{ "schemaVersion": "1.0", "item": { "slug": "codex-orchestrator", "name": "Codex Orchestrator", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/Microcarft/codex-orchestrator", "canonicalUrl": "https://clawhub.ai/Microcarft/codex-orchestrator", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/codex-orchestrator", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=codex-orchestrator", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "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. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/codex-orchestrator" }, "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." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/codex-orchestrator", "agentPageUrl": "https://openagent3.xyz/skills/codex-orchestrator/agent", "manifestUrl": "https://openagent3.xyz/skills/codex-orchestrator/agent.json", "briefUrl": "https://openagent3.xyz/skills/codex-orchestrator/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "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. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Codex Orchestrator", "body": "This skill provides a workflow for supervising the Codex coding agent running in background processes." }, { "title": "1. Start (Launch)", "body": "Always launch Codex in a background PTY session to maintain interactivity without blocking the main agent.\n\nbash pty:true workdir: background:true command:\"codex exec --full-auto ''\"\n\nStore the returned sessionId.\nIf sessionId is lost, find it via process action:list." }, { "title": "2. Monitor (Watch)", "body": "Check progress regularly (e.g., via cron or manual check).\n\n# Get last 2KB of logs to see current status\nprocess action:log sessionId: limit:2000\n\nSigns of life:\n\nSpinner animations or progress bars updating.\n\"Working...\", \"Thinking...\", \"Running...\".\nFile edits (Edit ...).\n\nSigns of blockage:\n\nInteractive prompts (e.g., \"Select directory\", \"Approve change [y/n]\").\nNo log output for >5 minutes (process might be hung or waiting for hidden input)." }, { "title": "3. Intervene (Control)", "body": "If Codex is stuck at a prompt:\n\n# Send 'y' and Enter\nprocess action:submit sessionId: data:\"y\"\n\n# Send just Enter (default choice)\nprocess action:submit sessionId: data:\"\"\n\nIf Codex is looping or hallucinating:\n\n# Kill the session\nprocess action:kill sessionId:" }, { "title": "4. Report (Notify)", "body": "When a significant milestone is reached or the task is done:\n\nSummarize the work done (files changed, tests passed).\nNotify the user." }, { "title": "\"The Stuck Agent\" Protocol", "body": "Diagnose: Run process action:log sessionId: limit:500.\nAnalyze: Is it asking a question? Is it downloading?\nAction:\n\nIf asking: Provide answer via submit.\nIf downloading (slow): Wait.\nIf silent >10m: Send a \"poke\" (e.g. submit data:\"\\n\" to refresh prompt) or kill/resume." }, { "title": "\"The Resume\" Protocol", "body": "If a session died or was killed:\n\nRun codex resume --last or codex resume in a new background process.\nVerify it picked up the context." }, { "title": "Logs & Artifacts", "body": "Codex logs are ephemeral in the PTY buffer.\nFor persistent logs, instruct Codex to write to a file: codex exec \"task...\" > codex.log 2>&1 (Note: buffering may delay output).\nBetter: Use process action:log to snapshot the buffer periodically." } ], "body": "Codex Orchestrator\n\nThis skill provides a workflow for supervising the Codex coding agent running in background processes.\n\nWorkflow\n1. Start (Launch)\n\nAlways launch Codex in a background PTY session to maintain interactivity without blocking the main agent.\n\nbash pty:true workdir: background:true command:\"codex exec --full-auto ''\"\n\nStore the returned sessionId.\nIf sessionId is lost, find it via process action:list.\n2. Monitor (Watch)\n\nCheck progress regularly (e.g., via cron or manual check).\n\n# Get last 2KB of logs to see current status\nprocess action:log sessionId: limit:2000\n\n\nSigns of life:\n\nSpinner animations or progress bars updating.\n\"Working...\", \"Thinking...\", \"Running...\".\nFile edits (Edit ...).\n\nSigns of blockage:\n\nInteractive prompts (e.g., \"Select directory\", \"Approve change [y/n]\").\nNo log output for >5 minutes (process might be hung or waiting for hidden input).\n3. Intervene (Control)\n\nIf Codex is stuck at a prompt:\n\n# Send 'y' and Enter\nprocess action:submit sessionId: data:\"y\"\n\n# Send just Enter (default choice)\nprocess action:submit sessionId: data:\"\"\n\n\nIf Codex is looping or hallucinating:\n\n# Kill the session\nprocess action:kill sessionId:\n\n4. Report (Notify)\n\nWhen a significant milestone is reached or the task is done:\n\nSummarize the work done (files changed, tests passed).\nNotify the user.\nStandard Operating Procedures (SOPs)\n\"The Stuck Agent\" Protocol\nDiagnose: Run process action:log sessionId: limit:500.\nAnalyze: Is it asking a question? Is it downloading?\nAction:\nIf asking: Provide answer via submit.\nIf downloading (slow): Wait.\nIf silent >10m: Send a \"poke\" (e.g. submit data:\"\\n\" to refresh prompt) or kill/resume.\n\"The Resume\" Protocol\n\nIf a session died or was killed:\n\nRun codex resume --last or codex resume in a new background process.\nVerify it picked up the context.\nLogs & Artifacts\nCodex logs are ephemeral in the PTY buffer.\nFor persistent logs, instruct Codex to write to a file: codex exec \"task...\" > codex.log 2>&1 (Note: buffering may delay output).\nBetter: Use process action:log to snapshot the buffer periodically." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Microcarft/codex-orchestrator", "publisherUrl": "https://clawhub.ai/Microcarft/codex-orchestrator", "owner": "Microcarft", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/codex-orchestrator", "downloadUrl": "https://openagent3.xyz/downloads/codex-orchestrator", "agentUrl": "https://openagent3.xyz/skills/codex-orchestrator/agent", "manifestUrl": "https://openagent3.xyz/skills/codex-orchestrator/agent.json", "briefUrl": "https://openagent3.xyz/skills/codex-orchestrator/agent.md" } }