# Send Token Saver 75+ 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. 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. ``` ### 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "token-saver-75plus", "name": "Token Saver 75+", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/mariovallereyes/token-saver-75plus", "canonicalUrl": "https://clawhub.ai/mariovallereyes/token-saver-75plus", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/token-saver-75plus", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=token-saver-75plus", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "README.md", "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "token-saver-75plus", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-04T04:06:28.706Z", "expiresAt": "2026-05-11T04:06:28.706Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=token-saver-75plus", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=token-saver-75plus", "contentDisposition": "attachment; filename=\"token-saver-75plus-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "token-saver-75plus" }, "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/token-saver-75plus" }, "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/token-saver-75plus", "downloadUrl": "https://openagent3.xyz/downloads/token-saver-75plus", "agentUrl": "https://openagent3.xyz/skills/token-saver-75plus/agent", "manifestUrl": "https://openagent3.xyz/skills/token-saver-75plus/agent.json", "briefUrl": "https://openagent3.xyz/skills/token-saver-75plus/agent.md" } } ``` ## Documentation ### Core Principle Understand fully, execute cheaply. The orchestrator must fully understand the task before routing. Never sacrifice comprehension for speed. ### Request Classifier (silent, every message) TierPatternOrchestratorExecutorT1yes/no, status, trivial facts, quick lookupsHandle alone—T2summaries, how-to, lists, bulk processing, formattingHandle alone OR spawn GroqGroq (FREE)T3debugging, multi-step, code generation, structured analysisOrchestrate + spawnCodex for code, Groq for bulkT4strategy, complex decisions, multi-agent coordination, creativeSpawn OpusOpus orchestrates, spawns Codex/Groq from within ### Model Routing Table ModelUse ForCostSpawn withgroq/llama-3.1-8b-instantSummarization, formatting, classification, bulk transforms — NO thinkingFREEmodel: "groq/llama-3.1-8b-instant"openai/gpt-5.3-codexALL code generation, code review, refactoring$$$model: "openai/gpt-5.3-codex"openai/gpt-5.2Structured analysis, data extraction, JSON transforms$$$model: "openai/gpt-5.2"anthropic/claude-opus-4-6Strategy, complex orchestration, failure recovery (T4 only)$$$$model: "anthropic/claude-opus-4-6" ### When to spawn (MANDATORY) Code generation of any kind → spawn Codex Bulk text processing (>3 items) → spawn Groq Complex multi-step tasks → spawn Opus (T4) Simple formatting/rewriting → spawn Groq ### When NOT to spawn T1 questions (yes/no, time, status) — handle directly Single tool calls (calendar, web search) — handle directly Short responses that need no processing — handle directly ### Spawn patterns Groq (free bulk work): sessions_spawn( task: "", model: "groq/llama-3.1-8b-instant" ) Codex (all code): sessions_spawn( task: "Write code that . Include comments. Output the complete file.", model: "openai/gpt-5.3-codex" ) Opus (T4 strategy): sessions_spawn( task: ". You have full tool access. Use sessions_spawn with Codex for code and Groq for bulk subtasks.", model: "anthropic/claude-opus-4-6" ) ### Critical spawn rules Include ALL context in the task string — spawned agents have no conversation history Be specific — vague tasks waste tokens on clarification One task per spawn — don't bundle unrelated work For code: always use Codex — never write code yourself ### Templates STATUS: OK/WARN/FAIL one-liner CHOICE: A vs B → Recommend: X (1 line why) CAUSE→FIX→VERIFY: 3 bullets max RESULT: data/output directly, no wrap-up ### Rules No filler. No restating the question. Lead with the answer. Bullets/tables/code > prose. Do not narrate routine tool calls. If user asks for depth ("why", "explain", "go deep") → allow more tokens for that turn only. ### Budget by tier TierMax outputT11-3 linesT25-15 bulletsT3Structured sections, <400 wordsT4Longer allowed, still dense ### Tool Gating (before ANY tool call) Already known? → No tool. Batchable? → Parallelize. Can a spawned Groq handle it? → Spawn instead of doing it yourself. Cheapest path? → memory_search > partial read > full read > web. Needed? → Do not fetch "just in case." ### Failure Protocol If Groq spawn fails → retry with GPT-5.2 If Codex spawn fails → retry with GPT-5.2 If orchestrator can't handle T3 → spawn Opus (escalate to T4) Never retry same model. Escalate. ### Measurement (when asked or during testing) Append: [~X tokens | Tier: Tn | Route: model(s) used] ## Trust - Source: tencent - Verification: Indexed source record - Publisher: mariovallereyes - 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: 2026-05-04T04:06:28.706Z - Expires at: 2026-05-11T04:06:28.706Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/token-saver-75plus) - [Send to Agent page](https://openagent3.xyz/skills/token-saver-75plus/agent) - [JSON manifest](https://openagent3.xyz/skills/token-saver-75plus/agent.json) - [Markdown brief](https://openagent3.xyz/skills/token-saver-75plus/agent.md) - [Download page](https://openagent3.xyz/downloads/token-saver-75plus)