Durable goal-following for Claude Code: contracts with definition-of-done, subagent judge gates, executor-subagent chain execution, and adaptive missions — with all state mechanics executed by a tested CLI and invariants enforced by hooks. Inspired by OpenAI Codex /goal and the Ralph loop pattern.
Multi-agent orchestration plugin - a virtual dev crew with intelligent model routing (Opus/Sonnet/Haiku), lite mode, 3-layer codebase indexing, auto-skill selection, task history, rollback, and custom agents.
★not rated 13 5mo agoA
tokens not measured
originalMIT
Spec-driven agentic engineering as graph engineering: shape (pitch) -> decide (ADR) -> execute (delegated cycle with adversarial review) -> measure -> eval, with /graph to fan work out across a fleet of subagents (diamond / router / verifier / cycle). Dark-launch eval-gated. Distilled from a real practice.
★not rated 13 1mo agoA
tokens not measured
originalMIT
Advisor Loop — an autonomous loop for long, multi-day work: an independent advisor certifies mission completion and the anchor survives every compaction, on subscription-safe agents.
★not rated 13
changed 8d agoA
tokens not measured
originalApache-2.0
Orchestrator plugin that weaves planning-with-files, DESIGN.md, memory routing, agent teams, and session handoff into one composable contract for any modern coding agent. Composes existing skills without altering their core. Includes code-to-DESIGN.md harvest and critique.
★not rated 13 4mo agoA
tokens not measured
originalApache-2.0
Security-audits installed Claude Code skills and marketplace plugins for data capture, secret exfiltration, prompt injection, and malicious code. Always leads with a disclaimer that detection cannot be guaranteed complete.
A multi-agent meta-skill for Codex, Claude Code, Kimi Code, and other coding agents. It turns each project, machine, device, API, and MCP server into a lightweight, self-improving skill: work through / , auto-log moments that matter, and reflect logs into lean lessons so the next session starts smarter.
★not rated 13
changed yesterdayA
tokens not measured
originalMIT
The PM playbook for building AI agent products. 12 slash commands covering the full agent product lifecycle — from 'should this be an agent?' through eval design to production safety. Grounded in primary sources from Anthropic, OpenAI, Karpathy, Hamel Husain, Linus Lee, and real production deployments.
★not rated 13 3mo agoA
tokens not measured
originalMIT
Fable 5's working loop for hard tasks: decompose by verification boundaries, verify against the world, choose next by plan-change. Includes scout + refuter agents and a preflight script.
Connect Claude Cowork to Claude Code on your own computer (macOS or Linux). Cowork hands a task to a local Claude Code agent (and can run approved scripts too); the bridge is idempotent, streams progress, and is token-protected. Install with one command; it sets up a global Cowork skill so every session connects…
★not rated 13▲
+1 7d agoA
tokens not measured
originalMIT
Turn any Claude Code session into a long-horizon master orchestrator: pick the right dynamic-workflow paradigm and keep the main thread productively advancing across compaction and sessions.
Syv.ai's curated agentic-coding skills collection — the practical companion to the Agentic Coding Playbook. A best-of-breed set of skills for planning, execution, quality, and verification with any agentic coding harness.
The horizontal layer of the insight-wave marketplace — it owns the shared workspace state the vertical business plugins consume. Manages shared infrastructure (env vars, settings), MCP server installation and Desktop config patching, theme management, theme picker, plugin discovery, workspace health, an interactive…
★not rated 13▲
+1
changed todayA
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: