From pragma
Multi-LLM craftsmanship council with live progress and debate mode for code review and design questions
npx claudepluginhub peteski22/agent-pragma --plugin pragmaThis skill is limited to using the following tools:
This skill is for explicit `/star-chamber` invocations with live progress in the main conversation. It supports `--debate` for multi-round deliberation. For automatic invocation on architectural decisions, the `star-chamber` agent handles that separately.
Runs multi-LLM council for adversarial debate, critique, and synthesis on implementation, architecture, review, security, research, and planning tasks via llm-council CLI.
Performs symmetric two-AI peer reviews using OpenAI Codex CLI: independent blind reviews followed by structured per-issue debate for plans, code reviews, architecture, and recommendations.
Orchestrates three-phase LLM consensus protocol coordinating Claude, OpenAI Codex, and Google Gemini CLIs for collaborative code review, multi-model problem-solving, and decision-making.
Share bugs, ideas, or general feedback.
This skill is for explicit /star-chamber invocations with live progress in the main conversation. It supports --debate for multi-round deliberation. For automatic invocation on architectural decisions, the star-chamber agent handles that separately.
Advisory skill that fans out code reviews and design questions to multiple LLM providers (Claude, OpenAI, Gemini, etc.) and aggregates their feedback into consensus recommendations.
| Flag | Description | Manual Only |
|---|---|---|
--provider <name> | LLM provider to use (repeatable, e.g., --provider openai --provider gemini). Defaults to all in config. | No |
--file <path> | Specify file to review (repeatable). Defaults to recent git changes. | No |
--timeout <seconds> | Timeout per provider request (overrides config timeout_seconds). | No |
--debate | Enable debate mode: multiple rounds with summarization between rounds. | Yes |
--rounds N | Number of debate rounds (default: 2, requires --debate). | Yes |
Manual-only flags are skill invocation parameters interpreted by Claude Code, NOT flags passed to the star-chamber CLI. Debate mode is orchestrated by Claude Code (see Debate Mode in the protocol).
The skill loader provides the base directory in the header: Base directory for this skill: <path>. Set the path variable used throughout the protocol:
STAR_CHAMBER_PATH="<base directory from header>"
# e.g., STAR_CHAMBER_PATH="$HOME/.claude/plugins/cache/pragma/skills/star-chamber"
Read and follow the full protocol from $STAR_CHAMBER_PATH/PROTOCOL.md. It contains Steps 0-4: prerequisite checks, invocation mode detection (code review vs design question), review target identification, context gathering, CLI invocation, and result presentation. Debate mode is documented as a separate section.
This skill is not auto-invoked (model-invocable: false). The star-chamber custom subagent handles auto-invocation based on its description. This skill is for explicit /star-chamber invocations only.