The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

Claude Code plugin — code quality hooks, knowledge graph, impact-aware reviews, decomposition enforcement. Babysitter for your AI's code quality.

Spec-driven development for Claude Code, layered on OpenSpec. You read one spec; parallel agents ship it to a tested commit.

Open-source skills for designing and reviewing software with AI agents

AI-powered spec generation and review using multi-repo code graph intelligence for backend teams that ship to production.

Reduce supplied context and check caller-declared, source-specific exact evidence retention.

Linter for AI agent configurations. Validates SKILL.md, CLAUDE.md, hooks, MCP, and more.

Static analysis scanner for MCP server code and multi-tenant SaaS applications. 57 deterministic rules covering tenant isolation, tool visibility, cache key scoping, RLS, IDOR, and credential vault isolation. MCP server for AI agent integration.

Keep the state. Change the model. Shared context and a multi-model panel across Claude Code, Codex, Cursor, Antigravity, GitHub Copilot, and Muse.

Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Docker deployment.

Claude Code plugin that stops Claude writing like an AI. 29 researched patterns, loaded every session and checked on every file write.

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.

Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts.

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes

Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.

The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 14 agents · 21 skills · 8 workflows. Fail-closed gates, test honesty, anti-anchored review.

Your AI forgets every session. Give it a memory it can trust: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code, Codex, Cursor and any MCP client, with an immutable audit log and a token ledger. Open source, self-hosted, no cloud.

DeepSeek Harness session and workspace manager —— Workspaces: archive and visibility. Sessions: move, migrate presets, delete, favorite, review later, prioritize, tag, and annotate. Batch operations. | DSH 会话与工作区管理——工作区：归档与显示。会话：跨工作区移动、预设迁移、删除；收藏、待回看、优先级、标签、备注。批量操作。

Enables capturing a tamper-evident, hash-chained local record of every AI agent tool call — both the decision before a tool runs and its outcome — so you can review what the agent actually did in order, detect edits, deletions, or reordering at the exact index, and export a signed evidence pack any third party can verify with no installs.

Comprehensive guide for Go database access — parameterized queries, struct scanning, NULLable columns, transactions, isolation levels, SELECT FOR UPDATE, connection pool, batch processing, context propagation, and migration tooling. Use when writing, reviewing, or debugging Golang code that interact

DeepSeek Harness plugin for previewable cross-preset session migration. Fixed-schema handoffs preserve state, source-model intent, and unresolved images; the original session stays untouched.

Enables AI assistants to access a user's Pusan National University Moodle-based LMS account, browsing courses, materials, notices, assignments, grades, calendars, and Q&A, downloading course files, and performing write actions like submitting assignments after a confirmation preview. It combines the official Moodle Web Service API with authenticated session scraping for the ubboard notice/Q&A boards.

Golang skills orchestrator — always active on any Golang coding, review, debug, or setup task. Reads the task context and loads the most relevant skills from samber/cc-skills-golang, often multiple at once: writing a gRPC service loads golang-grpc + golang-testing + golang-error-handling; debugging