open/ktg-plugin-marketplace
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions

feat(ultraplan-local)!: v2.4.0 — orchestrator agents as inline reference

Browse source 
Redefine research-orchestrator, planning-orchestrator, and
architect-orchestrator from "background executor" to "inline
reference documentation". The agent files remain as the canonical
workflow descriptions, but the /ultra* commands now execute the
phases directly in the main command context instead of spawning
these agents as sub-agents.

The /ultra* command markdowns are now the de-facto orchestrators.
Splitting work into a separate sub-agent was incompatible with the
harness's treatment of the Agent tool (not exposed to sub-agents).

BREAKING CHANGE: These agents are no longer invoked. Any external
integration that spawned them directly should now invoke the
corresponding /ultra* command instead.
This commit is contained in:
Kjell Tore Guttormsen 2026-04-19 21:24:45 +02:00
commit c8a6506384
3 changed files with 65 additions and 100 deletions
Download patch file Download diff file Expand all files Collapse all files

54
plugins/ultraplan-local/agents/research-orchestrator.md
View file

@ -1,36 +1,13 @@
---
name: research-orchestrator
description: |
Use this agent to run the full ultraresearch pipeline (parallel local + external
research, triangulation, synthesis) as a background task. Receives a research
question and produces a structured research brief.
<example>
Context: Ultraresearch default mode transitions to background after interview
user: "/ultraresearch-local Should we use Redis or Memcached for session caching?"
assistant: "Interview complete. Launching research-orchestrator in background."
<commentary>
Phase 3 of ultraresearch spawns this agent with the research question to run Phases 4-8 in background.
</commentary>
</example>
<example>
Context: Ultraresearch foreground mode runs the full pipeline inline
user: "/ultraresearch-local --fg What authentication approach fits our architecture?"
assistant: "Running research pipeline in foreground."
<commentary>
Foreground mode runs this agent's logic inline rather than in background.
</commentary>
</example>
<example>
Context: Ultraresearch with local-only mode
user: "/ultraresearch-local --local How is error handling structured in this codebase?"
assistant: "Launching research-orchestrator with local-only agents."
<commentary>
Local mode skips external agents and gemini bridge, only launches codebase analysis agents.
</commentary>
</example>
Inline reference (v2.4.0) — documents the research workflow that
/ultraresearch-local executes in main context. This file is NOT spawned as
a sub-agent anymore. The Claude Code harness does not expose the Agent tool
to sub-agents, so an orchestrator launched with run_in_background: true
cannot spawn the research swarm and would degrade to single-context
reasoning. The /ultraresearch-local command now orchestrates the phases
below directly in the main session.
model: opus
color: cyan
tools: ["Agent", "Read", "Glob", "Grep", "Write", "Edit", "Bash"]
@ -43,11 +20,20 @@ tools: ["Agent", "Read", "Glob", "Grep", "Write", "Edit", "Bash"]
Orchestrator Phase 4 = Command Phase 7 (Triangulation)
Orchestrator Phase 5 = Command Phase 8 (Synthesis + write brief)
Orchestrator Phase 6 = Command Phase 9 (Completion)
This agent handles Phases 4–9 when mode = default or foreground. -->
As of v2.4.0, /ultraresearch-local runs these phases inline in main
context instead of spawning this agent. Keep this file as the canonical
reference for what those phases do. -->
You are the ultraresearch research orchestrator. You receive a research question and
produce a structured research brief that combines local codebase analysis with external
knowledge. You run as a background agent while the user continues other work.
This document is the canonical workflow description for the ultraresearch
pipeline as of v2.4.0. The `/ultraresearch-local` command reads it as
reference and executes the phases below **inline in the main command
context**. It is no longer spawned as a background sub-agent — that mode
silently lost the Agent tool and degraded the swarm to single-context
reasoning.
The role of the "orchestrator" now belongs to the command markdown itself:
the main Opus session launches local + external agents via the Agent tool,
collects their results, triangulates, and writes the research brief.
## Design principle: Context Engineering