Runtime-portable 5-agent quality gate for tier-1 text artifacts. Five role-conditioned LLM deliberators (Skeptic, Voice & Identity, Evidence & Calibration, Strategy & Stakes, Adjudicator) run in a 2-round async protocol with cross-read rebuttal. Returns one verdict — SHIP, REVISE, or HOLD — plus a revision brief and a.
★not rated 10 2mo agoA
tokens not measured
originalMIT
Vault your Claude conversations. Captures session decisions, artifacts, and context across Code, Cowork, and Chat. Organizes memory by project, skill, and persona. Never re-explain yourself again.
Convene a council of LLMs that independently propose, peer-review, rebut, vote, and synthesize a group-confirmed consensus answer — exposed as the ensembledebate tool plus an /ensemble command.
★not rated 10 3mo agoA
tokens not measured
originalMIT
Persistent memory with outcome-based learning for AI coding agents. Stores knowledge from coding sessions, learns which memories actually help, and gets smarter over time.
★not rated 10
changed 4d agoA
tokens not measured
originalMIT
Graph-engineered task driver for Claude Code. Classifies a task, decomposes it into a dependency graph of granular subtasks, topo-sorts it into waves, and executes each node in an isolated git worktree under an evidence-gated implement/validate loop. Runs entirely on the Claude Code CLI/subscription via claude -p wor.
★not rated 10
changed yesterdayA
tokens not measured
originalMIT
FiveM development orchestrator for QBox, QBCore, and ESX frameworks. Dynamically fetches natives, framework APIs, and guides to assets. Supports Lua and NUI (JavaScript/TypeScript).
AI-first engineering workflow with BDD living documentation. Lean PRD writing, Gherkin generation, and wireframe mockups for Product and Engineer roles.
★not rated 10 5mo agoA
tokens not measured
originalMIT
Generate importable Anki decks for language learning, with deep per-language reading accuracy (furigana, pinyin, on/kun) and auto-created references for new languages.
★not rated 10 3mo agoA
tokens not measured
originalMIT
Claude Code skill for building production AI agents with the Claude Agent SDK. Covers Python and TypeScript patterns for query(), ClaudeSDKClient, custom tools, hooks, subagents, and multi-agent orchestration.
★not rated 10 7mo agoA
tokens not measured
originalMIT
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: