refactor(party-mode): consolidate into single SKILL.md with real subagents#2160
refactor(party-mode): consolidate into single SKILL.md with real subagents#2160
Conversation
…gents Replace the multi-file workflow architecture (workflow.md + 3 step files) with a self-contained SKILL.md that spawns each agent as an independent subagent via the Agent tool. This produces genuinely diverse perspectives instead of one LLM roleplaying multiple characters. Adds --model and --solo flags for flexibility. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
🤖 Augment PR SummarySummary: Refactors Party Mode to be a single, self-contained Changes:
Technical Notes: Party Mode now relies on 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
| Follow the instructions in ./workflow.md. | ||
| # Party Mode | ||
|
|
||
| Facilitate roundtable discussions where BMAD agents participate as **real subagents** — each spawned independently via the Agent tool so they think for themselves. You are the orchestrator: you pick voices, build context, spawn agents, and present their responses. You never generate agent responses yourself. |
There was a problem hiding this comment.
This says “You never generate agent responses yourself,” but later --solo explicitly instructs generating all agent responses in one message; that contradiction could cause the orchestrator to refuse to operate in solo mode.
Severity: medium
Other Locations
src/core-skills/bmad-party-mode/SKILL.md:87
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
|
|
||
| 1. **Parse arguments** — check for `--model` and `--solo` flags from the user's invocation. | ||
|
|
||
| 2. Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve: |
There was a problem hiding this comment.
Loading config only from {project-root}/_bmad/bmm/config.yaml assumes the BMM module is installed; if Party Mode is used in a core-only installation, this step may fail and prevent activation.
Severity: medium
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
📝 WalkthroughWalkthroughThe Party Mode skill documentation was reorganized by consolidating the workflow architecture from separate step files ( Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@src/core-skills/bmad-party-mode/SKILL.md`:
- Around line 14-19: Update user-facing docs to document the new Party Mode CLI
flags: add entries for `--model <model>` and `--solo` that explain behavior,
examples, and trade-offs; specifically, create or update
docs/reference/party-mode.md (or equivalent) to define `--model` (usage examples
like `--model haiku`, when to force models vs. defaults, impact on subagents)
and `--solo` (describe roleplaying fallback, announce on activation, and when to
use), update any how-to guides under docs/how-to/ with sample invocations
showing the flags, and add a release note/CHANGELOG entry highlighting the
architectural change to real subagents and the new control flags so users know
about the new options introduced by Party Mode (`--model`, `--solo`) and their
effects.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 9a8acd94-4bae-4734-b0e9-5bcae1fc65b2
📒 Files selected for processing (5)
src/core-skills/bmad-party-mode/SKILL.mdsrc/core-skills/bmad-party-mode/steps/step-01-agent-loading.mdsrc/core-skills/bmad-party-mode/steps/step-02-discussion-orchestration.mdsrc/core-skills/bmad-party-mode/steps/step-03-graceful-exit.mdsrc/core-skills/bmad-party-mode/workflow.md
💤 Files with no reviewable changes (4)
- src/core-skills/bmad-party-mode/steps/step-02-discussion-orchestration.md
- src/core-skills/bmad-party-mode/steps/step-03-graceful-exit.md
- src/core-skills/bmad-party-mode/workflow.md
- src/core-skills/bmad-party-mode/steps/step-01-agent-loading.md
| ## Arguments | ||
|
|
||
| Party mode accepts optional arguments when invoked: | ||
|
|
||
| - `--model <model>` — Force all subagents to use a specific model (e.g. `--model haiku`, `--model opus`). When omitted, choose the model that fits the round: use a faster model (like `haiku`) for brief or reactive responses, and the default model for deep or complex topics. Match model weight to the depth of thinking the round requires. | ||
| - `--solo` — Run without subagents. Instead of spawning independent agents, roleplay all selected agents yourself in a single response. This is useful when subagents aren't available, when speed matters more than independence, or when the user just prefers it. Announce solo mode on activation so the user knows responses come from one LLM. |
There was a problem hiding this comment.
Document the new CLI flags in user-facing documentation.
This PR introduces two significant user-facing features:
--model <model>: Force all subagents to a specific model (e.g.,--model haiku)--solo: Fall back to single-LLM mode (roleplay all agents in one response)
These CLI flags change how users invoke and control Party Mode. Per coding guidelines for src/** files, "altered CLI flags, or modified configuration options should all be reflected in the relevant doc pages."
Suggested documentation updates:
- docs/reference/party-mode.md (or similar): Document both flags with examples, use cases, and trade-offs (speed vs. independence)
- docs/how-to/ guides: Update any party-mode invocation examples to show the optional flags
- Release notes/CHANGELOG: Highlight the architectural shift to real subagents and the new control flags
As per coding guidelines, source file changes introducing new features or CLI flags require corresponding documentation updates.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@src/core-skills/bmad-party-mode/SKILL.md` around lines 14 - 19, Update
user-facing docs to document the new Party Mode CLI flags: add entries for
`--model <model>` and `--solo` that explain behavior, examples, and trade-offs;
specifically, create or update docs/reference/party-mode.md (or equivalent) to
define `--model` (usage examples like `--model haiku`, when to force models vs.
defaults, impact on subagents) and `--solo` (describe roleplaying fallback,
announce on activation, and when to use), update any how-to guides under
docs/how-to/ with sample invocations showing the flags, and add a release
note/CHANGELOG entry highlighting the architectural change to real subagents and
the new control flags so users know about the new options introduced by Party
Mode (`--model`, `--solo`) and their effects.
2 participants
Summary
--modeland--soloflags for controlling subagent model selection and fallback to single-LLM modeTest plan
--model haikuflag to confirm model override works--soloflag to confirm single-LLM fallback works🤖 Generated with Claude Code