ralph-loop
claudeInteractive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.
3 commands · hooks
Don't say done — pass the close gate. One markdown contract per task; the gate refuses to close while planned steps are unchecked, acceptance criteria lack evidence, or validation is failed/blocked.
Plugin capsulet from marketplace capsulet in ictseoyoungmin/hadara-capsulet. Commands read from the repo's manifest — 1 month ago.
capsuletA pocket HADARA task capsule — one markdown contract plus one zero-dependency close gate that stops you from saying "done" before you can prove it. Use this skill for any multi-step, verifiable coding or writing task where premature completion claims are costly: bug fixes that need tests, refactors
/capsulet:capsulet-checkRun the close gate on the current capsule — reports every blocker that prevents an honest "done
/capsulet:capsulet-closeClose the capsule — re-runs the gate and stamps Status Done (or Partial when follow-ups remain)
/capsulet:capsulet-listList all capsules with their status and, for open ones, the resume pointer for picking work back up
/capsulet:capsulet-newOpen a new task capsule — write the contract (Goal, Scope, Acceptance) before any work starts
Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.
3 commands · hooks
Tenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results
6 skills · 6 commands · 4 agents · 1 MCP server
Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.
44 skills · 1 MCP server
Cedar policy enforcement + Ed25519 signed receipts for every Claude Code tool call. First cryptographic governance plugin — decisions are policy-gated before they run and every decision produces a tamper-evident receipt verifiable offline.
1 skill · 2 commands · 2 agents · hooks
Evidence-backed BioPharma research workflows over Maven Bio's drug, trial, company, and deal knowledge graph. Skills for competitive pipelines, indication landscapes, asset profiles, deal and financing activity, and evidence synthesis grounded in FDA, SEC, clinical, and press sources. Requires a Maven Bio account.
16 skills · 1 agent · 1 MCP server
Use Codex from Claude Code to review code or delegate tasks.
3 skills · 8 commands · 1 agent · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.