← Back to Skills Marketplace
1149
Downloads
0
Stars
4
Active Installs
1
Versions
Install in OpenClaw
/install openclaw-token-memory-optimizer
Description
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).
Usage Guidance
This skill appears coherent and low-risk for its stated purpose, but take these practical precautions before installing or running any included scripts: 1) Review the included scripts yourself (scripts/check-optimization.sh) — they read local config and workspace files but do not exfiltrate data. 2) Back up your openclaw.json and MEMORY.md before making changes. 3) The helper script assumes workspace paths relative to your config (may not match your layout); test it in a safe environment. 4) There is no external network activity in the skill, but if you plan to run commands like 'openclaw gateway restart', ensure you understand their operational impact. 5) If you prefer, copy the SKILL.md guidance into your operational playbook and make changes manually rather than running scripts from untrusted sources.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-token-memory-optimizer
Version: 1.0.0
The OpenClaw Token Optimizer skill bundle appears benign. Its stated purpose is to optimize OpenClaw agent memory and token usage, and all instructions in SKILL.md and README.md, as well as the `scripts/check-optimization.sh` script, align with this goal. The skill instructs the agent to modify OpenClaw's configuration (`openclaw.json`), manage its internal memory files (`MEMORY.md`, `memory/YYYY-MM-DD.md`), and use OpenClaw's built-in tools like `session_status`, `memory_search`, `memory_get`, and `openclaw gateway restart`. The shell script reads OpenClaw configuration and workspace files for status checks. There is no evidence of data exfiltration, unauthorized remote execution, persistence mechanisms, or prompt injection designed to subvert the agent for malicious purposes.
Capability Assessment
Purpose & Capability
Name and description (token/context optimization, RAG, cron isolation) match the SKILL.md instructions and the included script. All file accesses (openclaw.json, memory files, ~/.openclaw/sessions) are relevant to the documented purpose. No unrelated credentials, binaries, or services are requested.
Instruction Scope
Runtime instructions focus on updating openclaw.json, using local embeddings/memory_search, indexing local session transcripts, and restarting the gateway. The SKILL.md directs reading local config and memory files only and does not instruct transmitting data to external endpoints or accessing unrelated system secrets. It does ask the agent/user to read files under home (expected for this skill).
Install Mechanism
No install spec is provided (instruction-only skill) — lowest-risk distribution. A helper script (scripts/check-optimization.sh) is included but there is no automatic download or execution mechanism. The script is plain shell and relies on common POSIX utilities; nothing is fetched from remote URLs or extracted.
Credentials
The skill declares no environment variables or credentials and indeed does not require any. The script reads local files (config and workspace memory files) which is proportionate to a tool designed to check/advise on local OpenClaw configuration. No unrelated secrets or credentials are referenced.
Persistence & Privilege
always is false and the skill is user-invocable; model invocation is allowed (default) which is normal. The skill does not request persistent system-wide changes or modify other skills' configs. It recommends the user run 'openclaw gateway restart' (a normal operational action).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-token-memory-optimizer - After installation, invoke the skill by name or use
/openclaw-token-memory-optimizer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Token Optimizer version 1.1.0 — major usability and documentation update.
- Added comprehensive documentation detailing all supported workflows and use-cases.
- Introduced step-by-step guides for periodic task isolation, Reset & Summarize protocol, and local RAG configuration.
- Provided sample configurations and troubleshooting advice for common token and memory management issues.
- Described advanced search techniques, including session transcript indexing and hybrid retrieval (vector + BM25).
- Aimed to help OpenClaw agents prevent token leaks, reduce context bloat, and maintain efficient, lean sessions.
- Updated author list and credits.
Metadata
Frequently Asked Questions
What is 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). It is an AI Agent Skill for Claude Code / OpenClaw, with 1149 downloads so far.
How do I install Openclaw Token Memory Optimizer?
Run "/install openclaw-token-memory-optimizer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Openclaw Token Memory Optimizer free?
Yes, Openclaw Token Memory Optimizer is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Openclaw Token Memory Optimizer support?
Openclaw Token Memory Optimizer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Openclaw Token Memory Optimizer?
It is built and maintained by klautimus (@klautimus); the current version is v1.0.0.
More Skills