claude

review-council

Always-on multi-persona code-review pipeline: parallel distinct-angle reviewer panels → a Code Review Master → a second adversarial panel → Master 2 → an opt-in Executor & Fixer. No token optimization; every panelist is always spun up. Opt-in.

0 on GitHubby Vasco Maiav0.1.0MITupdated 2 months agoworkflow
/

Plugin review-council from marketplace claude-specs in vmaia00/claude-specs. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (1)

  • deep-review

    The contract for an always-on, multi-persona code-review pipeline — parallel distinct-angle reviewer panels, an adversarial finding-verifier, a recall-biased Code Review Master that synthesizes one Solution, a second adversarial panel, a Master 2 verdict, and an opt-in Executor & Fixer. Use when run

Slash commands (1)

  • /review-council:deep-review

    Always-on multi-persona code review — two adversarial reviewer panels, two Code Review Masters, and an opt-in Executor & Fixer.

Subagents (13)

  • appsec-reviewer

    Read-only application-security reviewer (OWASP-class) for the review-council pipeline. Use as the security lane of Panel R1 and the security re-check in R2. Returns JSON findings (unified schema). (Named appsec-reviewer to avoid colliding with ECC's security-reviewer.)

  • architecture-critic

    Read-only architecture/design critic for the review-council pipeline. Use as the architecture lane of Panel R1 and the design-fit lane in R2. Returns JSON findings (unified schema).

  • code-review-master

    Read-only aggregator — the Code Review Master — for the review-council pipeline. Use at Stage 2 to synthesize one Solution from R1 findings, and at Stage 4 to produce the final verdict + fix work-list from R2. Returns Markdown (solution.md or verdict.md).

  • concurrency-contract-reviewer

    Read-only concurrency and API-contract reviewer for the review-council pipeline. Use as the concurrency-contract lane of Panel R1 — the documented LLM blind spots. Returns JSON findings (unified schema).

  • contrarian-reviewer

    Read-only adversarial contrarian (devils-advocate) reviewer for the review-council pipeline. Use as the contrarian/blast-radius lane of Panel R2, reviewing the proposed Solution. Returns JSON findings (unified schema).

  • correctness-reviewer

    Read-only logic/correctness reviewer for the review-council pipeline. Use as the correctness lane of Panel R1 (and the R1-finding fidelity lane in R2). Returns JSON findings (unified schema).

  • error-handling-reviewer

    Read-only error-handling reviewer (silent-failure hunter) for the review-council pipeline. Use as the error-handling lane of Panel R1. Returns JSON findings (unified schema).

  • finding-verifier

    Read-only adversarial finding verifier for the review-council pipeline. Use after each panel to falsify findings before they advance. Returns the same findings array with verified/verifier_note set.

  • fixer

    Write-capable code executor and fixer for the review-council pipeline. Use ONLY at Stage 5 when invoked with --fix to apply the Master-2 fix work-list, keep tests green, and re-review the patch. Returns a concise fix-report with file:line.

  • performance-reviewer

    Read-only performance reviewer for the review-council pipeline. Use as the performance lane of Panel R1. Returns JSON findings (unified schema).

  • readability-reviewer

    Read-only readability/maintainability reviewer (comments + simplification) for the review-council pipeline. Use as the readability lane of Panel R1. Returns JSON findings (unified schema).

  • test-reviewer

    Read-only test-coverage reviewer for the review-council pipeline. Use as the tests lane of Panel R1 and the test-adequacy lane in R2. Returns JSON findings (unified schema).

  • type-design-reviewer

    Read-only type-and-design reviewer for the review-council pipeline. Use as the type-design lane of Panel R1. Returns JSON findings (unified schema).

View source on GitHub

More from vmaia00/claude-specs

All 7 plugins →

ruby

claude

Curated Ruby/Rails/Hotwire/TDD skills (17), vendored (MIT) from superpowers-ruby + rails-agent-skills + ruby-core-skills, slimmed 2026-08-25. Opt-in; install for Ruby on Rails work.

17 skills

0

core

claude

Orchestrator foundations: generic builder/explorer/planner/reviewer agents, a new-project command, a secret-scan hook, and universal working principles.

5 skills · 4 commands · 4 agents · hooks

0

ecc

claude

Slim remnant of affaan-m/ECC (MIT): 6 curated skills — seo, design-system, api-design, accessibility, make-interfaces-feel-better, postgres-patterns. The other ~580 vendored items were removed 2026-08-25 after a usage audit (re-vendor from upstream if ever needed).

6 skills

0

spec-agentic

claude

Specification doctrine and toolkit for work executed by coding agents: declared-executor headers, a LOCKED/WORKING/OPEN facts ledger, stable anchor IDs with CI verifiers, an OpenAPI contract set, impact maps, and a read-only spec auditor. Pairs with spec-human.

5 skills · 1 agent

0

writing

claude

Document production: latex-doc renders Markdown deliverables into overflow-safe thesis-style PDFs (pandoc + XeLaTeX, three-families overflow method), and pt-pt enforces European Portuguese in every Portuguese response (vendored from mfrade/claude-skills).

2 skills

0

consulting

claude

Consulting-grade analysis-framework design: chapter skeleton, named frameworks, per-chapter data requirements, and a visualisation plan from just a research subject; data gathered via ordinary research, report written against the framework with a zero-hallucination policy. Opt-in.

1 skill

0

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

academic-research-skills

claude

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

open-code-review

claude

Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.

2 commands

alibaba/open-code-review 50,068

backend-development

claudecodex

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

codex

claude

Use Codex from Claude Code to review code or delegate tasks.

3 skills · 8 commands · 1 agent · hooks

openai/codex-plugin-cc 35,098

Maintain review-council?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins7 plugins