Autonomous loops

Takes a request all the way through without stopping, routing it to Compound Engineering skills so that a code change ends as an open pull request.

EveryInc/compound-engineering-plugin

Runs a persistent Ouroboros loop that repeats background evolve_step generations on a lineage until QA passes, evolution converges, or you cancel.

Q00/ouroboros

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

affaan-m/ECC

Build automated AI workflows combining multiple models and services.

NeverSight/learn-skills.dev

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture.

Orchestra-Research/AI-Research-SKILLs

XSkill 数据访问原则：文件系统是内容真相，由 worker 同步进库；面板与业务读 请求只走数据库；内核 agent loop 可直接写盘。适用于改 dashboard、recommend、 team、pipeline、ecosystems 等读路径，以及审查是否又引入业务侧扫盘。

SkillNerds/xskill

Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior

Yeachan-Heo/oh-my-claudecode

从论文与代码仓设计可交付的 AutoResearch 工程题，确定 Starter、Baseline、Reference、评分器、Harbor 结构和证据契约。用于出题、改题或审题；不替代提交包最终 QA。

bosprimigenious/autoresearch-skills

Automated iterative agent runner for spec-based development in Kiro.

fabricioctelles/skills

Drafts a single-line /goal command for Claude Code or Codex goal mode, built around a checkable end state, a stated verification command and a stop condition.

trailofbits/skills

Ralph Loop based autonomous development loop. An agent skill from jh941213/my-cc-harness.

jh941213/my-cc-harness

Cancel active Ralph Loop

charfeng1/opencode-ralph-loop

Expert in designing and building autonomous AI agents. An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

自主Claude代码循环的模式与架构——从简单的顺序管道到基于RFC的多智能体有向无环图系统. An agent skill from affaan-m/ECC.

affaan-m/ECC

把一个任务"写成"一个目标导向的 loop，并"检查"这个 loop 写得对不对、会不会跑飞——防止空转烧钱 / Goodhart 作弊 / 把错的干到底。两个动作：① 写 loop（先做减法判该不该建 → 定可判定目标 → 选回路类型 → 选骨架）② 体检 loop（过五个崩法 + 可判定性 + 边界 + 降级 + judge 独立 + 判断留人红线）。中文触发：写 loop、设计…

qshanx/docs-governance

Starts a background runner that works through ready batches of tasks from Plans.md one cycle at a time via Breezing, with status and stop controls.

Chachamaru127/claude-code-harness

Creates comprehensive handoff documents for seamless AI agent session transfers.

davila7/claude-code-templates

Runs a prompt now and repeats it on a fixed interval or through self-paced wakeups, with subcommands to list or clear scheduled loop jobs.

QwenLM/qwen-code

Start a Ralph Loop for iterative self-referential development.

cursor/plugins

Explain the Ralph Loop plugin, how it works, and available skills.

cursor/plugins

Full-stack diagnostic for agent and LLM applications. An agent skill from affaan-m/ECC.

affaan-m/ECC

Design a goal-oriented agent loop or review one for failure modes: spinning, Goodhart-gaming the verifier, or running a wrong answer to completion.

affaan-m/ECC

Symptom-to-cause triage playbook for Flowfile (core/worker/kernel/frontend/AI) — covers "no such table" DB cascades (two distinct causes), import-time Alembic migration corruption, silent…

Edwardvaneechoud/Flowfile

Execute exactly one explicitly assigned YYLO Ledger task through the Ralph loop to a validated queued commit.

sickn33/agentic-awesome-skills

Wrap Codex Autoresearch for Slate v2 measured loops. An agent skill from udecode/plate.

udecode/plate

Slate v2 Autoresearch gate loop. An agent skill from udecode/plate.

udecode/plate

Slate v2 performance lane for Codex Autoresearch. An agent skill from udecode/plate.

udecode/plate

Slate v2 Autoresearch recipe picker. An agent skill from udecode/plate.

udecode/plate

Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff.

anombyte93/prd-taskmaster

Parallel version of the Ralph Loop. An agent skill from jh941213/my-cc-harness.

jh941213/my-cc-harness

Prepare and guide human inspection of an Autoform roadmap or formalization through its Obsidian graph and rendered blueprint site.

facebookresearch/autoform-bot

Autonomous experiment loop that optimizes any file by a measurable metric.

alirezarezvani/claude-skills

在已获授权的飞书/Lark 多维表格中处理 AutoResearch 的领题、完成提交/验收和组长初检三表流转，核对当期题号、字段权限、证据和写后回读。用于领取题目、提交验收材料或回填初检结论；不用于绕过组织权限、恢复离职账号或替代任务 QA。

bosprimigenious/autoresearch-skills

This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR…

guanyang/open-agent-hub

This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal…

guanyang/open-agent-hub

This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops, meta-harnesses, self-improving harnesses that…

guanyang/open-agent-hub

Evolve a skill by generating variations, evaluating them, and updating the best version

aeonfun/aeon

Autonomously optimize a Claude Code skill or agent system by running it repeatedly, scoring outputs against evals, mutating owned artifacts (prompt, references, scripts, agent definitions), and…

byungjunjang/jangpm-meta-skills

Slate v2 quality-gap Autoresearch shortcut. An agent skill from udecode/plate.

udecode/plate

Draft /goal prompts and explain persistent agent loops. An agent skill from davidondrej/skills.

davidondrej/skills

Slate v2 Autoresearch daily driver. An agent skill from udecode/plate.

udecode/plate

This skill converts planning docs and specs into phase-based task structures and prompts for long-running Claude agents.

mikeOnBreeze/cc-crossbeam

具有质量门、评估和恢复控制的连续自主代理循环模式。

tpavanipradeep/everything-claude-code

Build, test, and debug Hermes Agent RL environments for Atropos training.

Tommy-yw/RunbookHermes

Async and concurrency patterns for Mistral Vibe. An agent skill from mistralai/mistral-vibe.

mistralai/mistral-vibe

Autonomous iterative experimentation loop for any programming task.

github/awesome-copilot

Run metric-driven iterative optimization loops. An agent skill from leo-kuang-ai/spec-first.

leo-kuang-ai/spec-first

A skill your agent uses when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g.

gaasher/Agent-Loop-Skills