Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
Openclaw Token Memory Optimizer
Optimization suite for OpenClaw agents to prevent token leaks and context bloat. Use when an agent needs to implement background task isolation (Cron) or a Reset & Summarize workflow (RAG).
skill openclawclawhub Free
Optimization suite for OpenClaw agents to prevent token leaks and context bloat. Use when an agent needs to implement background task isolation (Cron) or a Reset & Summarize workflow (RAG).
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- README.md, SKILL.md, package.json, scripts/check-optimization.sh
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- 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.
New install
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
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.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.0
Provenance
- Publisher
- klautimus
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Token Optimizer Skill
This skill provides the procedural knowledge to keep your OpenClaw instance lean and efficient.
Quick Reference
ProblemSolutionBackground tasks bloating contextCron isolation (sessionTarget: "isolated")Reading entire history every turnLocal RAG with memory_searchContext exceeds 100k tokensReset & Summarize protocolFinding old conversationsSession transcript indexing
Workflow 1: Periodic Task Isolation
To prevent background tasks from bloating your main conversation context, always isolate them.
Steps
Locate your openclaw.json config. In the cron.jobs array, set sessionTarget: "isolated" for any task that doesn't need to be part of the main chat history. Use the message tool within the task's payload if human intervention is required.
Example Config
{ "cron": { "jobs": [ { "name": "Background Check", "schedule": { "kind": "every", "everyMs": 1800000 }, "sessionTarget": "isolated", "payload": { "kind": "agentTurn", "message": "Check for updates. If found, use message tool to notify user.", "deliver": true } } ] } }
Key Points
sessionTarget: "isolated" runs the task in a separate, transient session Use deliver: true to send results back to the main channel Isolated sessions don't pollute your main context with heartbeat/check history
Workflow 2: Reset & Summarize (The "Digital Soul" Protocol)
When your context usage (visible via π session_status) exceeds 100k tokens, perform a manual consolidation.
Steps
Check Context: Run π session_status to see current token usage Scan History: Review the current session for new facts, preferences, or project updates Update MEMORY.md: Append these new facts to your long-term memory file Daily Log: Ensure memory/YYYY-MM-DD.md is up to date with today's events Restart: Run openclaw gateway restart to clear the active history
When to Trigger
Context > 100k tokens Session running for several days Noticeably slower responses User explicitly requests a "fresh start"
Workflow 3: Local RAG Configuration
For efficient recall without token burn, configure local embeddings.
Configuration (openclaw.json)
{ "memorySearch": { "embedding": { "provider": "local", "model": "hf:second-state/All-MiniLM-L6-v2-Embedding-GGUF" }, "store": "sqlite", "paths": ["memory/", "MEMORY.md"], "extraPaths": [] } }
Usage
Use memory_search to retrieve context from your logs instead of loading everything: memory_search(query="what did we decide about the API design") The tool returns relevant snippets with file paths and line numbers. Use memory_get to pull specific sections.
Workflow 4: Session Transcript Indexing (Advanced)
Index your session transcripts (.jsonl files) for searchable conversation history.
How It Works
OpenClaw stores session transcripts in ~/.openclaw/sessions/. These can be indexed for semantic search, allowing you to find old conversations without loading them into context.
Configuration
Add transcript paths to memorySearch.extraPaths: { "memorySearch": { "extraPaths": [ "~/.openclaw/sessions/*.jsonl" ] } }
Best Practices
Index selectively (recent sessions, important conversations) Use date-based filtering to limit search scope Archive old transcripts to cold storage after indexing
Workflow 5: Hybrid Search (Vector + BM25)
Combine semantic search with keyword matching for more accurate retrieval.
Why Hybrid?
Search TypeStrengthsWeaknessesVector (semantic)Finds conceptually similar contentMay miss exact termsBM25 (keyword)Finds exact matchesMisses synonyms/paraphrasesHybridBest of both worldsSlightly more compute
How to Use
When memory_search returns low-confidence results: Try the search with different phrasing (semantic variation) Search for exact keywords you remember (BM25 behavior) Combine results manually if needed
Future Enhancement
OpenClaw's RAG system may support native hybrid search in future versions. For now, run multiple queries when precision matters.
"My context is growing too fast"
Check cron jobs: Are they isolated? Check heartbeat frequency: Too frequent = more tokens Are you loading large files unnecessarily?
"memory_search returns nothing"
Verify memorySearch is configured in openclaw.json Check that the embedding model is downloaded Ensure memory files exist and have content
"Restart didn't clear context"
The restart clears the session history, but: System prompt is always loaded Workspace files (MEMORY.md, etc.) are injected fresh This is by design for continuity
Credits
PΓ©pΓ¨re (shAde) β Original concept and documentation Zayan (ClΓ©ment) β Implementation and testing Built for the OpenClaw community. π¦¦πΈ
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
2 Docs1 Scripts1 Config
- SKILL.md
- README.md
- scripts/check-optimization.sh
- package.json