# Send Context Visualization 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": "context-viz", "name": "Context Visualization", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/furukama/context-viz", "canonicalUrl": "https://clawhub.ai/furukama/context-viz", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/context-viz", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=context-viz", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "scripts/estimate_tokens.py", "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "context-viz", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T13:52:07.574Z", "expiresAt": "2026-05-06T13:52:07.574Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=context-viz", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=context-viz", "contentDisposition": "attachment; filename=\"context-viz-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "context-viz" }, "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/context-viz" }, "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/context-viz", "downloadUrl": "https://openagent3.xyz/downloads/context-viz", "agentUrl": "https://openagent3.xyz/skills/context-viz/agent", "manifestUrl": "https://openagent3.xyz/skills/context-viz/agent.json", "briefUrl": "https://openagent3.xyz/skills/context-viz/agent.md" } } ``` ## Documentation ### Context Visualization Estimate and display a breakdown of the current context window usage. ### How It Works Run the bundled script to estimate token counts for workspace files: python3 scripts/estimate_tokens.py /path/to/workspace The script counts characters in known workspace files and estimates tokens (~4 chars/token). Then call session_status to get the actual context usage from OpenClaw. ### Generating the Visualization Run session_status to get: model, context used/total, compactions Run scripts/estimate_tokens.py to estimate file token sizes Estimate message tokens: context_used - system_overhead - file_tokens Present the breakdown using the format below ### Output Format Use a monospace block with bar chart. Adapt the bar lengths proportionally. 📊 Context Usage • k/k tokens (%) Component Tokens % ───────────────────────────────────────────── ⚙️ System prompt + tools ~Xk X% ░░ 📋 AGENTS.md ~Xk X% ░ 👻 SOUL.md ~Xk X% 👤 USER.md ~Xk X% 🔧 TOOLS.md ~Xk X% ░ 💓 HEARTBEAT.md ~Xk X% 🧠 MEMORY.md ~Xk X% ░ 🪪 IDENTITY.md ~Xk X% 💬 Messages ~Xk X% ░░░░░░░░░░░░ 📭 Free space ~Xk X% ░░░░░ ───────────────────────────────────────────── Use ░ blocks: 1 block per ~2% of total context. Round to nearest block. ### Memory Inventory (not in context) Below the context chart, add a Memory on Disk section showing what's stored in memory/ — grouped by category. These files are NOT loaded into context but represent the agent's total knowledge base. 💾 Memory on Disk (not in context) Category Files Tokens Size ────────────────────────────────────────────────── 📰 chinese-ai-digests 12 ~23k 92KB 📁 other 11 ~12k 46KB 📅 daily-notes 9 ~5k 17KB 🗃️ zettelkasten 8 ~4k 15KB 💼 linkedin 2 ~1k 5KB ────────────────────────────────────────────────── Total: 42 ~44k 177KB The script auto-categorizes files by directory or filename pattern. ### Notes Token estimates use ~4 chars/token (rough average for English/mixed content) System prompt + tools overhead is estimated at ~8-10k tokens for a typical OpenClaw setup Message tokens are the remainder after subtracting files + system overhead Memory files are informational only — they show what the agent has accumulated For Discord/WhatsApp: skip markdown tables, use the block format above ## Trust - Source: tencent - Verification: Indexed source record - Publisher: furukama - 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: 2026-04-29T13:52:07.574Z - Expires at: 2026-05-06T13:52:07.574Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/context-viz) - [Send to Agent page](https://openagent3.xyz/skills/context-viz/agent) - [JSON manifest](https://openagent3.xyz/skills/context-viz/agent.json) - [Markdown brief](https://openagent3.xyz/skills/context-viz/agent.md) - [Download page](https://openagent3.xyz/downloads/context-viz)