Council Review
- 43 installs
- 706 repo stars
- Updated July 14, 2026
- alinaqi/claude-bootstrap
council-review is a Claude skill that auto-validates plans, architecture changes, and PRs through a multi-model reviewer council before execution.
About
council-review provides behavioral rules for a multi-model validation council that reviews plans, architecture changes, and PRs before execution. When a plan is written or an architectural change is made, it runs validate-plan or review across a panel of models led by a chief model, then applies threshold voting to decide whether to auto-execute or surface feedback. A developer relies on it so architecture and security decisions get independent verification before they run.
- Auto-validates plans, architecture changes, and PRs via a multi-model council
- Uses threshold voting so 2 of 3 reviewers approve to auto-execute
- Runs review contexts led by a chief model plus a panel of reviewers
Council Review by the numbers
- 43 all-time installs (skills.sh)
- Ranked #610 of 1,352 Code Review & Quality skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
council-review capabilities & compatibility
- Capabilities
- code review · orchestration
- Use cases
- code review · orchestration
- Pricing
- Free
What council-review says it does
Multi-model validation council — auto-validate plans, architecture changes, and PRs via validate-plan/review before executing
2+ of 3 approve → execute immediately
The whole point is that architecture and security decisions get independent verification before execution.
npx skills add https://github.com/alinaqi/claude-bootstrap --skill council-reviewAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 43 |
|---|---|
| repo stars | ★ 706 |
| Last updated | July 14, 2026 |
| Repository | alinaqi/claude-bootstrap ↗ |
What it does
Auto-validate a plan, architecture change, or PR through a multi-model reviewer panel before executing it.
Who is it for?
Getting independent multi-model sign-off on plans, architecture, and PRs before executing
Skip if: Simple standalone use, since it depends on installed helpers like ~/bin/validate-plan and ~/bin/review and council.yaml config
When should I use this skill?
You write a plan to ~/.claude/plans/, make architectural changes, or before marking a PR done
What you get
A threshold-based approval decision from a panel of models before code executes
- a threshold-based approval decision
- reviewer feedback surfaced to the user
By the numbers
- Three reviewer contexts: plan, review, and architecture
- Model inventory lists 13 tiers in council.yaml
Files
Council of Experts — Multi-Model Validation
When to Auto-Trigger
Plans (auto_validate_plans)
When you write a plan to ~/.claude/plans/, automatically validate it:
~/bin/validate-plan --threshold 2 ~/.claude/plans/<plan-file>.md- 2+ of 3 approve → execute immediately
- 1 of 3 → surface reviewer feedback to user before proceeding
- 0 of 3 → revise plan, re-validate
Architecture Decisions (auto_review_architecture)
When making architectural changes (new services, API redesigns, database schema changes), run:
~/bin/review --all "Review this architecture: <summary>"PR Review (auto_review_prs)
Before marking a PR as done, run:
~/bin/review --all --file <changed-files>Configuration
Council behavior is configured in ~/.claude/council.yaml. The Maggy dashboard (Settings > Council) also manages this config.
Chief of the Council
chief: claude-fable-5 — Claude Fable 5 (Anthropic's most capable widely-released model, GA 2026-06-09) leads every panel as the chief: it reviews first and casts the deciding synthesis. Invoked via ~/bin/claude-fable-5. Override the chief in ~/.claude/council.yaml.
Reviewer Contexts
The chief leads each context, followed by the panel:
| Context | Default Reviewers | When |
|---|---|---|
plan | Claude Fable 5 (chief), DeepSeek Pro, Codex, Gemini Pro | Before executing any plan |
review | Claude Fable 5 (chief), DeepSeek Pro, Kimi | Code review, PR review |
architecture | Claude Fable 5 (chief), DeepSeek Pro, Gemini Pro, Grok | System design, schema changes |
Threshold Rules
The threshold setting controls how many approvals are needed:
threshold: 2with 3 reviewers → need 2/3 to auto-execute- Clamped to [1, reviewer_count] — can't be 0 or exceed available reviewers
Model Inventory
All 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 name
Use POST /api/models/health to verify all models are responding.
How This Skill is Used
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.
Related skills
Improve Codebase ArchitectureSafely deepen clusters of shallow modules into cohesive, testable units while respecting their external dependencies.566k196k
Caveman ReviewGet ultra-compressed, one-line code review comments that cut noise while keeping every actionable fix.270k94.7kCodebase DesignShared vocabulary for designing deep modules: improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable.266k196kCavecrewDelegate coding tasks to specialized subagents that return compressed output, keeping the main context window usable for much longer sessions.220k94.7kCode ReviewReviews a branch or PR diff on two axes at once: conformance to coding standards plus a code-smell baseline, and whether it actually implements the original spec.201k196k
Requesting Code ReviewDispatch a consistent, high-signal code reviewer subagent that catches plan deviations and quality issues before merging or continuing development.183k264kFAQ
How does the council decide?
It uses threshold voting; with 3 reviewers and threshold 2, it needs 2 of 3 approvals to auto-execute, otherwise it surfaces feedback or revises.
How is the review executed?
Execution happens via the installed ~/bin/validate-plan and ~/bin/review commands, driven by config in ~/.claude/council.yaml.