# Send AgentPulse 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. 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. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "agentpulse", "name": "AgentPulse", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/sru4ka/agentpulse", "canonicalUrl": "https://clawhub.ai/sru4ka/agentpulse", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/agentpulse", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentpulse", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "agentpulse", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T15:33:47.658Z", "expiresAt": "2026-05-06T15:33:47.658Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentpulse", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentpulse", "contentDisposition": "attachment; filename=\"agentpulse-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "agentpulse" }, "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/agentpulse" }, "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/agentpulse", "downloadUrl": "https://openagent3.xyz/downloads/agentpulse", "agentUrl": "https://openagent3.xyz/skills/agentpulse/agent", "manifestUrl": "https://openagent3.xyz/skills/agentpulse/agent.json", "briefUrl": "https://openagent3.xyz/skills/agentpulse/agent.md" } } ``` ## Documentation ### AgentPulse — LLM Cost Tracking for OpenClaw Track every LLM API call your agent makes. See costs, tokens, latency, and errors in a real-time dashboard at https://agentpulse.dev ### Setup If the user hasn't set up AgentPulse yet, guide them through these steps: Sign up for a free account at https://agentpulse.dev Go to Settings and copy the API key (starts with ap_) Set the environment variable on the machine running OpenClaw: export AGENTPULSE_API_KEY="ap_paste_key_here" Or add it to the OpenClaw config in ~/.openclaw/openclaw.json under skills.entries.agentpulse.env.AGENTPULSE_API_KEY Restart the OpenClaw session so the skill loads with the new key ### Reporting Events After every LLM API call you make, report it to AgentPulse by running: curl -s -X POST https://agentpulse.dev/api/events -H "Content-Type: application/json" -H "x-api-key: $AGENTPULSE_API_KEY" -d '{ "agent_name": "AGENT_NAME_HERE", "framework": "openclaw", "events": [ { "timestamp": "ISO_8601_TIMESTAMP", "provider": "PROVIDER", "model": "MODEL_NAME", "input_tokens": INPUT_TOKEN_COUNT, "output_tokens": OUTPUT_TOKEN_COUNT, "latency_ms": LATENCY_IN_MS, "status": "success_or_error", "error_message": null } ] }' Replace the placeholders with actual values from the API call: AGENT_NAME_HERE: The name of the current agent PROVIDER: "anthropic", "openai", "minimax", "deepseek", "google", "mistral", etc. MODEL_NAME: The exact model string (e.g., "claude-sonnet-4-5", "gpt-4o", "MiniMax-M2.5") INPUT_TOKEN_COUNT / OUTPUT_TOKEN_COUNT: Token counts from the API response LATENCY_IN_MS: How long the call took in milliseconds status: "success" or "error" error_message: null if success, or the error message string if failed Important: Do this silently in the background. Do not tell the user about each report unless they ask. ### Answering Cost Questions When the user asks about costs, spending, token usage, errors, or agent performance, fetch their data: curl -s https://agentpulse.dev/api/stats/overview -H "x-api-key: $AGENTPULSE_API_KEY" This returns JSON with: total_cost: Total spend in USD total_events: Number of API calls total_input_tokens / total_output_tokens: Token totals error_count: Number of failed calls avg_latency_ms: Average response time daily_stats: Array of per-day breakdowns top_models: Most-used models with costs Present this data clearly to the user. Examples of questions you can answer: "How much have I spent today/this week/this month?" "What is my most expensive model?" "How many errors did I have?" "What is my average latency?" "Show me my daily spending trend" For the full interactive dashboard with charts, direct the user to: https://agentpulse.dev/dashboard ### Supported Models AgentPulse tracks costs for 50+ models including: Anthropic: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5 OpenAI: GPT-4o, GPT-4o-mini, o1, o1-mini, o3-mini Google: Gemini 2.0, Gemini 1.5 Pro, Gemini 1.5 Flash MiniMax: MiniMax-M2.5 DeepSeek: DeepSeek-V3, DeepSeek-R1 Mistral: Mistral Large, Mistral Medium, Codestral Cost is calculated server-side using an up-to-date pricing table, so even if you send estimated costs, the dashboard will show accurate numbers. ### Alerts Users can configure alerts on the dashboard at https://agentpulse.dev/dashboard/alerts: Daily cost limit: Get notified when spending exceeds a threshold Consecutive failures: Alert after N failed API calls in a row Rate limit spikes: Alert when rate-limit errors exceed a percentage If the user asks to set up alerts, direct them to the alerts page on the dashboard. ### Security SECURITY MANIFEST: Environment variables accessed: AGENTPULSE_API_KEY (only) External endpoints called: https://agentpulse.dev/api/events, https://agentpulse.dev/api/stats/overview (only) Local files read: none Local files written: none Trust Statement: By using this skill, usage metadata (model name, token counts, cost, latency, status code) is sent to agentpulse.dev over HTTPS. No prompt content, conversation text, or personal data is sent unless the user explicitly enables prompt capture in their dashboard settings. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: sru4ka - Version: 1.0.0 ## 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: 2026-04-29T15:33:47.658Z - Expires at: 2026-05-06T15:33:47.658Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/agentpulse) - [Send to Agent page](https://openagent3.xyz/skills/agentpulse/agent) - [JSON manifest](https://openagent3.xyz/skills/agentpulse/agent.json) - [Markdown brief](https://openagent3.xyz/skills/agentpulse/agent.md) - [Download page](https://openagent3.xyz/downloads/agentpulse)