claude

goodvibes

Structure-aware code intelligence, token/cost analytics with a self-contained HTML report, and registered HTTP/database access under an explicit trust boundary — 25 tools across three MCP servers (intel 15, analytics 7, connect 3).

6 on GitHubby Mike Davisv2.3.6MITupdated 2 months ago
/

Plugin goodvibes from marketplace goodvibes-market in mgd34msu/goodvibes-plugin. Commands read from the repo's manifest — 1 month ago.

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

What it installs

Skills (6)

  • goodvibes-memory

    Documents the .goodvibes/memory/ cross-session memory files (decisions, patterns, failures, preferences): what's written automatically, what you should read and write, and the exact JSON shape of each file. Load at the start of a task to check prior context, and before finishing to record what you l

  • intel-mastery

    Usage guide for the goodvibes intel server's 15 structure-aware tools (code_read, code_grep, code_glob, code_surface, code_safe_delete, api_routes, api_spec, api_validate, db_schema, component_tree, hook_dependencies, client_boundary, layout_analysis, scaffold, structural_edit). Load when working in

  • project-onboarding

    Step-by-step approach to mapping an unfamiliar codebase's architecture using the goodvibes intel server's analyzers before making changes to it. Load when starting work in a codebase you haven't worked in before.

  • review-scoring

    The refutation-based review rubric used by the refutation-reviewer agent and the Write-Review-Fix-Confirm (WRFC) workflow template. A defect list with severity, not a single pass/fail score. Load when reviewing a change or deciding whether a review's findings clear the bar to merge.

  • service-integration

    How to reach authenticated APIs and project databases through the connect trust boundary. Register a service or connection, store credentials safely, then call api_request or db_query. Load when a task needs an authenticated HTTP call or a live database query (not a public URL; use native WebFetch f

  • task-orchestration

    Decomposing work into parallel subagent tasks using native Workflow/Task tooling and the Write-Review-Fix-Confirm (WRFC) template. No background daemon, no runtime engine. Load when planning how to split work across multiple agents.

Slash commands (5)

  • /goodvibes:analytics

    View session analytics, generate the HTML analytics report, manage budgets, export data, manage tags, and sync sessions

  • /goodvibes:codebase-review

    Entry point for the Write-Review-Fix-Confirm (WRFC) workflow template: reviews the current diff with grounded checks first and a refutation-based defect list, fixes confirmed high/critical findings, and re-reviews the fix before reporting. - Bash - Task

  • /goodvibes:plugin

    goodvibes plugin management. Native dependency repair, health status, and optional prompt-chain install

  • /goodvibes:services

    Manage the connect service registry. Register API services and database connections, store credentials, set read-only vs write access, manage the destination allowlist, and report trust status

  • /goodvibes:setup

    Re-run the goodvibes native dependency install in the foreground. The manual repair path when the automatic background install did not finish

Subagents (4)

  • architect

    Architecture, planning, and codebase-onboarding specialist. Use to design an approach, break a task into a plan other agents can execute, or map an unfamiliar codebase before work starts.

  • engineer

    Full-stack engineer for backend and frontend implementation. APIs, databases, authentication, UI components, styling. Delegate concrete implementation work here once the approach is decided.

  • refutation-reviewer

    Refutation-based code reviewer. Actively tries to disprove that a change works, rather than confirming it looks fine. Use after implementation work to get an honest defect list before merging.

  • tester

    Testing specialist. Writes and runs tests that verify real behavior. Use after implementation work to establish honest, risk-based coverage rather than a coverage-percentage target.

MCP servers (3)

  • intel

    runs: node ${CLAUDE_PLUGIN_ROOT}/server/intel/index.cjs

  • analytics

    runs: node ${CLAUDE_PLUGIN_ROOT}/server/analytics/index.cjs

  • connect

    runs: node ${CLAUDE_PLUGIN_ROOT}/server/connect/index.cjs

Hooks (10)

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.mjs"

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start-open-mode.mjs"

  • Setup

    node "${CLAUDE_PLUGIN_ROOT}/hooks/setup.mjs"

  • SubagentStart

    node "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-start.mjs"

  • PostToolUseFailure

    node "${CLAUDE_PLUGIN_ROOT}/hooks/post-tool-use-failure.mjs"

  • PreToolUse

    node "${CLAUDE_PLUGIN_ROOT}/hooks/commit-guard.mjs"

  • SessionEnd

    node "${CLAUDE_PLUGIN_ROOT}/hooks/session-end.mjs"

  • Stop

    node "${CLAUDE_PLUGIN_ROOT}/hooks/stop.mjs"

  • SubagentStop

    node "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-stop.mjs"

  • PreCompact

    node "${CLAUDE_PLUGIN_ROOT}/hooks/pre-compact.mjs"

View source on GitHub goodvibes.sh

Similar plugins

telemetry

claude

Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.

anthropics/claude-code 155,476

Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations

24 skills · 1 command · 1 agent · hooks

ruvnet/ruflo 81,589

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

gitnexus

claudecodex

Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.

12 skills · 1 MCP server · hooks

abhigyanpatwari/GitNexus 48,482

azure

claude

Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.

44 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

Maintain goodvibes?

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 pluginslisted