Skip to main content
affpapa.org
RU EN
plugin

collab-proof — Claude Code plugin: what it does, how to install

Runs post-session retrospectives to compare Claude contributions against developer decisions using a four-frame rubric without external dependencies.

Install into Claude Code · Plugin marketplace All methods and platforms ↓ 
/plugin marketplace add alirezarezvani/claude-skills
/plugin install collab-proof@claude-code-skills
Open on GitHub

What collab-proof does

The plugin reviews completed coding sessions to balance Claude output against developer-led choices. It evaluates the work through a four-frame assessment model with an explicit rubric.

No extra packages or background tools are required. Because it has zero external dependencies, the plugin runs directly via the LLM inside Claude Code.

What it helps with

  • review session contributions between Claude and the developer
  • audit who drove key decisions during implementation
  • run a structured post-session retrospective without external tools

Example prompts for the agent

  • Run a collab-proof retrospective on our recent session
  • Analyze what Claude contributed versus what I guided using collab-proof
  • Break down session decisions using the 4-frame rubric

How to install collab-proof

Plugin marketplace

/plugin marketplace add alirezarezvani/claude-skills
/plugin install collab-proof@claude-code-skills

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about collab-proof

How to install collab-proof in Claude Code?

First register the catalog by running /plugin marketplace add alirezarezvani/claude-skills. Next, install the package with /plugin install collab-proof@claude-code-skills.

What does collab-proof do?

It evaluates completed sessions by comparing Claude contributions against developer direction using an LLM-driven four-frame rubric.

Does collab-proof need external dependencies?

No, the plugin requires zero external dependencies. Everything runs directly inside Claude Code through model prompts.

Source text

collab-proof · MIT 
Assisted retrospective: after a session, calibrates what Claude contributed vs what the developer drove. LLM-assessed 4-frame analysis with explicit rubric, zero dependencies.

© dong7812 · MIT · alirezarezvani/claude-skills

Similar plugins

All plugins for Agent setup: memory, context, orchestration →
ponytail DietrichGebert ponytail steers Claude Code toward small, direct solutions and away from abstractions nobody asked for. Use it when you want the agent to build on what the project already has. ★ 176,443repo stars impeccable pbakaus Hands your agent a designer's vocabulary: 24 commands like polish, audit and bolder, so UI feedback stops being “make it pretty”. ★ 88,212repo stars last-30-days-skill mvanhorn Searches the web for what people posted about a topic in the last month and turns it into one structured brief. ★ 65,508repo stars claude-hud jarrodwatts Shows context usage, rate limits, running tools and todo progress under your input line. Useful when a session runs long and you want to watch the spend. ★ 28,841repo stars understand-anything Egonex-AI Turns codebases or markdown wikis into an interactive knowledge graph with a browser dashboard. Helps navigate unfamiliar repositories without reading files blindly. ★ 88,314repo stars mem0 mem0ai Adds persistent memory to Claude Code so your agent retains project context across terminal sessions. ★ 67,829repo stars

From the same set463

The whole set →
loop-library Guides you through designing, auditing, and finding repeatable AI agent loops with explicit guardrails and stop conditions. Helpful for managing Claude Code autonomy. ★ 28,733repo stars spinning-up-deep-rl A knowledge base built from Spinning Up in Deep RL: a resident core with the algorithm taxonomy plus 20 chapters loaded on demand. ★ 28,733repo stars agent-memory A four-tier memory ladder for Claude Code that promotes facts through recurrence across days instead of model confidence. ★ 28,733repo stars agent-launcher-skills Turn a goal into a Claude Managed Agent workflow, a bounded grading loop, or a recurring deployment. Use it to build and run agents in your Anthropic account. ★ 28,733repo stars compliance-team-iso42001 This plugin checks ISO/IEC 42001 coverage, builds an AI risk register, and plans internal audits. It’s for teams working on an AI management system. ★ 28,733repo stars compliance-team-eu-ai-act Three stdlib scripts classify an AI system under the EU AI Act, plan the conformity route and build an obligation matrix for your organizational role. ★ 28,733repo stars video-content-strategist Plans video content strategy, writes scripts, and optimizes YouTube channels. Suitable for setting up Reels, TikTok, and Shorts workflows or repurposing long-form content. ★ 28,733repo stars business-investment-advisor Assess spending on equipment, property, hiring, technology, or a new business. Compare investment options when deciding how to allocate a limited budget. ★ 28,733repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor