38,381 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Analyze, deduplicate, and restructure agent skills to follow agentskills.io best practices. Merges duplicate skills, extracts shared content into references, reduces SKILL.md sizes, and tracks original sources for update-then-recompact workflows. Use when the user mentions "compact skills", "deduplicate skills"…
Developer and Software Architect agent for architecture decisions, full-stack implementation, code writing, testing, infrastructure, CI/CD, and technical documentation. MUST BE USED for any coding, implementation, architecture, refactoring, or technical task. Use PROACTIVELY when the user needs code written, bugs…
Vetted playbook for delegating heavy/deep/boundary work to the Fable 5 model as a background subagent: avoid the silent Fable→Opus keyword fallback, verify the subagent's real model, handle Fable's slowness and mid-run latch, decompose big jobs, and verify Fable's output. Includes a fable-check.sh model verifier.
★not rated 3 3mo agoA
tokens not measured
originalMIT
Maps your projects into a living architecture graph: scan a directory of repos, sync the graph to the quasar-graph backend, then use it as a map — graph-aware context, cross-repo research, one-command stack cloning, and in-place graph editing.
★not rated 3 1mo agoA
tokens not measured
originalMIT
Launches and manages local Claude Code and Codex CLI sub-agents, plus orchestration-mode hooks for per-turn directives and deterministic Claude tool gates.
★not rated 3 6d agoA
tokens not measured
originalApache-2.0
Use Cursor's CLI (cursor-agent) from Claude Code to delegate coding tasks and review code, choosing the model per call. Shells out to your locally installed, authenticated cursor-agent (no data is sent to the plugin author). Registers session-lifecycle hooks and an optional, off-by-default stop-time review gate.
★not rated 3 2mo agoA
tokens not measured
originalMIT
Use when Claude Mail Bridge is installed (presence.json exists). Provides behavior guidelines for remote collaboration scenarios, including presence detection and MCP usage.
Quick AI reviewer for Agent Skills: checks structure, workflow, references, and links. Clear report without jargon, with a summary from an exhausted data scientist.
★not rated 3
changed todayA
tokens not measured
originalMIT
Turn your AI agents and automations into installable plugins and packages — 12 skills, 10 commands across 3 phases (ASSESS → PACKAGE → SHIP). Covers every major framework (LangChain, CrewAI, AutoGen, Pydantic AI, LlamaIndex, n8n, Flowise, Dify, ComfyUI, browser agents) and every distribution target (MCP servers…
★not rated 3 1mo agoA
tokens not measured
originalApache-2.0
Companion plugin for the AI Primer guidebook — environment setup, project creation, and workflow guidance for beginners building full-stack AI products.
★not rated 3 2mo agoA
tokens not measured
originalMIT
Pair Claude with the Codex CLI: mixed-model planning and implementation, adversarial reviews, delegated tasks, and background jobs.
★not rated 3
changed 9d agoA
tokens not measured
originalApache-2.0
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: