Keeps MCP-server config in sync between Claude Code and Claude Desktop via a SessionStart hook, and reports the manual steps for anything that can't be auto-synced.
★not rated 2 21d agoA
tokens not measured
originalMIT
A portable Claude Code engineering harness — plan → work → verify → feedback discipline as reusable agents, skills, and hooks, plus an introspect skill that tailors a .claude/ setup to any repo's tech stack.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Turn your idea into working code — Shipyard runs Claude Code through a spec-driven agile sprint lifecycle: discuss features, plan sprints, build with TDD, review, and ship.
★not rated 2 27d agoA
tokens not measured
originalMIT
Bifrost MCP gateway plugin for Claude Code and Claude Desktop: skill discovery, agent-driven memory, one-command onboarding, signed admin policy, and OAuth 2.1 for Desktop.
★not rated 2 21d agoA
tokens not measured
originalMIT
Adversarial audit suite: whole-repo codebase/docs/process/security audits, a diff-scoped change audit, an orchestrator that synthesizes one fixes backlog, and a human-gated fixing agent. Evidence labels, stable finding IDs, acceptance checks.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Throughline plugin: a PRD/TDD/ADR design-doc pipeline with phase-gate PRs, layered as a thin governance overlay on top of the official superpowers/pr-review-toolkit plugins (it owns governance; they own discovery + engineering). /prd-author requires an observable acceptance criterion per new requirement. /tdd-author…
★not rated 2 23d agoA
tokens not measured
originalMIT
Build true to spec, zero drift. A contract-first lifecycle: define a locked contract (the invariant), plan against the real codebase, build, and pass three adversarial reviews — enforced by a real gate script, with reconciliation to an independent gold figure, user-driven gates, a human sign-off, and clean…
★not rated 2
changed 2d agoA
tokens not measured
originalMIT
Statusline segment + prompt-submit guard for Claude Code's 5-hour and 7-day usage limits. Shows live usage %, and at a configurable threshold it blocks new prompts (with an override) so a long token-heavy task doesn't get cut off mid-run.
★not rated 2 2mo 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