with one click
council-review
Multi-model validation council — auto-validate plans, architecture changes, and PRs via validate-plan/review before executing
Menu
Multi-model validation council — auto-validate plans, architecture changes, and PRs via validate-plan/review before executing
Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies
Mandatory code reviews via /code-review before commits and deploys
Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement
Maggy is a local AI engineering command center. AI-prioritized inbox across issue trackers (GitHub Issues/Asana), one-click TDD execute with iCPG context enrichment, daily competitor intelligence briefing.
Dynamic multi-repo and monorepo awareness for Claude Code. Analyze workspace topology, track API contracts, and maintain cross-repo context.
Multi-agent orchestration with container-isolated workspaces — each agent session runs in its own Docker container with independent git branches
| name | council-review |
| description | Multi-model validation council — auto-validate plans, architecture changes, and PRs via validate-plan/review before executing |
| when-to-use | When you write a plan to ~/.claude/plans/, make architectural changes, or before marking a PR done; required for CLAUDE-tier tasks |
| user-invocable | false |
| allowed-tools | ["Bash","Read"] |
| effort | high |
When you write a plan to ~/.claude/plans/, automatically validate it:
~/bin/validate-plan --threshold 2 ~/.claude/plans/<plan-file>.md
When making architectural changes (new services, API redesigns, database schema changes), run:
~/bin/review --all "Review this architecture: <summary>"
Before marking a PR as done, run:
~/bin/review --all --file <changed-files>
Council behavior is configured in ~/.claude/council.yaml. The Maggy dashboard (Settings > Council) also manages this config.
| Context | Default Reviewers | When |
|---|---|---|
plan | DeepSeek Pro, Codex, Gemini Pro | Before executing any plan |
review | DeepSeek Pro, Kimi | Code review, PR review |
architecture | DeepSeek Pro, Gemini Pro, Grok | System design, schema changes |
The threshold setting controls how many approvals are needed:
threshold: 2 with 3 reviewers → need 2/3 to auto-executeAll 13 tiers are listed in ~/.claude/council.yaml under models:. Each has:
id — unique identifiercmd — CLI command to invoke (null for Claude models, which are the host)tier — routing priority (0=cheapest, 12=most capable)label — human-readable nameUse POST /api/models/health to verify all models are responding.
This skill is loaded by Claude Code on session start. It provides the behavioral rules for when to invoke multi-model validation. The actual execution happens via ~/bin/validate-plan and ~/bin/review which are already installed.
Do not skip council validation for CLAUDE-tier tasks. The whole point is that architecture and security decisions get independent verification before execution.