🔌
Plugins
Loading...
Showing 30 of 23002 results
Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI configuration. Joins protect-mcp and signed-audit-trails in the governance category; composes with protect-mcp for runtime enforcement.
Prompt/question A/B benchmarking and ablation tooling. Depends on review-suite.
A Claude Code plugin that uses your signed-in Codex account as an independent reviewer and keeps a strict issue ledger, so Claude cannot claim 'all fixed' until every review finding is actually closed.
Adversarial review-chain workflow: orchestrator + specialist reviewers in sequential waves + judge, file-based artifacts, one-shot agents.
The Conventional Comments standard for pull and merge request reviews: labelled, decorated, actionable comments. Composable with your own conventions.
要件定義→設計→タスク分解→実装の厳密なレビューゲートワークフロー。エージェントによる自動レビュー、階層タスク管理、並列実行対応。
Severity-ranked code review and multi-pass security review with parallel specialist subagents.
Plan review, code review (Adversarial Auditor), iterative review-fix loop, security/red-team review, memory audits.
Symptom-based multi-agent code review: fans out one investigator per quality symptom, then distills the findings into an actionable review
Dynamic review team composition with 14 stack-agnostic specialist agents (including a workflow-first UX/interaction evaluator, an adversarial devils-advocate, a pre-publication safety auditor, and a Claude Code config reviewer) for collaborative, multi-angle review using Claude Code agent teams
Comprehensive PR review pipeline: a pre-review readiness gate (stops on merge conflicts or red code-related CI with a fix-it note, no verdict), branch-level analysis with merge-base attribution (the verdict is decided only by defects the diff introduced, worsened, or interacts with — purely pre-existing defects are reported in full in a separate outside-findings section and routed to a filed issue, parked branch, or memory entry instead of blocking), sequential Claude+Codex dual-model review with evidence-based verification, and opt-in GitHub PR review publishing under a five-frame substance framework. A value/design gate weighs whether the change should exist at all — value versus permanent maintenance cost, right layer, root cause in-repo versus upstream — and can block a PR even when the code is flawless. Remedies stay proportional: changed logic needs tests in the existing test surface, fixed prose is its own deliverable, and a new checker or guard script is never a required remedy. Findings carry git-computed origin labels (feature vs churn) that diagnose diverging review loops without ever touching the verdict. Reviews land on an LGTM or NOT LGTM verdict, compatible with non-blocking recommendations; the only no-verdict path is the readiness gate's fix-CI / fix-conflicts note.
Review a finished system design against the 7 Universal Building Blocks and the non-functional '-ilities': decompose it, flag wrong/missing blocks, rate each load-bearing -ility, and surface the questions a senior would ask. The design-review end of design → build → review.
Iterative code-review loop — review the diff, fix critical/major/minor issues, commit each round, re-review until clean. Project-agnostic.
Enterprise code review by a four-agent team (architect, security, correctness, style) running in parallel. Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.
Architect/executor workflow over MCP — Claude Code or Google Antigravity drives a local LLM executor through structured phases, review gates, and telemetry.
Motor determinístico de revisão de RF em Excel (La Positiva / InsureMO): extrai, o agente analisa cruzando com a memória, e injeta a análise de volta na MESMA planilha de forma mecânica e não-destrutiva. Perfis de coluna por assunto. Escopo tabular (xlsx/csv).
RForge toolkit for Claude Code: 42 commands for R package development, ecosystem management, CRAN submission, and intelligent orchestration
Command-line interface for Feishu (Lark) platform operations, enabling automation of messaging, collaboration, and workspace management tasks.
Your guide to building a Rich Life, powered by Ramit Sethi's philosophy
Tailored feature development workflow with socratic discovery, architecture-first design, SOLID-focused code review, and specialized .NET/UE5 support
rig — a LEGO-style harness composer. Compose bricks (facets/patterns/steps/recipes) at invocation time into a task-specific agent harness for dev-flow orchestration (review, implement, PR, and more). Claude Code native; no heavy DSL engine.
Skills for developing and querying projects in the Rill business intelligence platform