Best autonomous loops skills for Claude Code, Codex and other agents.

Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.

cursor/plugins

Runs a bounded, source-grounded research loop that drafts a cited dossier and can propose a separately reviewed merge into an Obsidian vault.

AgriciDaniel/claude-obsidian

Runs an autonomous modify, verify, keep-or-discard loop against any metric, with subcommands for planning, debugging, fixing, security audits, shipping and more.

uditgoenka/autoresearch

Teaches the Swarms Python framework: the Agent class, tools, loops, memory and multi-agent structures such as sequential, concurrent and graph workflows.

kyegomez/swarms

Runs an unattended iterate-until-verified loop in which a user-set verify command, not the agent's own claim, decides when the task is finished.

tanweai/pua

Takes a short product idea through requirements, design, planning, parallel implementation, QA cycles and multi-reviewer validation to produce working code.

Yeachan-Heo/oh-my-claudecode

This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve…

guanyang/open-agent-hub

Installs Loop Engineering into a project through the single @cobusgreyling/loop CLI, scaffolding a report-only loop and a readiness score.

cobusgreyling/loop-engineering

Discover, find, compare, audit, repair, adapt, craft, run, debrief, save, and prepare repeatable AI-agent loops for publication.

Forward-Future/loopy

Pushes an agent to exhaust every option, investigate before asking and take initiative beyond the literal request, instead of giving up or waiting passively.

tanweai/pua

Diagnoses surprising LoopX behavior, such as stale recommendations or tiny progress, assigns it to the responsible layer and repairs it at the lowest durable level.

loopx-project/loopx

A skill your agent uses when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain.

DenisSergeevitch/agents-best-practices

Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.

ksimback/looper

Post to and read from the A1 Agent Board — a public, auditable, permanent message board for AI agents.

hyperspaceai/agi

Use Zeroshot to prepare, run, observe, or troubleshoot explicit multi-agent software work locally or on Zeroshot Cloud.

the-open-engine/zeroshot

Detects which autonomous OMG mode is currently active - Autopilot, Ralph, Ultrawork, UltraQA, Team or Self-Improve - and shuts it down cleanly.

zereight/gitlab-mcp

Set up, resume, inspect, or pause a measured experiment loop in Claude Code or Codex.

drivelineresearch/autoresearch-claude-code

Re-grounds a long-running agent in the current product outcome by running a path-based trace to the root of its topology and work trees.

mvschwarz/openrig

Runs the plan, implement and review pipeline detached in fresh headless sessions, looping review and fix until the pull request is clean.

Wirasm/prp

Builds a website page by page with Stitch in an autonomous loop, passing a baton file from one iteration to the next that names the next page and prompt.

google-labs-code/stitch-skills

Triage improvement work and run or resume accepted measured loops in a local project.

TheGreenCedar/codex-autoresearch

Watches an open GitHub pull request over time, routing review comments and CI failures to other skills until the PR is ready to merge.

EveryInc/compound-engineering-plugin

Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.

fynnfluegge/agtx

Runs an autonomous improvement loop on a repository: agents propose and execute plans, a tournament picks the winner by benchmark, and each round is recorded and plotted.

Yeachan-Heo/oh-my-claudecode

Role playbook for a LoopX worker running an auto-research lane, with execution checklists, artifact contracts and stop conditions.

loopx-project/loopx

Runs one improvement mission as a bounded loop: each round makes a change, runs a strict JSON evaluator, logs the decision in markdown and continues until a max runtime is hit.

Yeachan-Heo/gajae-code

Runs a detached, resumable loop that plans, implements, opens a PR, reviews and fixes a feature across headless CLI sessions until the review is clean.

Wirasm/prp

Explain the IM+Agent framework: create+send as minimal primitives, IM system vs agent loop separation, message vs llmHistory, and the recursive property.

chmod777john/swarm-ide

Build high-quality /goal commands for OpenAI Codex CLI 0.128+ that maximize audit-friendliness and minimize false-completion.

win4r/goal-prompt-builder

创建、修改并验证可安装的 Lexora 桌面插件，包括工作台装饰、导航与面板、文件阅读工具、控件样式、网络查询、通知和定时命令。也响应 $plugin-creator。普通任务执行、使用现有插件、其他产品的插件开发不属于此技能。

useLexora/Lexora

Autonomous agent loop for completing features. An agent skill from julianromli/opencode-template.

julianromli/opencode-template

A production-grade framework for long-running, autonomous agents based on Harness Engineering principles.

thu-nmrc/OpenHarness

Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.

10xChengTu/harness-engineering

Drafts and reviews /goal prompts for long-running autonomous agents, turning a vague request into a completion contract with outcome, evidence, constraints and a stop condition.

Michaelliv/pi-goal

Record real OpenAI/Anthropic HTTP back-and-forth (requests + responses, including streaming text/event-stream) and print paste-ready Swift fixtures for SwiftAgent unit tests (ReplayHTTPClient) using…

SwiftedMind/SwiftAgent

Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness.

pydantic/pydantic-ai

A skill your agent uses when a contributor wants to create, repair, or complete an OpenRSI-Index AutoResearch task proposal grounded in a remote model-development repository, including…

OpenRSI-Foundation/OpenRSI-Index

Repeats a long task as a series of scheduled wake-ups, each re-entering with fresh context and calling harness-work for one task per cycle.

Chachamaru127/claude-code-harness

Run and debug Preloop local CI — GitHub Actions-compatible workflows executed in one isolated microVM per job (smolvm/libkrun).

preloopdev/preloop

A skill your agent uses when optimizing or generating a CUDA megakernel for a HuggingFace Llama-family model with AutoMegaKernel (AMK), drives the correctness-gated propose - eval - keep/revert loop…

RightNow-AI/AutoMegaKernel

A skill your agent uses when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a generational evolution where parallel…

gaasher/Agent-Loop-Skills

AI project OS for autonomous loop, automated orchestration, and rule-driven execution.

Peiiii/AgentVerse

Run the hive experiment loop — autonomous iteration on a shared task.

rllm-org/hive

Full ascent-research CLI — incremental, resumable research sessions driven from a Claude Code or Codex instance.

actionbook/ascent-research

Runs the `autoctx` CLI to improve an approach to a task over several generations, score or refine a single output and inspect what a run produced.

greyhaven-ai/autocontext

A skill your agent uses when a repeatable task must become a bounded Trigger - Execute - Verify - State loop, scheduled automation, goal agent, or metric-driven research cycle.

Mark393295827/third-brain-v7-skills

TanStack AI (alpha) provider-agnostic type-safe chat with streaming for OpenAI, Anthropic, Gemini, Ollama.

secondsky/claude-skills

Splits a large goal into a tree of parallel Cursor cloud agents, with planners, workers and verifiers coordinated by a script and reporting through structured handoffs.

cursor/plugins