Back to Discover

ccc

connector

lexfrei

Claude Code Companions — external marketplace for Claude Code plugins: agents, skills, and MCP servers

View on GitHub
10 starsBSD-3-ClauseSynced Aug 17, 2026

Install to Claude Code

/plugin marketplace add lexfrei/ccc

README

Claude Code Companions (CCC)

External marketplace repository for Claude Code plugins.

Installation

First, add the marketplace:

/plugin marketplace add lexfrei/ccc

Then install any plugin:

/plugin install <plugin-name>@claude-code-companions

Or browse available plugins interactively via /pluginDiscover tab.

Updating

Update all plugins from the marketplace:

/plugin marketplace update claude-code-companions

Update a specific plugin:

/plugin update <plugin-name>@claude-code-companions

Or enable automatic updates: /pluginMarketplaces tab → select claude-code-companionsEnable auto-update.

Plugins

Skills

The ten standalone agent plugins are gone. Nine of their agents ship inside become, renamed to their craft; the tenth was dropped. The old-to-new mapping is in its README.

PluginDescription
review-toolkitCode review pipeline: branch review with merge-base attribution (only defects the diff introduced, worsened, or interacts with block; pre-existing ones are reported separately and never dropped), churn diagnostics for review loops, PR review with a readiness gate (fix-CI / fix-conflicts, no verdict), a value/design gate (should this change exist at all — value vs maintenance cost), dual-model analysis (Claude + Codex), and GitHub PR review publishing with evidence-based verification
address-pr-commentsClose out unresolved review comments across one or more PRs — verify, fix with auto-pushed signed commits (one per thread), post user-approved replies, restore original branch
git-toolsGit workflow utilities: fork refresh and repo setup with branch protection
gennameGenerate a /rename command from type, title, and optional PR number
tldrprGenerate plain-text TLDR summaries for PRs, ready for Slack
learnAnalyze the current session and extract key learnings into CLAUDE.md and memory
renovate-checkRun Renovate locally in dry-run mode, research migration guides, apply selected updates
agent-fatherInteractive guide for creating Claude Code subagents following official documentation standards
billy"Where's the proof, Billy?" — stop and prove a claim with deep investigation
m4b-audiobookAssemble m4b audiobook from audio files with chapters, metadata, and cover art
saySpeak text aloud using macOS TTS with automatic voice selection
slack-formatterCopy markdown to macOS clipboard as rich HTML + plain-text fallback, ready for Cmd+V into Slack with formatting preserved
helm-add-gwapi-routeAdd or modernize Gateway API *Route templates (HTTPRoute/GRPCRoute/TLSRoute/TCPRoute/UDPRoute) in a Helm chart. Auto-detects add vs update mode per route kind; applies current best practices (named rules, typed filters, optional BackendTLSPolicy). File edits only — no git operations
pore-analysisMeasure porosity, pore size/shape, lattice period and ordering (psi6, Voronoi, radial g(r) + orientational correlation length) from top-view SEM images of porous films such as anodic aluminium oxide. The agent reads the image to calibrate and crop; a Python core does the morphometry and flags results that contradict physics. Vision decides, Python computes — no hardcoded autodetect
cleanupLocal disk cleanup: stale git worktrees, dead personal forks, Docker prune (incl. non-default buildx builders and VM disk trim), Go caches, and Homebrew — each report → confirm → execute with interactive prompts, plus a cleanup-all pipeline. Paths are asked, never hardcoded
becomeSession role switches plus the specialist agents they run. Manager (/become:manager): lead of a subagent fleet — brief teammates, delegate whole loops, approve their output inside the delegated scope, integrate by ground truth, report upward in short digests. Bundled workforce, spawnable as teammates or callable as @agent-become:<name>: architecture (technical decisions, .architecture.yaml), go, python, templ (Templ + HTMX), kubernetes (manifests, ArgoCD), helm (charts), containers (image builds), quality (lint, tests, security, then commit and push), hygiene (AI-artifact cleanup)

MCP Servers

PluginDescription
mcp-lokiGrafana Loki — LogQL queries, label discovery, series exploration, index statistics
mcp-transmissionTransmission — torrent management, session stats, queue and bandwidth control
mcp-tgTelegram — MTProto client API, messaging, contacts, groups, channels, media handling

Hooks

PluginDescription
comment-hygieneSessionStart hook that injects code-comment discipline into every session — every comment must earn its place: say what the code cannot, never duplicate it; bans narration, changelog comments, reviewer asides, signature-restating docstrings, and leaky provenance
golangci-lintAuto-run golangci-lint on package when Go files are edited
md-no-hardwrapPreToolUse hook: reject Write/Edit on markdown files when a paragraph spans more than one line — enforces "one continuous line per paragraph" so renderers wrap to viewer width instead of fighting hardwraps in the source
worksyncDaily work-sync markdown log — PostToolUse hook captures gh pr/issue create/merge/close automatically, companion skill logs research/ops/checkpoint events (prompts for vault path on install, works with Obsidian, Logseq, or plain markdown)

License

BSD-3-Clause

Rendered live from lexfrei/ccc's GitHub README — not stored, always reflects the source repo.

24 Plugins

NameDescriptionCategorySource
review-toolkitComprehensive 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.productivity./skills/review-toolkit
address-pr-commentsEnd-to-end closeout of unresolved review comments across one or more GitHub PRs — verifies each thread, fixes legitimate findings with one signed commit per thread, posts approved replies, restores original branchproductivity./skills/address-pr-comments
git-toolsGit workflow utilities: fork refresh and repo setup with branch protectionproductivity./skills/git-tools
gennameGenerate a /rename command from type, title, and optional PR number — pure string formatting utilityproductivity./skills/genname
tldrprGenerate concise plain-text TLDR summaries for GitHub Pull Requests, ready for pasting into Slack or other messengersproductivity./skills/tldrpr
learnAnalyze the current session and extract key learnings into CLAUDE.md files and memory systemproductivity./skills/learn
renovate-checkRun Renovate locally in dry-run mode to discover available dependency updates, research migration guides for major bumps, and apply selected updatesdevelopment./skills/renovate-check
agent-fatherInteractive skill for creating well-structured Claude Code subagents following official documentation standardsdevelopment./skills/agent-father
billyWhere's the proof, Billy? — stop and prove a claim with deep investigationproductivity./skills/billy
m4b-audiobookAssemble m4b audiobook from audio files with chapters, metadata, and cover art using ffmpegproductivity./skills/m4b-audiobook
saySpeak text aloud using macOS TTS with automatic voice selectionproductivity./skills/say
slack-formatterCopy markdown to macOS clipboard as rich HTML + plain-text fallback, ready for Cmd+V into Slack with formatting preservedproductivity./skills/slack-formatter
helm-add-gwapi-routeAdd or modernize Gateway API *Route templates (HTTPRoute/GRPCRoute/TLSRoute/TCPRoute/UDPRoute) in a Helm chart, mirroring its ingress conventions. Auto-detects add vs update mode per route kind, applies current best practices (named rules, typed filters, optional BackendTLSPolicy). File edits only — no git operations, no push, no PRinfrastructure./skills/helm-add-gwapi-route
pore-analysisMeasure porosity, pore size/shape, lattice period and ordering (psi6, Voronoi coordination, radial g(r) and orientational correlation length) from top-view SEM images of porous films such as anodic aluminium oxide. The agent reads the image to calibrate and crop; a Python core does the morphometry and flags results that contradict physics. Vision decides, Python computes — no hardcoded autodetect, so it adapts to different instruments and scale-bar formats.science./skills/pore-analysis
mcp-lokiMCP server for querying Grafana Loki logs — LogQL queries, label discovery, series exploration, and index statisticsmonitoring./mcp/mcp-loki
mcp-transmissionMCP server for managing Transmission BitTorrent client — list, add, remove, start, stop torrents, session stats, queue and bandwidth managementproductivity./mcp/mcp-transmission
golangci-lintAuto-run golangci-lint on package when Go files are editedquality./hooks/golangci-lint
macro-claudeSession status hooks for the macro-claude macropad plugin — writes per-session JSON so the MX Creative Console shows live Claude Code stateproductivity./hooks/macro-claude
worksyncAutomatic daily work-sync log — PostToolUse hook captures gh pr/issue create/merge/close, and a companion skill lets Claude log research/ops/checkpoint events into a dated markdown note (feeds standups via Obsidian/Logseq/plain markdown)productivity./hooks/worksync
comment-hygieneSessionStart hook that injects code-comment discipline into every session — every comment must earn its place: say what the code cannot, never duplicate it; bans narration, changelog comments, reviewer asides, signature-restating docstrings, and leaky provenancequality./hooks/comment-hygiene
md-no-hardwrapPreToolUse hook: reject Write/Edit on markdown files when a paragraph spans more than one line. Enforces 'one continuous line per paragraph' so renderers wrap to viewer width instead of fighting hardwraps baked into the sourcequality./hooks/md-no-hardwrap
mcp-tgMCP server for Telegram Client API (MTProto) — messaging, contacts, groups, channels, media, stickers via user accountproductivity./mcp/mcp-tg
cleanupLocal disk cleanup utilities: stale git worktrees, dead personal forks, Docker prune (incl. non-default buildx builders and VM disk trim), Go caches, and Homebrew — each runs report → confirm → execute with interactive prompts, plus one orchestrating pipelineproductivity./skills/cleanup
becomeSession role switches plus the specialist agent workforce they run. Roles: manager — turn the session into the lead of a subagent fleet that briefs teammates, delegates whole loops, approves their output inside the delegated scope, integrates by ground truth, and reports upward in short digests instead of executing directly. Bundled agents, spawnable as fleet teammates or callable directly as @agent-become:<name>: architecture (technical decisions and .architecture.yaml), go, python, templ (Templ and HTMX frontend), kubernetes (manifests and ArgoCD), helm (charts), containers (image builds), quality (lint, tests, security, then commit and push), hygiene (AI-artifact cleanup)productivity./skills/become

0 Comments

Login required
Log in to post a comment or update on this repo.

No comments yet — be the first to share an update.