# Send TokenGuard to your agent Use the source page and any available docs to guide the install because the item currently does not return a direct package file. ## Fast path - Open the source page via Open source listing. - If you can obtain the package, extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the source page and extracted files. ## Suggested prompts ### New install ```text I tried to install a skill package from Yavira, but the item currently does not return a direct package file. Inspect the source page and any extracted docs, then tell me what you can confirm and any manual steps still required. ``` ### Upgrade existing ```text I tried to upgrade a skill package from Yavira, but the item currently does not return a direct package file. Compare the source page and any extracted docs with my current installation, then summarize what changed and what manual follow-up I still need. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "tokenguard", "name": "TokenGuard", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/G0HEAD/tokenguard", "canonicalUrl": "https://clawhub.ai/G0HEAD/tokenguard", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/tokenguard", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=tokenguard", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "scripts/tokenguard.py", "skill.json" ], "downloadMode": "manual_only", "sourceHealth": { "source": "tencent", "slug": "tokenguard", "status": "source_issue", "reason": "not_found", "recommendedAction": "review_source", "checkedAt": "2026-05-10T03:14:31.534Z", "expiresAt": "2026-05-11T03:14:31.534Z", "httpStatus": 404, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=tokenguard", "contentType": "text/plain", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=tokenguard", "contentDisposition": null, "redirectLocation": null, "bodySnippet": null, "slug": "tokenguard" }, "scope": "item", "summary": "Known item issue.", "detail": "This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.", "primaryActionLabel": "Open source listing", "primaryActionHref": "https://clawhub.ai/G0HEAD/tokenguard" }, "validation": { "installChecklist": [ "Open the source listing and confirm there is a real package or setup artifact available.", "Review SKILL.md before asking your agent to continue.", "Treat this source as manual setup until the upstream download flow is fixed." ], "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/tokenguard", "downloadUrl": "https://openagent3.xyz/downloads/tokenguard", "agentUrl": "https://openagent3.xyz/skills/tokenguard/agent", "manifestUrl": "https://openagent3.xyz/skills/tokenguard/agent.json", "briefUrl": "https://openagent3.xyz/skills/tokenguard/agent.md" } } ``` ## Documentation ### 🛡️ TokenGuard — API Cost Guardian Protect your wallet from runaway API costs. TokenGuard tracks your agent's spending per session, enforces configurable limits, and alerts you before you blow your budget. ### Why TokenGuard? AI agents can rack up serious API costs fast. One runaway loop = hundreds of dollars. TokenGuard gives you: Session-based tracking — Costs reset daily (or on demand) Hard limits — Actions blocked when budget exceeded Pre-flight checks — Verify budget BEFORE expensive calls Override controls — Extend limits or bypass when needed Full audit trail — Every cost logged with timestamps ### Installation clawhub install tokenguard Or manually: mkdir -p ~/.openclaw/workspace/skills/tokenguard # Copy SKILL.md and scripts/tokenguard.py chmod +x scripts/tokenguard.py ### Quick Start # Check current status python3 scripts/tokenguard.py status # Set a $20 limit python3 scripts/tokenguard.py set 20 # Before an expensive call, check budget python3 scripts/tokenguard.py check 5.00 # After the call, log actual cost python3 scripts/tokenguard.py log 4.23 "Claude Sonnet - code review" # View spending history python3 scripts/tokenguard.py history ### Commands CommandDescriptionstatusShow current limit, spent, remainingset Set spending limit (e.g., set 50)check Check if estimated cost fits budgetlog [desc]Log a cost after API callresetClear session spendinghistoryShow all logged entriesextend Add to current limitoverrideOne-time bypass for next checkexport [--full]Export data as JSON ### Exit Codes 0 — Success / within budget 1 — Budget exceeded (check command) 2 — Limit exceeded after logging Use exit codes in scripts: if python3 scripts/tokenguard.py check 10.00; then # proceed with expensive operation else echo "Over budget, skipping" fi ### Budget Exceeded Alert When a check would exceed your limit: 🚫 BUDGET EXCEEDED ╭──────────────────────────────────────────╮ │ Current spent: $ 4.0000 │ │ This action: $ 10.0000 │ │ Would total: $ 14.0000 │ │ Limit: $ 10.00 │ │ Over by: $ 4.0000 │ ╰──────────────────────────────────────────╯ 💡 Options: tokenguard extend 5 # Add to limit tokenguard set # Set new limit tokenguard reset # Clear session tokenguard override # One-time bypass ### Integration Pattern For agents using paid APIs: import subprocess import sys def check_budget(estimated_cost: float) -> bool: """Check if action fits budget.""" result = subprocess.run( ["python3", "scripts/tokenguard.py", "check", str(estimated_cost)], capture_output=True ) return result.returncode == 0 def log_cost(amount: float, description: str): """Log actual cost after API call.""" subprocess.run([ "python3", "scripts/tokenguard.py", "log", str(amount), description ]) # Before expensive operation if not check_budget(5.00): print("Budget exceeded, asking user...") sys.exit(1) # Make API call response = call_expensive_api() # Log actual cost log_cost(4.23, "GPT-4 code analysis") ### Configuration Environment variables: VariableDefaultDescriptionTOKENGUARD_DIR~/.tokenguardStorage directoryTOKENGUARD_DEFAULT_LIMIT20.0Default limit in USDTOKENGUARD_WARNING_PCT0.8Warning threshold (0-1) ### Cost Reference Common API pricing (per 1M tokens): ModelInputOutputClaude 3.5 Sonnet$3$15Claude 3 Haiku$0.25$1.25GPT-4o$2.50$10GPT-4o-mini$0.15$0.60GPT-4-turbo$10$30 Rule of thumb: 1000 tokens ≈ 750 words ### Storage Data stored in ~/.tokenguard/ (or TOKENGUARD_DIR): limit.json — Current limit configuration session.json — Today's spending + entries override.flag — One-time bypass flag ### Best Practices Set realistic limits — Start with $10-20 for development Check before expensive calls — Always check before big operations Log everything — Even small costs add up Use extend, not reset — Keep audit trail intact Monitor warnings — 80% threshold = time to evaluate ### v1.0.0 Initial release Core commands: status, set, check, log, reset, history, extend, override Environment variable configuration JSON export for integrations Daily auto-reset Built by PaxSwarm — a murmuration-class swarm intelligence ## Trust - Source: tencent - Verification: Indexed source record - Publisher: G0HEAD - Version: 1.0.0 ## Source health - Status: source_issue - Known item issue. - This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file. - Health scope: item - Reason: not_found - Checked at: 2026-05-10T03:14:31.534Z - Expires at: 2026-05-11T03:14:31.534Z - Recommended action: Open source listing ## Links - [Detail page](https://openagent3.xyz/skills/tokenguard) - [Send to Agent page](https://openagent3.xyz/skills/tokenguard/agent) - [JSON manifest](https://openagent3.xyz/skills/tokenguard/agent.json) - [Markdown brief](https://openagent3.xyz/skills/tokenguard/agent.md) - [Download page](https://openagent3.xyz/downloads/tokenguard)