Warns the main session as its own context fills, captures a wake packet before compaction, and reorients the session after it — so an autonomous orchestrator survives past one context window.
★not rated 2 18d agoA
tokens not measured
originalMIT
A connector for Japanese public business data, including company records, grants, tax information, financial filings, laws, government contracts, and trade data. It lets an AI agent quote these sources with citations.
★not rated 2 2mo agoA
tokens not measured
originalApache-2.0
Find and quantify cloud and CI spend waste from your coding agent. Costguard runs read-only billing checks (GitHub Actions, Supabase, Railway, Netlify, Neon), static CI/cron waste rules, dry-run-first auto-fixes for workflow files, and a monthly cost digest — all driven from your session via /costguard-audit…
★not rated 2 12d agoA
tokens not measured
originalMIT
Local-first codebase memory for coding agents: AST-aware context, durable decisions, failure records, review packs, and a local graph GUI. Twenty tools are advertised by default; writefile, patchfile, prompt compression, and bash are opt-in. Discipline protocols ship as MCP prompts rather than tools. Pre-2.0 tool nam.
★not rated 2 11d agoA
tokens not measured
originalMIT
Closes the memory loop mechanically: recall before changing code, recall before storing, and a turn that cannot end with an unmade decision left silent. Requires Node >= 23.6 (the hooks run TypeScript directly).
★not rated 2 1mo agoA
tokens not measured
originalApache-2.0
The most comprehensive Google Ads and advertising automation plugin for Claude Code. Buddy enterprise agent (Opus-powered), MCP servers for Google Ads + Ad Creative, 75 production skills across Google Ads, AI agent engineering, Claude mythos, software dev, security, infrastructure, productivity, web frontend, scientif.
A local commenting overlay for a website you're building (a static build or your local dev server) or a Markdown file, not public sites you browse. Click or tap any element (or select text) and leave typed or spoken feedback; comments persist to .feedback/, then you tell your agent 'PPF' (Please Process Feedback) to…
★not rated 2
changed 3d agoA
tokens not measured
originalMIT
Skills, agents, and commands for deploying, operating, and troubleshooting Ceph storage clusters — cluster setup, OSD/MON/MGR management, pool and CRUSH map configuration, health diagnostics, and day-2 operations.
Loads canonical knowledge of Requirements Engineering, Business Analysis, and Professional Ethics into any Claude session. Built from the IFPB ERS course material (Prof. Dr. Juliana Dantas Ribeiro Viana de Medeiros) plus the canonical bibliography (Sommerville, Pressman, Wiegers, Cohn, Robertson, Hull, Falbo, BABOK v3.
★not rated 2 2mo agoA
tokens not measured
CC-BY-SA-4.0
LLM-based semantic analysis for false-positive test detection. Applies the J1-J6 judgment framework across Python, TypeScript, JavaScript, and Robot Framework, plus semantic patterns no static tool can see.
★not rated 2 todayA
tokens not measured
originalMIT
Live observability + an agent (MCP) surface for Blender -> glTF pipelines. Streams Claude Code activity to the hologram dashboard, exposes four read-only asset tools (listassets, inspectasset, tailevents, pipelinestatus) plus a non-destructive renderasset, and bundles guided skills (start, inspect, check, status.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Cross-session, cross-device memory for Claude Code. Markdown-first captures, vector-backed recall. Points at any universal-memory server — local Docker, remote self-hosted, or cloud-backed. Auto-starts the server on demand when configured to.
★not rated 2
changed 4d agoA
tokens not measured
originalMIT
Turns a brief plus a folder of reference images into an optimal, credit-aware Higgsfield pipeline. Shows an HTML process preview as a mandatory approval gate before spending any credits, then executes stage-by-stage with auto-verification, human gates, and zero-credit deterministic text/dimension overlays.
★not rated 2 29d agoA
tokens not measured
originalMIT
★not rated 2 2mo 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: