claudecodex

review-cycle

Beta change-verification workflow. Reconstructs what a diff does before reading any declared intent, routes review depth by a deterministic risk floor, applies intent-drift, architecture and risk lenses, and hands deterministic fixes to a hygiene lane that commits locally and never pushes.

0 on GitHubby elmisiv0.2.0-beta.1MITupdated 19 days agoProductivity
/

Plugin review-cycle from marketplace elmisi in elmisi/claude-code-automation. Commands read from the repo's manifest — 19 days ago.

What it installs

Skills (6)

  • review-cycle-architecture

    Judge whether a change fits the system it lands in — boundaries, patterns, distribution of responsibility, technical direction — and surface trade-offs as open questions rather than defects. Invoke it alone to get an architectural read on a branch.

  • review-cycle-drift

    Compare the reconstructed behaviour of a change against its validated intent contract, and report mismatch, intent drift, undeclared assumptions and uncovered acceptance criteria. Runs on a closed change brief; invoke it alone to check a change against an intent you already wrote.

  • review-cycle-hygiene

    Apply the deterministic fixes a review labelled auto-fixable as themed local commits, gated on a green test suite before and after, and never touching test files or pushing. Invoke it alone to clean up the nits on a branch without opening a single comment thread.

  • review-cycle-intent

    Reconstruct the intent of a change from its commits and pull request description, present it for validation, and write the validated intent contract. Runs after the change brief is closed. Invoke it alone when you want the intent handover without any judgement.

  • review-cycle-risk

    Price what it costs if a change is wrong: probability, impact, blast radius, detectability and reversibility — plus rollback plan, negative tests and threat modelling in the strict lane. Invoke it alone to assess a branch before merging.

  • review-cycle

    Verify a change rather than audit a diff. Reconstructs what the change does before reading any declared intent, computes a deterministic risk floor, runs the intent, drift, architecture and risk skills the floor selects, and hands deterministic fixes to the hygiene lane. Use for reviewing a branch,

Subagents (1)

  • lens-runner

    Runs a single review-cycle lens in an isolated context so the three lenses can execute concurrently. Carries no lens logic of its own — it invokes the lens skill, which stays the single source.

View source on GitHub

More from elmisi/claude-code-automation

All 6 plugins →

automate

claude

Expert advisor that helps you decide and create the right Claude Code automation (skills, hooks, subagents, permissions, etc.)

9 skills

0

plan-cycle

claudecodex

File-based planning with annotation pipeline. Creates persistent markdown plans, companion ops guide, and supports impact/quality analysis via composable skills.

3 skills

0

Research methodology to surface non-obvious structural smell leads before promoting refactor candidates. Discovers project areas, investigates in parallel with subagents, synthesizes cross-cutting tensions, and produces a prioritized discovery document.

1 skill · 1 agent

0

qa-architect

claudecodex

Beta contract-driven QA discovery, design, build, and audit workflow.

1 skill

0

takeaway

claudecodex

Structured feedback extraction from skill/tool usage. Interviews the user, distills observations into portable principles, and produces two files — a project-specific evidence retrospective and a tool-agnostic lessons document an improving agent can consume.

1 skill

0

Similar plugins

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

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

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

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

AI-powered codebase understanding — analyze, visualize, and explain any project

9 skills · 10 agents · hooks

Egonex-AI/Understand-Anything 92,410

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

Maintain review-cycle?

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 plugins6 plugins