# Send Ralph Loop (Agent Mode) to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "ralph-loop-agent", "name": "Ralph Loop (Agent Mode)", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/addozhang/ralph-loop-agent", "canonicalUrl": "https://clawhub.ai/addozhang/ralph-loop-agent", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/ralph-loop-agent", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ralph-loop-agent", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "README.md", "SKILL.md", "_meta.json", "package.json" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "ralph-loop-agent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-03T09:09:11.489Z", "expiresAt": "2026-05-10T09:09:11.489Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ralph-loop-agent", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ralph-loop-agent", "contentDisposition": "attachment; filename=\"ralph-loop-agent-1.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "ralph-loop-agent" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/ralph-loop-agent" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/ralph-loop-agent", "downloadUrl": "https://openagent3.xyz/downloads/ralph-loop-agent", "agentUrl": "https://openagent3.xyz/skills/ralph-loop-agent/agent", "manifestUrl": "https://openagent3.xyz/skills/ralph-loop-agent/agent.json", "briefUrl": "https://openagent3.xyz/skills/ralph-loop-agent/agent.md" } } ``` ## Documentation ### Overview This skill guides OpenClaw agents to execute Ralph Loop workflows using the exec and process tools. The agent orchestrates AI coding agent sessions following the Ralph playbook flow: Define Requirements → JTBD → Focus Topics → specs/*.md PLANNING Loop → Create/update IMPLEMENTATION_PLAN.md (do not implement) BUILDING Loop → Implement tasks, run tests (backpressure), update plan, commit The loop persists context via PROMPT.md + AGENTS.md (loaded each iteration) and the plan/specs on disk. ### How This Skill Works This skill generates instructions for OpenClaw agents to execute Ralph Loops using the exec and process tools. The agent calls exec tool with the coding agent command Uses pty: true to provide TTY for interactive CLIs Uses background: true for monitoring capabilities Uses process tool to monitor progress and detect completion Important: Users don't run these scripts directly - the OpenClaw agent executes them using its tool capabilities. ### TTY Requirements Some coding agents require a real terminal (TTY) to work properly, or they will hang: Interactive CLIs (need TTY): OpenCode, Codex, Claude Code, Pi, Goose Non-interactive CLIs (file-based): aider, custom scripts Solution: Use exec + process mode for interactive CLIs, simple loops for file-based tools. ### Interactive CLIs (Recommended Pattern) For OpenCode, Codex, Claude Code, Pi, and Goose - these require TTY support: When I (the agent) receive a Ralph Loop request, I will: Use exec tool to launch the coding agent: exec tool with parameters: - command: "opencode run --model \\"$(cat PROMPT.md)\\"" - workdir: - background: true - pty: true - yieldMs: 60000 - timeout: 3600 Capture session ID from exec tool response Use process tool to monitor: process tool with: - action: "poll" - sessionId: process tool with: - action: "log" - sessionId: - offset: -30 (for recent output) Check completion by reading IMPLEMENTATION_PLAN.md for sentinel text Clean up with process kill if needed: process tool with: - action: "kill" - sessionId: Benefits: TTY support, real-time logs, timeout handling, parallel sessions, workdir isolation ### 1) Gather Inputs Required: Goal / JTBD CLI (opencode, codex, claude, goose, pi, other) Mode (PLANNING, BUILDING, or BOTH) Max iterations (default: PLANNING=5, BUILDING=10) Optional: Completion sentinel (default: STATUS: COMPLETE in IMPLEMENTATION_PLAN.md) Working directory (default: $PWD) Timeout per iteration (default: 3600s) Sandbox choice Auto-approval flags (--full-auto, --yolo, --dangerously-skip-permissions) Auto-detect: If CLI in interactive list → use exec tool with pty: true Extract model flag from CLI requirements ### 2) Requirements → Specs (Optional) If requirements are unclear: Break JTBD into focus topics Draft specs/.md for each Keep specs short and testable ### 3) PROMPT.md + AGENTS.md PROMPT.md references: specs/*.md IMPLEMENTATION_PLAN.md Relevant project files AGENTS.md includes: Test commands (backpressure) Build/run instructions Operational learnings ### 4) Prompt Templates PLANNING Prompt (no implementation): You are running a Ralph PLANNING loop for this goal: . Read specs/* and the current codebase. Only update IMPLEMENTATION_PLAN.md. Rules: - Do not implement - Do not commit - Create a prioritized task list - Write down questions if unclear Completion: When plan is ready, add: STATUS: PLANNING_COMPLETE BUILDING Prompt: You are running a Ralph BUILDING loop for this goal: . Context: specs/*, IMPLEMENTATION_PLAN.md, AGENTS.md Tasks: 1) Pick the most important task 2) Investigate code 3) Implement 4) Run backpressure commands from AGENTS.md 5) Update IMPLEMENTATION_PLAN.md 6) Update AGENTS.md with learnings 7) Commit with clear message Completion: When all done, add: STATUS: COMPLETE ### 5) CLI Command Reference The agent constructs command strings using these patterns: CLICommand String PatternOpenCodeopencode run --model "$(cat PROMPT.md)"Codexcodex exec "$(cat PROMPT.md)" (requires git)Claude Codeclaude "$(cat PROMPT.md)"Pipi --provider --model -p "$(cat PROMPT.md)"Goosegoose run "$(cat PROMPT.md)" Common flags: Codex: --full-auto, --yolo, --model Claude: --dangerously-skip-permissions ### Example 1: OpenCode Ralph Loop Agent executes this sequence: Step 1: Launch OpenCode with exec tool { command: "opencode run --model github-copilot/claude-opus-4.5 \\"$(cat PROMPT.md)\\"", workdir: "/path/to/project", background: true, pty: true, timeout: 3600, yieldMs: 60000 } Step 2: Capture session ID from response sessionId: "abc123" Step 3: Monitor with process tool every 10-30 seconds { action: "poll", sessionId: "abc123" } Step 4: Check recent logs { action: "log", sessionId: "abc123", offset: -30 } Step 5: Read IMPLEMENTATION_PLAN.md to check for completion - Look for: "STATUS: COMPLETE" or "STATUS: PLANNING_COMPLETE" Step 6: If complete or timeout, cleanup { action: "kill", sessionId: "abc123" } ### Example 2: Codex with Full Auto Agent tool calls: exec tool: { command: "codex exec --full-auto --model anthropic/claude-opus-4 \\"$(cat PROMPT.md)\\"", workdir: "/path/to/project", background: true, pty: true, timeout: 3600 } # Then monitor with process tool as above ### Completion Detection Use flexible regex to match variations: grep -Eq "STATUS:?\\s*(PLANNING_)?COMPLETE" IMPLEMENTATION_PLAN.md Matches: STATUS: COMPLETE STATUS:COMPLETE STATUS: PLANNING_COMPLETE ## Status: PLANNING_COMPLETE ### Auto-Approval Flags (Risky!) Codex: --full-auto (sandboxed, auto-approve) or --yolo (no sandbox!) Claude: --dangerously-skip-permissions Recommendation: Use sandboxes (docker/e2b/fly) and limited credentials ### Escape Hatches Stop: Ctrl+C Kill session: process tool with action: "kill" Rollback: git reset --hard HEAD~N ### Best Practices Start small: Test with 1-2 iterations first Workdir isolation: Prevent reading unrelated files Set timeouts: Default 1h may not fit all tasks Monitor actively: Check logs, don't terminate prematurely Requirements first: Clear specs before building Backpressure early: Add tests from the start ### Troubleshooting ProblemSolutionOpenCode hangsEnsure agent uses exec tool with pty: trueSession won't startCheck CLI path, git repo, command syntaxCompletion not detectedVerify sentinel format in IMPLEMENTATION_PLAN.mdProcess timeoutAgent should increase timeout parameter or simplify tasksParallel conflictsAgent should use git worktrees for isolationCan't see progressAgent should use process tool with action: "log" ### License MIT ### Credits This skill builds upon work by: @jordyvandomselaar - Original Ralph Loop concept and workflow design @steipete - Coding agent patterns and exec/process tool usage with pty support Key improvement: Uses OpenClaw's exec tool with pty: true to provide TTY for interactive CLIs, solving the hanging issue that occurs with simple background bash execution. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: addozhang - Version: 1.1.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-03T09:09:11.489Z - Expires at: 2026-05-10T09:09:11.489Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/ralph-loop-agent) - [Send to Agent page](https://openagent3.xyz/skills/ralph-loop-agent/agent) - [JSON manifest](https://openagent3.xyz/skills/ralph-loop-agent/agent.json) - [Markdown brief](https://openagent3.xyz/skills/ralph-loop-agent/agent.md) - [Download page](https://openagent3.xyz/downloads/ralph-loop-agent)