claude plugins

2,654 tagged claude, measured the same way as everything else here.

Browse within: claude-code-plugin 319skills 164ai-tools 120plugins 98claudecode 97ai-coding 91claudecode-hooks 72commands 71claude-plugins 70claude-plugin 67claude-code-marketplace 66claude-code-plugins 62ai-skills 54claude-ai 51

rolling-context

409

NodeNestor/claude-rolling-context

Plugin Claude Code

Bundles 4 commands, 1 hook · 94 tokens together

Rolling context compression - old messages get summarized, recent messages stay verbatim. Never hit the context wall. Toggle it off per session with /rolling-context:off (or --global) when a session wants the full history - subagents follow the session that spawned them, and nothing already compressed is thrown away.

not rated 31 changed today A tokens not measured original MIT

octo

410

CES-Ltd/Lumi

Plugin Claude Code

Bundles 10 skills, 47 commands · 1,130 tokens together

v9.29.2 — Model defaults refreshed: Opus 4.7 for planning/strategy/security-review, GPT-5.4 for code-review/implementation. New GPT-5.4 prompting guide. Set OCTOPUSLEGACYROLES=1 to opt out. Run /octo:setup.

not rated 31 +1 3mo ago A tokens not measured original MIT

odoo-skills

411

mart337i/odoo-skills

Plugin Claude Code

Bundles 15 skills · 1,428 tokens together

odoo-skills. Agent skills for Odoo addon development and OCA module migration.

not rated 31 +1 3mo ago A tokens not measured

ai-native-toolkit

413

bjcoombs/ai-native-toolkit

Plugin Claude Code

Bundles 15 skills, 7 commands, 8 agents · 1,988 tokens together

Skills for AI-native development. /assess scores a codebase's readiness for AI agent contributors (0-8 layered contract model) and generates a Codecov-style complexity hotspot SVG plus a colour-blind-safe doc-navigability graph. /huddle runs structured multi-perspective deliberation using Six Thinking Hats with…

not rated 30 today A tokens not measured original Apache-2.0

claude-code-recap

414

noluyorAbi/claude-code-recap

Plugin Claude Code

Bundles 1 skill · 186 tokens together

Lists recent Claude Code sessions across every project with summaries, git branch, model, turn count, and a ready-to-paste resume command, and can re-open a whole working set in terminal tabs.

not rated 30 27d ago A tokens not measured original MIT

gitgud

415

MissingPackage/gitgud

Plugin Claude Code

Bundles 4 commands, 1 hook · 33 tokens together

Keep your coding skills sharp! Periodic manual coding challenges with gamification (streaks, achievements, skip system).

not rated 30 7mo ago A tokens not measured original MIT

jujutsu-skills

420

YPares/agent-skills

Plugin Claude Code

Bundles 2 skills · 132 tokens together

Skills for working with Jujutsu VCS, including core workflows and TODO-based development patterns.

not rated 30 +1 6d ago A tokens not measured original MIT

useosint

421

UseOSINT/Skills

Plugin Claude Code

Bundles 29 skills · 4,050 tokens together

Open-source intelligence tradecraft for agents: 29 investigation workflows covering people, companies, domains, images, phones, emails, usernames, crypto and vessels. Every workflow sets an authorised scope before collecting, sources each claim independently, and grades identity attribution separately from the claim…

not rated 31 1mo ago A tokens not measured original MIT

ynab-mcp-server

428

oliverames/ynab-mcp-server

Plugin Claude Code

Bundles 1 MCP server

YNAB MCP connector for budgets, transactions, categories, scheduled transactions, accounts, months, payees, and budget review workflows.

not rated 28 +3 yesterday A tokens not measured original MIT

nodesign

429

Xiaokebuyu/Nodesign

Plugin Claude Code

Bundles 8 skills · 1,413 tokens together

NoDesign design agent runtime — methodology skills + canvas templates.

not rated 28 +4 today A tokens not measured AGPL-3.0

sol

432

ozankasikci/sol-skill

Plugin Claude Code

Bundles 1 skill · 48 tokens together

Two frontier models, one job each. Claude plans and reviews; GPT-5.6 Sol writes the code via Codex CLI. The model that wrote the diff never grades it.

not rated 27 +1 changed yesterday A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: