Plugin marketplace
Skill packs and plugins for Claude Code, published by Entelligentsia
Add this marketplace
Then install any plugin below by name — each page has its exact command.
Problems in this repo's manifests
13 skills for agent harness components — memory/compaction, session persistence, prompt caching, subagent orchestration, sandboxing, permissions, streaming, concurrency, telemetry, hooks, workspace state, model routing, rate limiting
13 skills
Commit-time clean-code review gate — blocks unreviewed commits, reviews the staged diff against a layered rubric, and resolves findings through a single apply/manual/approve decision; silent when there is nothing to report
4 skills · 4 commands · 1 agent · hooks
10 skills covering all 23 GoF patterns plus enterprise and DDD patterns
10 skills
9 skills for LLM integration patterns — RAG, tool use, agents, guardrails, tool synthesis
10 skills
10 skills for Three.js 3D development
10 skills
8 skills for Meta Quest PWA XR engineering
8 skills
In-browser annotation overlay for HTML/Markdown/text documents; click Apply in the browser to have Claude Code apply edits to source within ~60s
1 skill · 4 commands · hooks
Auto-scans newly installed Claude Code plugins for prompt injection, malicious hook scripts, and data exfiltration
1 skill · 1 command · hooks
WalkInto.in virtual-tour platform and helpdesk — profile, 360 tours, knowledge base, and the support ticket lifecycle; bundles the WalkInto MCP server (13 tools) via a stdio bridge that reuses the plugin login token
1 skill · 1 MCP server
Report Claude Code token usage and equivalent Anthropic API cost by model for any date range from local session transcripts — dedup-accurate, cache priced at real per-entry TTL; the only place subscription usage is visible
1 skill
Audit a project for developer tooling gaps (LSP, AST, test runners, type checkers, linters, debuggers, dep graph) and recommend exact install steps to make Claude Code most effective
1 skill
Freshdesk helpdesk API skill — tickets, contacts, companies, knowledge base (Solutions), webhooks, and automation
1 skill
Evaluate whether the lean-ctx MCP saves more context tokens than it costs, using your Claude Code session transcripts — per-call counterfactual for ctx_read, observational baseline for ctx_shell, net token ledger after overhead
1 skill
Report forge-cli orchestrator run token usage and cost by model / project / sprint / phase for any date range, read from the central transcript archive (~/.pi/forge-cli/transcripts/) — the only place forge run usage is visible; uses the authoritative per-phase cost forge recorded at run time
Shows how many plugins this repo ships, and links here.