Graph-native memory, self-learning, and multi-agent coordination for Claude Code. Every session is captured, every pattern learned, every agent connected. WINDOWS AGENTS: git pull then .\setup.cmd -PythonOnly (never & setup.ps1). SessionStart banner shows install steps when needed.
Not Another Code Reviewer. A corporate review pipeline plugin: a Profiler casts an adaptive committee from a 23-persona library; peers review at the code level, departments hunt for gaps, leadership grades aim alignment.
★not rated 4 3mo agoA
tokens not measured
originalMIT
Policy enforcement, PII detection, and audit trails for Claude Code. Govern tool execution, scan outputs for sensitive data, and maintain compliance-grade records of every action.
★not rated 4
changed 6d agoA
tokens not measured
originalMIT
Integrate and debug the Hyper Solutions anti-bot API (Akamai, Incapsula, DataDome, Kasada) across the Go, Python, and JS/TS SDKs and raw REST. Bundles a request-debugging workflow: capture traffic via the powhttp MCP or analyze an exported HAR via the har-analyzer MCP, and apply a full rule set for…
Interactive HTML briefs for intermediate operator-agent discussion. Renders plans, specs, option comparisons, annotated reviews, and recommendations as a single self-contained .html file with inline decision controls and a copy-execution-prompt button, instead of a flat markdown wall.
★not rated 4 1mo agoA
tokens not measured
originalApache-2.0
Spec-first workflows and specialized agent roles for Claude Code. Design docs before code, structured deliberation, automatic previous-session recap on startup.
★not rated 4 1mo agoA
tokens not measured
originalMIT
The fifth universal primitive of the agent-plus framework. Mines real Claude Code session transcripts to surface repeated tool-use patterns, scaffolds them into project-scoped Claude skills (.claude/skills/ /), audits existing skills against a quality contract, and closes the loop with a cross-source feedback ag.
★not rated 4 2mo agoA
tokens not measured
originalMIT
Set the time your Claude 5-hour usage window starts each day. /sunrise:set creates a tiny cloud routine that primes your window so resets stay predictable.
★not rated 4 2mo agoA
tokens not measured
originalMIT
Ultra-advanced multi-agent orchestration system using RabbitMQ for distributed Claude Code instances. Enables team-like collaboration, task distribution, brainstorming, and result aggregation across independent sessions.
wise copilot — flat slash commands, a workflow engine with an SDLC agent roster (CEO/CTO/architect/engineer/QA/security/SRE/…), a session-mining self-improvement loop (mine + refine + reset), and shared scripts for everyday git / PR / ticket-planning / skill-authoring tasks. The /wise command is a natural-language he.
★not rated 4
changed yesterdayA
tokens not measured
originalMIT
One head, many tentacles: a task queue built on GitHub Issues where named agent workers (Claude Code, GitHub Copilot CLI, or any protocol-conforming tool) claim tasks, execute them, validate against acceptance criteria, and record the evidence — dependencies, expiring leases, and automatic dead-worker recovery…
Fear of Zeno. Makes the agent close tasks: no trailing offers, no hedged dones, no seeded TODOs. A deterministic stop gate catches loose ends the persona misses.
★not rated 4 1mo 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: