claude

verified

Stop-hook correctness gate: scores an answer's factual claims against what the session actually ran, blocks on anything unbacked, and records verdicts to a replay ledger so pattern changes are scored before they ship.

0 on GitHubby Personal AI Setupv0.3.1MITupdated yesterdaydevelopment
/

Plugin verified from marketplace ai-setup in josippapez/ai-setup. Commands read from the repo's manifest — today.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Slash commands (1)

  • /verified:verified-replay

    Score a change to the verified gate's claim patterns against the stored replay ledger, and ship it only if it does not score worse.

Hooks (3)

  • Stop

    CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}" NODE_PATH="${CLAUDE_PLUGIN_DATA}/node_modules" node "${CLAUDE_PLUGIN_ROOT}/hooks/verify-stop.cjs"

  • SubagentStop

    CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}" NODE_PATH="${CLAUDE_PLUGIN_DATA}/node_modules" node "${CLAUDE_PLUGIN_ROOT}/hooks/verify-stop.cjs"

  • SessionStart

    diff -q "${CLAUDE_PLUGIN_ROOT}/package.json" "${CLAUDE_PLUGIN_DATA}/.installed-package.json" >/dev/null 2>&1 || (cd "${CLAUDE_PLUGIN_DATA}" && cp "${CLAUDE_PLUGIN_ROOT}/package.json" . && npm install

View source on GitHub

More from josippapez/ai-setup

All 12 plugins →

better-design

claude

Vendored web design, motion, and 3D skills from MengTo/Skills, GreenSock, Emil Kowalski, ibelick, and Vercel's web interface guidelines. Skills only; no rules, hooks, or MCP servers.

40 skills

0

dev-core

claude

The always-on engineering rules, core skills, and the tier and domain specialist agents. Requires the repo-docs plugin for repo grounding.

11 skills · 13 agents · 4 MCP servers · hooks

0

repo-docs

claude

Local semantic doc search, installed-package lookup and JS/TS file-impact tools for one repository. dev-core requires it.

2 commands · 1 MCP server · hooks

0

concise-output

claude

Always-on rules for how output reads: short and plain in anything a person sees, and only what was asked for in anything that leaves the machine.

1 skill · hooks

0

feedback

claude

Local feedback inbox MCP for the AI setup: collect_feedback records bugs, pain points, ambiguities, and ideas; read_feedback lists them so they can be acted on later. Stored as JSONL inside the plugin.

1 MCP server · hooks

0

fundamentals

claude

One skill, building-blocks: explains what is going on, what was built, or the answer to a question in plain words, for someone who was not in the session. For end-of-session handoffs that are actually readable.

1 skill

0

Similar plugins

superpowers

claudecodex

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

15 skills · hooks

obra/superpowers 316,836

CMEM Pro

claude

CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents

3 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

cli-anything

claude

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

agent-browser

claude

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain verified?

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 plugins12 plugins