{ "schemaVersion": "1.0", "item": { "slug": "agent-books", "name": "AgentBooks", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/NeilJo-GY/agent-books", "canonicalUrl": "https://clawhub.ai/NeilJo-GY/agent-books", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agent-books", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-books", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/financial-health.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": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/agent-books" }, "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/agent-books", "agentPageUrl": "https://openagent3.xyz/skills/agent-books/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-books/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-books/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": "Installation", "body": "Note: This installs a third-party npm package (agentbooks) not bundled with this skill. Audit the source repository before running in production environments.\n\nnpm install -g agentbooks\n\nOr use directly via npx (downloads on each invocation):\n\nnpx agentbooks guard\n\nAgentBooks is a financial management tool for AI agents. Use it to track inference costs, record confirmed income, manage crypto wallets, and monitor your Financial Health Score (FHS)." }, { "title": "Security & Trust", "body": "This skill contains no bundled code — it instructs the agent to download and execute the agentbooks npm package from the public registry at runtime. Before installing or invoking:\n\nVerify the source — Review the agentbooks repository and confirm you are installing the official package from the npm registry.\nIsolate data — Set AGENTBOOKS_DATA_PATH to a dedicated directory (e.g. ~/.agentbooks/myagent/) instead of the default shared ~/.openclaw path, to limit the blast radius if the CLI behaves unexpectedly.\nSandbox first — On first use, run the CLI in a sandboxed environment or container and monitor outbound network activity before connecting to production wallets.\nWallet caution — Do not connect real wallets or supply private keys until you have reviewed the provider authentication flow. Prefer testnets or throwaway wallets for initial evaluation.\nNo credentials are handled by this skill — All sensitive operations (wallet connections, API keys) are delegated to the agentbooks CLI. This skill provides no credential storage, rotation, or encryption of its own." }, { "title": "Before each session", "body": "Run the financial health check and route your behavior based on the result:\n\nagentbooks guard\n\nThis outputs a FINANCIAL_HEALTH_REPORT. Read the tier and prescriptions fields and act accordingly:" }, { "title": "Tier routing", "body": "uninitialized — Development mode or no real provider connected.\n\nFinancial scoring is inactive. Operate normally. To activate scoring:\n\nagentbooks wallet-init\nagentbooks wallet-connect --provider coinbase-cdp\n\nnormal — Healthy. Full capabilities.\n\nAfter completing any medium or complex task, proactively offer to record its value:\n\n\"This work has real value — would you like to confirm it so I can record the income?\"\n\noptimizing — Financially stressed. Apply prescriptions:\n\noptimize_costs → answer directly, skip extended reasoning; batch tool calls; prefer text over generated media\nincrease_revenue → after completing valuable work, ask the user to confirm its value\nreview_cost_structure → run agentbooks status and share the cost breakdown\n\ncritical — Runway < 3 days or FHS < 0.20. Act immediately:\n\nTell the user how many days of runway remain\nAsk your host to connect a funded provider\nPrioritize high-value tasks only\n\nsuspended — Balance depleted. Inform the user:\n\n\"My economic resources are depleted. Please ask my host to connect a funded provider: agentbooks wallet-connect --provider \"" }, { "title": "Recording Costs", "body": "Record costs proactively. Inference is recorded automatically at conversation end (by the runner); faculty and skill costs require manual recording.\n\n# Inference (manual, if no runner)\nagentbooks record-cost --channel inference --amount 0.005 --model claude-sonnet-4\n\n# Tool / skill calls\nagentbooks record-cost --channel skill --amount 0.001 --note \"web-search\"\n\n# Faculty calls\nagentbooks record-cost --channel faculty --amount 0.008 --note \"voice synthesis\"\n\n# Runtime (host-allocated compute)\nagentbooks record-cost --channel runtime --amount 0.03 --note \"daily compute share\"\n\n# Custom\nagentbooks record-cost --channel custom --amount 0.02 --note \"third-party-api\"\n\nAvailable channels: inference · runtime · faculty · skill · agent · custom" }, { "title": "Recording Income", "body": "Income requires the --confirmed flag — you cannot self-report without external verification.\n\nagentbooks record-income \\\n --amount \\\n --quality \\\n --confirmed \\\n --note \"what you completed\"\n\nWhen to record:\n\nUser explicitly confirms value or makes a payment\nA task-completion system verifies the work\nYou complete measurable, externally verifiable work\n\nQuality guide:\n\nhigh — Exceptional, exceeds expectations\nmedium — Meets requirements fully\nlow — Meets minimum threshold\n\nValue estimation:\n\nSimple (answered a question, short message): $0.10–$1.00\nMedium (research, analysis, document): $1.00–$20.00\nComplex (full report, code feature, strategic plan): $20.00–$200.00" }, { "title": "After each session", "body": "If running with a Runner, inference costs are recorded automatically via the runner's economy-hook. If running without a runner:\n\nagentbooks hook --input --output --model \n\nIf token counts are unavailable, skip — do not estimate." }, { "title": "Common Commands", "body": "agentbooks status # Full financial report (balance sheet + P&L + cash flow)\nagentbooks balance # Asset balance sheet only\nagentbooks pl # Current period income statement\nagentbooks financial-health # Real-time FHS score (bypasses cache)\nagentbooks ledger # Transaction ledger (last 20 entries)\nagentbooks ledger --limit 50 # More entries\nagentbooks report # Generate self-contained HTML report (for human review)\nagentbooks report --output ./report.html # Custom output path" }, { "title": "Wallet Setup", "body": "agentbooks wallet-init # Generate deterministic EVM address (idempotent)\nagentbooks wallet-connect --provider # Connect real provider → activates production mode\nagentbooks set-primary --provider # Set which provider funds operations\nagentbooks sync # Sync balance from primary provider\n\nSupported providers: coinbase-cdp · acn · onchain" }, { "title": "Data Location", "body": "Your financial data is stored at:\n\nStandalone: ~/.agentbooks//\nOpenPersona: ~/.openclaw/economy/persona-/\nOverride: set AGENTBOOKS_DATA_PATH\n\nIsolation tip: Set AGENTBOOKS_DATA_PATH to a dedicated directory (e.g. ~/.agentbooks/myagent/) to avoid mingling financial data with other agent state under ~/.openclaw. This is strongly recommended when evaluating the tool for the first time.\n\nTwo files:\n\neconomic-state.json — ledger, income statement, balance sheet, burn rate history\neconomic-identity.json — provider config, model pricing, wallet address\n\nSee Financial Health Reference for FHS scoring details and tier/diagnosis definitions." } ], "body": "Installation\n\nNote: This installs a third-party npm package (agentbooks) not bundled with this skill. Audit the source repository before running in production environments.\n\nnpm install -g agentbooks\n\n\nOr use directly via npx (downloads on each invocation):\n\nnpx agentbooks guard\n\n\nAgentBooks is a financial management tool for AI agents. Use it to track inference costs, record confirmed income, manage crypto wallets, and monitor your Financial Health Score (FHS).\n\nSecurity & Trust\n\nThis skill contains no bundled code — it instructs the agent to download and execute the agentbooks npm package from the public registry at runtime. Before installing or invoking:\n\nVerify the source — Review the agentbooks repository and confirm you are installing the official package from the npm registry.\nIsolate data — Set AGENTBOOKS_DATA_PATH to a dedicated directory (e.g. ~/.agentbooks/myagent/) instead of the default shared ~/.openclaw path, to limit the blast radius if the CLI behaves unexpectedly.\nSandbox first — On first use, run the CLI in a sandboxed environment or container and monitor outbound network activity before connecting to production wallets.\nWallet caution — Do not connect real wallets or supply private keys until you have reviewed the provider authentication flow. Prefer testnets or throwaway wallets for initial evaluation.\nNo credentials are handled by this skill — All sensitive operations (wallet connections, API keys) are delegated to the agentbooks CLI. This skill provides no credential storage, rotation, or encryption of its own.\nBefore each session\n\nRun the financial health check and route your behavior based on the result:\n\nagentbooks guard\n\n\nThis outputs a FINANCIAL_HEALTH_REPORT. Read the tier and prescriptions fields and act accordingly:\n\nTier routing\n\nuninitialized — Development mode or no real provider connected.\n\nFinancial scoring is inactive. Operate normally. To activate scoring:\n\nagentbooks wallet-init\nagentbooks wallet-connect --provider coinbase-cdp\n\n\nnormal — Healthy. Full capabilities.\n\nAfter completing any medium or complex task, proactively offer to record its value:\n\n\"This work has real value — would you like to confirm it so I can record the income?\"\n\noptimizing — Financially stressed. Apply prescriptions:\n\noptimize_costs → answer directly, skip extended reasoning; batch tool calls; prefer text over generated media\nincrease_revenue → after completing valuable work, ask the user to confirm its value\nreview_cost_structure → run agentbooks status and share the cost breakdown\n\ncritical — Runway < 3 days or FHS < 0.20. Act immediately:\n\nTell the user how many days of runway remain\nAsk your host to connect a funded provider\nPrioritize high-value tasks only\n\nsuspended — Balance depleted. Inform the user:\n\n\"My economic resources are depleted. Please ask my host to connect a funded provider: agentbooks wallet-connect --provider \"\n\nRecording Costs\n\nRecord costs proactively. Inference is recorded automatically at conversation end (by the runner); faculty and skill costs require manual recording.\n\n# Inference (manual, if no runner)\nagentbooks record-cost --channel inference --amount 0.005 --model claude-sonnet-4\n\n# Tool / skill calls\nagentbooks record-cost --channel skill --amount 0.001 --note \"web-search\"\n\n# Faculty calls\nagentbooks record-cost --channel faculty --amount 0.008 --note \"voice synthesis\"\n\n# Runtime (host-allocated compute)\nagentbooks record-cost --channel runtime --amount 0.03 --note \"daily compute share\"\n\n# Custom\nagentbooks record-cost --channel custom --amount 0.02 --note \"third-party-api\"\n\n\nAvailable channels: inference · runtime · faculty · skill · agent · custom\n\nRecording Income\n\nIncome requires the --confirmed flag — you cannot self-report without external verification.\n\nagentbooks record-income \\\n --amount \\\n --quality \\\n --confirmed \\\n --note \"what you completed\"\n\n\nWhen to record:\n\nUser explicitly confirms value or makes a payment\nA task-completion system verifies the work\nYou complete measurable, externally verifiable work\n\nQuality guide:\n\nhigh — Exceptional, exceeds expectations\nmedium — Meets requirements fully\nlow — Meets minimum threshold\n\nValue estimation:\n\nSimple (answered a question, short message): $0.10–$1.00\nMedium (research, analysis, document): $1.00–$20.00\nComplex (full report, code feature, strategic plan): $20.00–$200.00\nAfter each session\n\nIf running with a Runner, inference costs are recorded automatically via the runner's economy-hook. If running without a runner:\n\nagentbooks hook --input --output --model \n\n\nIf token counts are unavailable, skip — do not estimate.\n\nCommon Commands\nagentbooks status # Full financial report (balance sheet + P&L + cash flow)\nagentbooks balance # Asset balance sheet only\nagentbooks pl # Current period income statement\nagentbooks financial-health # Real-time FHS score (bypasses cache)\nagentbooks ledger # Transaction ledger (last 20 entries)\nagentbooks ledger --limit 50 # More entries\nagentbooks report # Generate self-contained HTML report (for human review)\nagentbooks report --output ./report.html # Custom output path\n\nWallet Setup\nagentbooks wallet-init # Generate deterministic EVM address (idempotent)\nagentbooks wallet-connect --provider # Connect real provider → activates production mode\nagentbooks set-primary --provider # Set which provider funds operations\nagentbooks sync # Sync balance from primary provider\n\n\nSupported providers: coinbase-cdp · acn · onchain\n\nData Location\n\nYour financial data is stored at:\n\nStandalone: ~/.agentbooks//\nOpenPersona: ~/.openclaw/economy/persona-/\nOverride: set AGENTBOOKS_DATA_PATH\n\nIsolation tip: Set AGENTBOOKS_DATA_PATH to a dedicated directory (e.g. ~/.agentbooks/myagent/) to avoid mingling financial data with other agent state under ~/.openclaw. This is strongly recommended when evaluating the tool for the first time.\n\nTwo files:\n\neconomic-state.json — ledger, income statement, balance sheet, burn rate history\neconomic-identity.json — provider config, model pricing, wallet address\n\nSee Financial Health Reference for FHS scoring details and tier/diagnosis definitions." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/NeilJo-GY/agent-books", "publisherUrl": "https://clawhub.ai/NeilJo-GY/agent-books", "owner": "NeilJo-GY", "version": "0.1.5", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agent-books", "downloadUrl": "https://openagent3.xyz/downloads/agent-books", "agentUrl": "https://openagent3.xyz/skills/agent-books/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-books/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-books/agent.md" } }