Coding harness configs and SDKs

Skill packs, slash-command libraries, meta-prompting frameworks, and official SDKs that give you the harness (the agent loop, planning, memory, hooks) without bundling a specific IDE or CLI shell.

#ProjectStarsTierOSSDescription
1superpowers
memoryide
265kcomplexPerformance-oriented harness pack for Claude Code, Codex, OpenCode, Cursor: skills, instincts, memory, security, research-first workflows. Treats harness engineering itself as the performance lever.
2Anthropic Skills
166kmostly simpleAnthropic's official Agent Skills repository: SKILL.md-based folders (instructions, scripts, resources) Claude dynamically loads on Claude Code, Claude.ai, and the API. The reference for progressive-disclosure skill packs in 2026.
3GStack
typescript
126kslightly complexGarry Tan's Claude Code skill stack: 23 slash-command modes (CEO/eng/design review, QA, ship, browse, retro, …) that structure one assistant as a virtual engineering team. Daily driver while running YC.
4addyosmani/agent-skills
workflowide
81.3kmostly simpleAddy Osmani's production-grade skill pack: 24 engineering skills and 4 specialist agent personas that encode senior-dev workflows (spec through deploy) across 70+ coding agents including Claude Code, Cursor, and Copilot. The **harness** contribution is the skill/workflow layer, not a new agent loop.
5awesome-claude-code
51.5ksuper simpleLarge community-curated index of Claude Code skills, slash commands, status lines, and plugins—resources for extending the harness, not a harness itself, but the most-followed catalog of the genre.
6wshobson/agents
multi-agentcliide
38.4ksuper simpleCross-harness marketplace of drop-in subagents and skills for Claude Code, Codex CLI, Cursor, OpenCode, and Copilot; specialized, production-ready agent definitions you install rather than hand-write.
7planning-with-files
memory
25.9kmostly simpleSkill for persistent, file-based planning across long-running coding-agent sessions: crash-proof markdown plans, session recovery after `/clear`/compaction, and a deterministic completion gate—Manus-style planning as a drop-in **harness** layer via the Agent Skills standard.
8SWE-agent
memoryevalspython
20kslightly complexLM-driven harness built for SWE-bench: edit state, command execution, and issue-focused loop—the reference agent stack next to the benchmark itself.
9Claude Agent SDK
mcpmemorypythontypescript
7.8kcomplexOfficial Anthropic SDK (Python + [TypeScript](https://github.com/anthropics/claude-agent-sdk-typescript), [demos](https://github.com/anthropics/claude-agent-sdk-demos), [quickstarts](https://github.com/anthropics/claude-quickstarts)): built-in tools, MCP, long-running coding agents with session bridging.
10get-shit-done
clipython
7.6kmostly simpleGoal-backward planning and wave-based execution over fresh context windows; avoids context rot by design. Python/JS meta-prompting for Claude Code, OpenCode, Gemini CLI.
11agents-cli
evalscli
5.5kmostly simpleGoogle's official CLI and skill pack that layers agent-creation, evaluation, and deployment skills on top of whatever coding assistant you already run, rather than shipping its own agent loop—the **harness** as a config/skills add-on, not a new runtime.
12skillhub
localcliide
4.8kmostly simpleiFlytek's self-hosted registry for publishing, versioning, and governing agent skill packages—the **harness** config layer treated as an enterprise artifact store rather than a CLI or IDE shell.
13Meta-Harness
1.4kslightly complexReference implementation from the Meta-Harness paper: an academic testbed for harness-engineering research, not a product—useful as a citation-grade baseline rather than something you'd run in production.
14RepoMaster
workflowpython
541slightly complexRepo-scoped research harness: builds function-call and module-dependency graphs to explore only what's needed; large relative gains on MLE-bench and GitTaskBench with lower token use.
15AutoHarness
memorymulti-agentprovider-agnosticpython
363super simpleLightweight governance harness: wraps any LLM client in ~2 lines for automated harness engineering—6–14 step pipeline, YAML constitution, risk-pattern matching, session persistence with cost tracking, multi-agent profiles.
16LoopTroop
typescript
106mostly simpleConfig layer that chains LLM councils for planning, Ralph loops for iterative refinement, and OpenCode worktrees for shipping. The **harness** contribution is the council → loop → worktree pipeline; OpenCode underneath executes.
17pmstack
evals
8super simpleClaude Code config for AI product managers: CLAUDE.md plus skills for competitive analysis, PRD-from-signal, metric frameworks, stakeholder briefs, and agent eval design. "GStack for PMs."