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 24d 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
Tracks every Claude Code session as a GitHub Issue in the repository you are currently working in. Creates a new issue per session, appends every prompt and response as comments.
★not rated 2 5mo agoA
tokens not measured
originalMIT
Real-time HUD statusline for Claude Code with API balance monitoring. Shows context health, tool activity, agent tracking, todo progress, git status, and DeepSeek/OpenAI/Anthropic balance tracking with low-balance warnings.
★not rated 2 27d 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 5d 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
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
Code governance for AI-written code — 289 free rules (every BLOCKER + the AI-code safety net), diff-aware gating, and an MCP server. $79 one-time unlocks the full 1,137-rule engine and all 67 Pantheon agents.
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 todayA
tokens not measured
originalMIT
Strategy maps and balanced scorecards — perspective design, causal-link strategy mapping, lead/lag measure selection, target-and-initiative setting, cascaded business-unit scorecards, and periodic reviews that test the strategy's causal theory, not just the numbers.
★not rated 2 2mo agoA
tokens not measured
originalMIT
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 2d 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 yesterdayA
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: