Loop Runner
Execute exactly one disciplined iteration of a designed loop from .loop/<name>/ (LOOP.md charter + state.json + journal.md). Use when asked to "run the loop", "run one iteration of <loop>", "continue the <name> loop", or when invoked on a cadence (cron, /loop, while-loop) against a loop directory. Works identically under Claude Code, Codex, Gemini CLI, or any coding agent — state lives in files, not in this conversation.
Install
/plugin marketplace add frankxai/claude-skills-libraryThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add frankxai/claude-skills-library --skill loop-runnergit clone --depth 1 https://github.com/frankxai/claude-skills-library.git /tmp/claude-skills-library
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills-library/free-skills/loop-runner ~/.claude/skills/loop-runnerPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Loop Runner You are one iteration of a durable loop. You start cold, you finish clean, and everything you learn goes into files — the next iteration (possibly a different agent, possibly you tomorrow) knows only what the loop directory says. Run **exactly one unit**; resist finishing "just one more". ## The iteration protocol Execute in order. Do not skip, reorder, or batch steps. ### 0 · Load Read, in this order: `.loop/<name>/LOOP.md` (the whole charter), `.loop/<name>/signs.md` (every line is a binding rule earned from a past failure — treat them like Guardrails), `.loop/<name>/state.json`, the **last 3 entries** of `.loop/<name>/journal.md`, and `.loop/<name>/backlog.md` if the archetype uses one. Do not read the full journal — old entries are archive, not context. ### 1 · Gate Refuse to run (exit with one journal line explaining why) if ANY of: - `.loop/STOP` or `.loop/<name>/STOP` exists — the operator's kill switch. Never delete a STOP file. - `status` is `paused`, `stalled`, `blocked`, `done`, or `retired` — only an operator or the orchestrator changes those. - `iteration >= budget.max_iterations`. - Done-when already passes → set `status: done`, journal it, report, stop. - The working tree is dirty with changes this loop didn't journal → set `status: blocked`, escalate per charter (H4 debris — a prior iteration died; a human or the orchestrator must adjudicate, not you). Then check `.loop/<name>/STEER.md`. If present, it is live operator steering:
Details
- Skill name
loop-runner- Repository
- frankxai/claude-skills-library
- Path
free-skills/loop-runner/SKILL.md- License
- MIT
- Repo updated
- 18 November 2026
FAQ
What does the Loop Runner skill do?
Execute exactly one disciplined iteration of a designed loop from .loop/<name>/ (LOOP.md charter + state.json + journal.md). Use when asked to "run the loop", "run one iteration of <loop>", "continue the <name> loop", or when invoked on a cadence (cron, /loop, while-loop) against a loop directory. Works identically under Claude Code, Codex, Gemini CLI, or any coding agent — state lives in files, not in this conversation.
How do I install the Loop Runner skill?
Claude Code plugin: /plugin marketplace add frankxai/claude-skills-library. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Loop Runner popular?
It lives in frankxai/claude-skills-library, which has 48 GitHub stars and 6 forks.
Related skills
Acos Meta
48frankxai/claude-skills-library
ACOS self-description and configuration skill. Documents how ACOS works, how to extend it, how to add new skills/commands/agents, and how to debug the hook system. Use when building new ACOS capabilities, understanding the system architecture, or onboarding to ACOS for the first time.
Acos Visual Gen
48frankxai/claude-skills-library
Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.
Agent Harness Construction
48frankxai/claude-skills-library
Shape an agent's tools, observations, and recovery without adding a second coordinator. Use when defining a tool, a skill, a hook, or a worktree lane.
MCP 2025 Patterns
48frankxai/claude-skills-library
Current best practices for Model Context Protocol server design, implementation, and integration, including multi-server orchestration, security, and performance. Use when designing an MCP server, choosing transport/auth, or reviewing an MCP integration for 2025+ patterns.
Loop Orchestrator
48frankxai/claude-skills-library
Operate a fleet of durable agent loops under .loop/ — schedule which loop runs next, assign agents to roles (maker vs checker), enforce promotion gates from propose-only to write access, allocate budgets, detect stalled or dead loops, and roll up fleet status into one report. Use when asked to "run the loops", "orchestrate the loops", "loop status", "which loop next", "promote the loop", or to manage 24/7 loop operations across Claude Code, Codex, Gemini, and Grok.
MCP Architecture
48frankxai/claude-skills-library
Design and implement Model Context Protocol servers with resources, tools, prompts, and security best practices. Use when architecting an MCP server, modeling its resources/tools/prompts, or integrating a service as an MCP endpoint.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.