Scheduler/launcher for Claude Code headless runs. Cron-scheduled jobs launch claude -p in a folder, with per-job model, reasoning effort, timeout, duplicate guard, missed-tick catch-up, log rotation, a process-level circuit breaker that treats a Claude usage-limit / transient API overload as a skip (not a failure) so.
Toolkit for writing sqlanvil data projects on PostgreSQL and Supabase. Corrects the Dataform/BigQuery priors that produce broken sqlanvil config, credentials, and DDL, and covers named connections (cross-warehouse sources via the auto-generated FDW bridge) and the introspect workflow.
★not rated 2
changed yesterdayA
tokens not measured
Guided architecture and infrastructure design workflow — from requirements gathering to code implementation — with interactive Mermaid diagrams, browser preview, and structured documentation.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Delegate research and deliverable generation to the Spine API. Claude auto-invokes this skill for multi-source research, competitive analyses, and polished document/slide/spreadsheet deliverables.
A persistent, indexed knowledge bank that stores learnings, ADR decisions, technical context, and session notes as markdown files inside your repo. Scales to thousands of files with fast grep-based index lookups. Integrates with Claude hooks for automatic session capture.
★not rated 2 4mo agoA
tokens not measured
originalMIT
Author draw.io diagrams that are readable and correct, then prove it by looking at them. Bundles a drawiotool script that exports any page to PNG through the desktop app's Electron binary so the agent can Read its own render, plus a linter for the defects a render cannot show. draw.io's desktop app, VS Code extension.
LmHeads A2A network plugin. Discover agents, invoke their skills, receive and respond to tasks. Skills CRUD + opaque delegation + end-to-end-encrypted vault for credential sharing. Run /lmheads:configure once to save your agent API key; the plugin reads it at boot.
Audit and prune Claude Code's persistent memory: verify stale claims against the project, catch contradictions and duplicates, then fix them through one confirmed docket, never silently rewriting what a memory means. Nudges at session start when the store needs attention; /garden schedule adds a scheduled dry-run…
★not rated 2 1mo agoA
tokens not measured
originalMIT
Audit and organize Claude Code permissions settings.
★not rated 2 7mo agoA
tokens not measured
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: