{ "schemaVersion": "1.0", "item": { "slug": "codecast", "name": "Codecast", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/allanjeng/codecast", "canonicalUrl": "https://clawhub.ai/allanjeng/codecast", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/codecast", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=codecast", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "references/advanced-modes.md", "references/discord-output.md", "references/setup.md", "scripts/codecast-watch.sh" ], "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. 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." }, { "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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "slug": "codecast", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T22:22:06.780Z", "expiresAt": "2026-05-08T22:22:06.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=codecast", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=codecast", "contentDisposition": "attachment; filename=\"codecast-4.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "codecast" }, "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/codecast" }, "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/codecast", "agentPageUrl": "https://openagent3.xyz/skills/codecast/agent", "manifestUrl": "https://openagent3.xyz/skills/codecast/agent.json", "briefUrl": "https://openagent3.xyz/skills/codecast/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. 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." }, { "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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Codecast", "body": "Live-stream coding agent sessions to Discord. Zero AI tokens burned." }, { "title": "Setup", "body": "First-time setup: see references/setup.md for webhook creation, unbuffer install, bot token, and smoke test." }, { "title": "Invocation", "body": "Launch with exec background:true. Background exec sessions survive agent turns and OpenClaw fires notifyOnExit automatically when the process ends.\n\nexec background:true command:\"{baseDir}/scripts/dev-relay.sh -w ~/projects/myapp -- claude -p --dangerously-skip-permissions --output-format stream-json --verbose 'Your task here'\"\n\nNote the session ID from the response — use it to monitor via process." }, { "title": "Options", "body": "FlagDescriptionDefault-w Working directoryCurrent dir-t Timeout1800-h Hang threshold120-n Agent display nameAuto-detected-r Rate limit (posts/60s)25--threadPost into a Discord threadOff--skip-readsHide Read tool eventsOff--review PR review mode—--parallel Parallel tasks mode—--resume Replay session—\n\nFor PR review, parallel tasks, Discord bridge, and Codex structured output: see references/advanced-modes.md." }, { "title": "Agent Launch Checklist", "body": "Start background session → note session ID and PID from response\nPost to dev channel → announce agent name, workdir, task\nWrite breadcrumb for completion routing:\necho '{\"channel\":\"\",\"relayDir\":\"\",\"pid\":}' > /tmp/codecast-pending-.json\n\n\nLog to daily memory → session ID, relay dir, invoking channel\n\nThe breadcrumb file tells the heartbeat precheck where to post results when the session completes. It auto-detects completion by checking if the PID is still alive.\n\nThat's it. When the process ends, OpenClaw's notifyOnExit fires a system event + heartbeat request. The heartbeat handler reads the result from the relay dir's stream.jsonl and posts to the invoking channel." }, { "title": "Completion Detection", "body": "OpenClaw handles this natively:\n\ntools.exec.notifyOnExit: true (default) — system event + heartbeat on process exit\nHeartbeat precheck script detects completed sessions via /tmp/dev-relay-sessions/\nNo cron watcher needed\n\nBackup: Append this to the inner agent's prompt for an additional signal:\n\nWhen completely finished, run: openclaw system event --text \"Done: \" --mode now" }, { "title": "Monitoring", "body": "process poll sessionId: # Check status\nprocess log sessionId: # View recent output\nprocess kill sessionId: # Stop session" }, { "title": "Agent Support", "body": "AgentOutput ModeStatusClaude Codestream-jsonFull supportCodex--json JSONLFull supportAny CLIRaw ANSIBasic support" }, { "title": "Session Tracking", "body": "Active sessions: /tmp/dev-relay-sessions/.json (auto-removed on end)\nEvent logs: /tmp/dev-relay.XXXXXX/stream.jsonl (7-day auto-cleanup)\nInteractive input: process submit sessionId: data:\"message\"" }, { "title": "Reference Docs", "body": "Setup guide — first-time install, webhook, bot token\nAdvanced modes — PR review, parallel tasks, Discord bridge, Codex\nDiscord output — message formats, architecture, env vars, troubleshooting" } ], "body": "Codecast\n\nLive-stream coding agent sessions to Discord. Zero AI tokens burned.\n\nSetup\n\nFirst-time setup: see references/setup.md for webhook creation, unbuffer install, bot token, and smoke test.\n\nInvocation\n\nLaunch with exec background:true. Background exec sessions survive agent turns and OpenClaw fires notifyOnExit automatically when the process ends.\n\nexec background:true command:\"{baseDir}/scripts/dev-relay.sh -w ~/projects/myapp -- claude -p --dangerously-skip-permissions --output-format stream-json --verbose 'Your task here'\"\n\n\nNote the session ID from the response — use it to monitor via process.\n\nOptions\nFlag\tDescription\tDefault\n-w \tWorking directory\tCurrent dir\n-t \tTimeout\t1800\n-h \tHang threshold\t120\n-n \tAgent display name\tAuto-detected\n-r \tRate limit (posts/60s)\t25\n--thread\tPost into a Discord thread\tOff\n--skip-reads\tHide Read tool events\tOff\n--review \tPR review mode\t—\n--parallel \tParallel tasks mode\t—\n--resume \tReplay session\t—\n\nFor PR review, parallel tasks, Discord bridge, and Codex structured output: see references/advanced-modes.md.\n\nAgent Launch Checklist\nStart background session → note session ID and PID from response\nPost to dev channel → announce agent name, workdir, task\nWrite breadcrumb for completion routing:\necho '{\"channel\":\"\",\"relayDir\":\"\",\"pid\":}' > /tmp/codecast-pending-.json\n\nLog to daily memory → session ID, relay dir, invoking channel\n\nThe breadcrumb file tells the heartbeat precheck where to post results when the session completes. It auto-detects completion by checking if the PID is still alive.\n\nThat's it. When the process ends, OpenClaw's notifyOnExit fires a system event + heartbeat request. The heartbeat handler reads the result from the relay dir's stream.jsonl and posts to the invoking channel.\n\nCompletion Detection\n\nOpenClaw handles this natively:\n\ntools.exec.notifyOnExit: true (default) — system event + heartbeat on process exit\nHeartbeat precheck script detects completed sessions via /tmp/dev-relay-sessions/\nNo cron watcher needed\n\nBackup: Append this to the inner agent's prompt for an additional signal:\n\nWhen completely finished, run: openclaw system event --text \"Done: \" --mode now\n\nMonitoring\nprocess poll sessionId: # Check status\nprocess log sessionId: # View recent output\nprocess kill sessionId: # Stop session\n\nAgent Support\nAgent\tOutput Mode\tStatus\nClaude Code\tstream-json\tFull support\nCodex\t--json JSONL\tFull support\nAny CLI\tRaw ANSI\tBasic support\nSession Tracking\nActive sessions: /tmp/dev-relay-sessions/.json (auto-removed on end)\nEvent logs: /tmp/dev-relay.XXXXXX/stream.jsonl (7-day auto-cleanup)\nInteractive input: process submit sessionId: data:\"message\"\nReference Docs\nSetup guide — first-time install, webhook, bot token\nAdvanced modes — PR review, parallel tasks, Discord bridge, Codex\nDiscord output — message formats, architecture, env vars, troubleshooting" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/allanjeng/codecast", "publisherUrl": "https://clawhub.ai/allanjeng/codecast", "owner": "allanjeng", "version": "4.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/codecast", "downloadUrl": "https://openagent3.xyz/downloads/codecast", "agentUrl": "https://openagent3.xyz/skills/codecast/agent", "manifestUrl": "https://openagent3.xyz/skills/codecast/agent.json", "briefUrl": "https://openagent3.xyz/skills/codecast/agent.md" } }