claude

review-suite

Plan review, code review (Adversarial Auditor), iterative review-fix loop, security/red-team review, memory audits.

2 on GitHubby whichguyv0.2.6MITupdated 14 days ago
/

Plugin review-suite from marketplace claude-craft in whichguy/claude-craft. Commands read from the repo's manifest — 14 days ago.

What it installs

Skills (1)

  • review-plan

    Universal plan review: senior-engineer directive + deterministic count-based severity rule. AUTOMATICALLY INVOKE when: - MANDATORY_PRE_EXIT_PLAN directive applies (before ExitPlanMode) - User says "review plan", "check plan", "plan ready?" - Any plan file needs review NOT for: Code review of existin

Slash commands (4)

  • /review-suite:code-security

    Code security analysis and vulnerability assessment

  • /review-suite:memory-security

    Security analysis for memory files and personal information detection

  • /review-suite:red-team

    Expert-driven iterative red team review with Opus orchestration (--fast for Haiku, --deep for Opus throughout)

  • /review-suite:review-fix

    Iterative review-fix loop — spawns parallel code-reviewer subagents per file (single Task for 1 file, parallel Tasks for 2+ files); max 5 rounds; concurrent fix application via parallel fixer Task() agents; optional plan_summary parameter for intent-aligned review; git fallback for auto-detecting ch

Subagents (5)

  • code-reviewer

    Ultimate Adversarial Auditor. Combines language-specific "Domain Radar" with a "Suspicion-First" internal monologue for 100% logic trap detection.

  • prompt-reviewer

    Comprehensive prompt analysis and enhancement using phased development framework. **AUTOMATICALLY INVOKE** this agent when user mentions "review prompt", "improve prompt", "analyze prompt", or when editing agent/skill markdown files. **STRONGLY RECOMMENDED** for new agent creation, prompt optimizati

  • review-fix-judge

    LLM judge that semantically evaluates code reviewer output against ground-truth issues. Used by review-fix-bench harness to replace fragile regex-based finding extraction and matching. Outputs structured JSON only — no prose wrapper.

  • review-fix

    Simplified orchestrator for the iterative review-fix loop. Detects files → delegates to specialized reviewers in standalone mode → aggregates results → commits/PRs. Reviewers (code-reviewer, etc.) handle their own inner loops, auto-fixes, and re-verification. **AUTOMATICALLY INVOKE** after implement

  • trap-generator

    Generative Adversarial Network (GAN) Red Team. Writes novel, obfuscated vulnerabilities to test the limits of the code-reviewer agent.

View source on GitHub

More from whichguy/claude-craft

All 11 plugins →

gas-suite

claude

Google Apps Script review, debugging, planning, sidebar testing, Gmail Cards.

8 skills · 2 commands · 15 agents · 1 MCP server

2

planning-suite

claude

node-plan, test-prompt-harness, alias/unalias, performance, knowledge, iterative red-team plan review, and ExitPlanMode plan gates with an execute nudge (Execute: schedule routes to /skill-craft:backchain + /skill-craft:plan-dispatcher). Architect, c-plan, plan-test and prompt-align/audit/migrate/refine live in skill-craft (/skill-craft:<leaf>).

2 skills · 6 commands · 12 agents · hooks

2

review-bench

claude

Question A/B benchmarking, prompt improvement and ablation tooling. Depends on review-suite. compare-prompts, improve-system-prompt and review-fix-bench live in skill-craft (/skill-craft:<leaf>).

8 skills · 4 agents

2

wiki-suite

claude

Project LLM wiki: ingest, query, process queue, lint, plus proactive research hook.

7 skills · hooks

2

async-suite

claude

Background task workflow: bg / todo / todo-cleanup + task-persist + feedback ingestion.

3 skills · 3 commands · hooks

2

c-thru

claude

Shape C: marketplace plugin bootstraps the c-thru CLI via /c-thru:install-cli; runtime is cthru (fleet inject). Product: whichguy/c-thru (git-subdir plugins/c-thru). Prefer one marketplace identity only. Optional planning-suite for plan-scheduler.

2 commands · hooks

2

Similar plugins

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

agentic-qe-fleet

claude

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

headroom-skill

claude

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

headroomlabs-ai/headroom 79,508

agentic-awesome-skills

claudecodex

Expose the plugin-safe Claude Code subset of Agentic Awesome Skills through a single marketplace entry.

200 skills

sickn33/agentic-awesome-skills 49,620

ai-plugins

claude

Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain

12 skills · 11 agents · hooks

anthropics/claude-plugins-official 47,076

Maintain review-suite?

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 plugins11 plugins