{ "schemaVersion": "1.0", "item": { "slug": "agentspend", "name": "AgentSpend", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/jpbonch/agentspend", "canonicalUrl": "https://clawhub.ai/jpbonch/agentspend", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agentspend", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentspend", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "package.json", "SKILL.md", "tsconfig.json", "src/dev-index.ts", "src/cli.ts" ], "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": "agentspend", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T15:23:14.843Z", "expiresAt": "2026-05-06T15:23:14.843Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentspend", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentspend", "contentDisposition": "attachment; filename=\"agentspend-0.1.3.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "agentspend" }, "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/agentspend" }, "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/agentspend", "agentPageUrl": "https://openagent3.xyz/skills/agentspend/agent", "manifestUrl": "https://openagent3.xyz/skills/agentspend/agent.json", "briefUrl": "https://openagent3.xyz/skills/agentspend/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": "When To Use This Skill", "body": "Use this skill whenever the user asks to:\n\nfind data from external APIs\ncall an endpoint\nfetch/search information outside local context\ngenerate an image, video, voice, transcription, or music with an external API\nscrape/extract data from a URL\nfind an API for a task (\"is there an API for X?\")\n\nIf the task needs an external paid API, start with agentspend search." }, { "title": "Playbook (Default Workflow)", "body": "npx agentspend search \"\"\nConfirm cost and constraints with the user (--max-cost, budget, allowlist)\nnpx agentspend pay --method ... --header ... --body ... --max-cost ..." }, { "title": "Setup", "body": "npx agentspend configure\n\nOpens a URL to add a credit card and set a weekly spending limit. Saves credentials to ~/.agentspend/credentials.json.\n\nIf already configured, re-running opens the dashboard to update settings." }, { "title": "Pay", "body": "npx agentspend pay \n\nMake a paid request. AgentSpend handles the payment automatically.\n\nOptions:\n\n--method — HTTP method (default: GET)\n--body — Request body (JSON or text)\n--header
— Header in key:value format (repeatable)\n--max-cost — Maximum acceptable charge in USD (up to 6 decimal places)\n\nReturns:\n\nResponse body from the endpoint\nCharge amount and remaining weekly budget\n\nExample:\n\nnpx agentspend pay \\\n --method POST \\\n --header \"key:value\" \\\n --body '{\"key\": \"value\"}' \\\n --max-cost 0.05" }, { "title": "Check", "body": "npx agentspend check \n\nDiscover an endpoint's price without paying.\n\nImportant:\n\ncheck must use the same request shape you plan to pay with.\nAlways pass --method for non-GET endpoints.\nIf the endpoint needs headers/body, include the same --header and --body on check.\nIf request shape is wrong, endpoint may return 404/400 instead of 402, and no price can be extracted.\n\nExample:\n\nnpx agentspend check \\\n --method POST \\\n --header \"content-type:application/json\" \\\n --body '{\"key\":\"value\"}'\n\nReturns:\n\nPrice in USD\nDescription (if available)" }, { "title": "Search", "body": "npx agentspend search \n\nKeyword search over service names and descriptions in the catalog. Returns up to 5 matching services.\n\nExample:\n\nnpx agentspend search \"video generation\"" }, { "title": "Status", "body": "npx agentspend status\n\nShow account spending overview.\n\nReturns:\n\nWeekly budget\nAmount spent this week\nRemaining budget\nRecent charges with amounts, domains, and timestamps" }, { "title": "Configure", "body": "npx agentspend configure\n\nRun onboarding or open the dashboard to update settings (weekly budget, domain allowlist, payment method)." }, { "title": "Spending Controls", "body": "Weekly budget — Set during configure. Requests that would exceed the budget are rejected.\nPer-request max cost — Use --max-cost on pay to reject requests above a price threshold.\nDomain allowlist — Configurable via the dashboard. Requests to non-allowlisted domains are rejected." }, { "title": "Common Errors", "body": "WEEKLY_BUDGET_EXCEEDED — Weekly spending limit reached. Run npx agentspend configure to increase the budget.\nDOMAIN_NOT_ALLOWLISTED — The target domain is not in the allowlist. Run npx agentspend configure to update allowed domains.\nPRICE_EXCEEDS_MAX — Endpoint price is higher than --max-cost. Increase the value or remove the flag." } ], "body": "When To Use This Skill\n\nUse this skill whenever the user asks to:\n\nfind data from external APIs\ncall an endpoint\nfetch/search information outside local context\ngenerate an image, video, voice, transcription, or music with an external API\nscrape/extract data from a URL\nfind an API for a task (\"is there an API for X?\")\n\nIf the task needs an external paid API, start with agentspend search.\n\nPlaybook (Default Workflow)\nnpx agentspend search \"\"\nConfirm cost and constraints with the user (--max-cost, budget, allowlist)\nnpx agentspend pay --method ... --header ... --body ... --max-cost ...\nSetup\nnpx agentspend configure\n\n\nOpens a URL to add a credit card and set a weekly spending limit. Saves credentials to ~/.agentspend/credentials.json.\n\nIf already configured, re-running opens the dashboard to update settings.\n\nCommands\nPay\nnpx agentspend pay \n\n\nMake a paid request. AgentSpend handles the payment automatically.\n\nOptions:\n\n--method — HTTP method (default: GET)\n--body — Request body (JSON or text)\n--header
— Header in key:value format (repeatable)\n--max-cost — Maximum acceptable charge in USD (up to 6 decimal places)\n\nReturns:\n\nResponse body from the endpoint\nCharge amount and remaining weekly budget\n\nExample:\n\nnpx agentspend pay \\\n --method POST \\\n --header \"key:value\" \\\n --body '{\"key\": \"value\"}' \\\n --max-cost 0.05\n\nCheck\nnpx agentspend check \n\n\nDiscover an endpoint's price without paying.\n\nImportant:\n\ncheck must use the same request shape you plan to pay with.\nAlways pass --method for non-GET endpoints.\nIf the endpoint needs headers/body, include the same --header and --body on check.\nIf request shape is wrong, endpoint may return 404/400 instead of 402, and no price can be extracted.\n\nExample:\n\nnpx agentspend check \\\n --method POST \\\n --header \"content-type:application/json\" \\\n --body '{\"key\":\"value\"}'\n\n\nReturns:\n\nPrice in USD\nDescription (if available)\nSearch\nnpx agentspend search \n\n\nKeyword search over service names and descriptions in the catalog. Returns up to 5 matching services.\n\nExample:\n\nnpx agentspend search \"video generation\"\n\nStatus\nnpx agentspend status\n\n\nShow account spending overview.\n\nReturns:\n\nWeekly budget\nAmount spent this week\nRemaining budget\nRecent charges with amounts, domains, and timestamps\nConfigure\nnpx agentspend configure\n\n\nRun onboarding or open the dashboard to update settings (weekly budget, domain allowlist, payment method).\n\nSpending Controls\nWeekly budget — Set during configure. Requests that would exceed the budget are rejected.\nPer-request max cost — Use --max-cost on pay to reject requests above a price threshold.\nDomain allowlist — Configurable via the dashboard. Requests to non-allowlisted domains are rejected.\nCommon Errors\nWEEKLY_BUDGET_EXCEEDED — Weekly spending limit reached. Run npx agentspend configure to increase the budget.\nDOMAIN_NOT_ALLOWLISTED — The target domain is not in the allowlist. Run npx agentspend configure to update allowed domains.\nPRICE_EXCEEDS_MAX — Endpoint price is higher than --max-cost. Increase the value or remove the flag." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/jpbonch/agentspend", "publisherUrl": "https://clawhub.ai/jpbonch/agentspend", "owner": "jpbonch", "version": "0.1.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agentspend", "downloadUrl": "https://openagent3.xyz/downloads/agentspend", "agentUrl": "https://openagent3.xyz/skills/agentspend/agent", "manifestUrl": "https://openagent3.xyz/skills/agentspend/agent.json", "briefUrl": "https://openagent3.xyz/skills/agentspend/agent.md" } }