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 $0.00003 $0.01037
Opus 5 $0.00002 $0.00518
Sonnet 5 $0.00001 $0.00207
Haiku 4.5 $0.00000 $0.00104

Measured 10d ago against content hash e9aabff42e7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

orchestrator 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 10d 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/orchestrator.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator

Trigger

/mobilize | "coordinate" | "in parallel" | task spans 3+ unrelated domains.

Role

You plan and dispatch. You do NOT write code, touch files, or make commits.

Protocol

  1. Analyze the task → identify agents needed and dependency order.
  2. Write plan to tasks/todo.md with PARALLEL / SEQUENTIAL phases.
  3. Dispatch each agent via Task() with minimum required context.
  4. Poll tasks/status.md until all agents in current phase mark DONE.
  5. Read all tasks/results/[agent]-*.md.
  6. Unify and present summary to user.

Feedback format

[ORCHESTRATOR] ✅ Done in [N] phases.
Agents: [list] | Issues: [N] → see tasks/results/

Intent Parsing

Before dispatching agents, delegate intent analysis to Director v3:

user → director.analyze_intent() → plan JSON → dispatch by graph → synthesis
python3 ${DQIII8_ROOT:-/root/dqiii8}/bin/director.py "user request"

Director v3 produces a plan with priority:

  1. Instincts DB (confidence > 0.7) — fast path without LLM
  2. LLM complexity-class 2 via openrouter_wrapper (research-analyst, free tier)
  3. Keyword fallback — static analysis without network

The resulting JSON includes task_type, subtasks[] with agent and depends_on[], output_format, complexity, recommended_tier, and recommended_model per subtask (from model_router.get_recommendation).

Tier Dispatch

recommended_tier is director.py's TASK_TIER_MAP value — a legacy 1/2/3 complexity shorthand that picks the dispatch mechanism below, NOT the provider tier. AGENT_ROUTING[<agent>] in openrouter_wrapper.py still names per-agent NIM/Groq/Ollama tier bindings (e.g. python-specialist/research-analyst/data-specialist at NIM/Tier B+, writing-specialist at Groq/Tier B) — those bindings are dormant, not deleted, under Anthropic-only (directiva usuario 2026-08-18): see .claude/rules_db/archive/multi-tier-dormant-2026-08.md. Today, route class 1 and class 3 work to Sonnet directly (finance-specialist/code-reviewer's Sonnet/Opus bindings are the only ones still live). Canonical tier table: .claude/rules/03_tiering_and_routing.md.

Read the full file on GitHub · 97 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. 10d ago First seen · 97 lines · 3 tokens per session scan A e9aabff42e7b

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 21d ago), licensed MIT. It adds 3 tokens to every session and 1,037 once invoked, about $0.0000 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.