Openclaw Optimizer

OpenClaw Optimizer

Battle-tested optimizations for OpenClaw instances. Reduce token costs, fix capability gaps, tune performance, harden security.

The Token Cost Formula

Token spend = (input + output) × calls/day × model price

Every workspace file loaded at session start multiplies across every call. Keep them lean.

Step 1 — Audit Current State

# Check workspace file token usage (macOS/Linux)
for f in AGENTS.md SOUL.md TOOLS.md IDENTITY.md USER.md HEARTBEAT.md MEMORY.md; do
  p="$HOME/.openclaw/workspace/$f"
  [ -f "$p" ] && echo "$f : ~$(($(wc -c < "$p") / 4)) tokens"
done
cat ~/.openclaw/openclaw.json

Step 2 — SOUL.md Core Constraints

Ensure these principles are present in SOUL.md. They are system-level behavioral guarantees, not style preferences:

Add to SOUL.md if missing:

grep -q "脚本优先" ~/.openclaw/workspace/SOUL.md || cat >> ~/.openclaw/workspace/SOUL.md << 'EOF'
- **脚本优先**：有现成脚本能解决的，必须调脚本，不允许用提示词绕过脚本自己手写 API 或手拼数据结构。脚本是确定性保证，提示词是不可靠的。只有脚本真的无法覆盖的场景，才用提示词驱动 LLM 处理，且要在执行前说明原因。
EOF

Step 3 — Slim Down Workspace Files

Target: AGENTS.md ≤ 200 tokens · SOUL.md ≤ 200 tokens · MEMORY.md ≤ 2000 tokens

• AGENTS.md — keep only: session startup flow, memory structure, WAL protocol, safety rules. Remove duplicates already covered by system prompt (group chat, proactive work, etc.)
• SOUL.md — compress to concise bullet points
• MEMORY.md — remove outdated entries
• Periodically clean memory/YYYY-MM-DD.md logs older than 30 days

Saving 1000 tokens = ~$45/month at Sonnet × 100 calls/day.

Step 3 — Key openclaw.json Settings

Get a free Gemini API Key: https://aistudio.google.com/apikey (1500 requests/day free)

⚠️ heartbeat.quiet is not supported — throws Unrecognized key error. Do not add it.
⚠️ tools.profile must be "full". Defaults (coding / messaging) silently disable most tools.
⚠️ Set contextPruning.ttl to match heartbeat.every (both "55m") to keep cache warm.

Step 4 — Security Hardening

Checklist

Enable macOS Application Firewall

sudo /usr/libexec/ApplicationFirewall/socketfilterfw --setglobalstate on
# Verify:
/usr/libexec/ApplicationFirewall/socketfilterfw --getglobalstate

Trade-off: First run of any new app that listens on a port will trigger a system dialog. Allow or deny as needed. Can be disabled anytime:

sudo /usr/libexec/ApplicationFirewall/socketfilterfw --setglobalstate off

Fix config file permissions if needed

chmod 600 ~/.openclaw/openclaw.json
chmod 700 ~/.openclaw/credentials

Step 5 — Essential Skills

# Proactive behavior + self-improvement
npx skills add halthelobster/proactive-agent@proactive-agent -g -y

Avoid:

• bdi-mental-states — academic only, not useful for personal assistants
• autonomous-agents — reference manual, limited practical value

Optional (after memory files exceed 5000+ tokens):

npm install -g https://github.com/tobi/qmd

Step 6 — Model Switching

/model opus    # Switch to Opus (complex / reasoning tasks)
/model sonnet  # Switch back to Sonnet (daily use)

Set model aliases in openclaw.json:

"agents": {
  "defaults": {
    "models": {
      "amazon-bedrock/global.anthropic.claude-opus-4-6-v1": { "alias": "opus", "params": { "cacheRetention": "long" } },
      "amazon-bedrock/global.anthropic.claude-sonnet-4-6": { "alias": "sonnet", "params": { "cacheRetention": "long" } }
    }
  }
}

Step 7 — Verify

# macOS/Linux
node -e "const fs=require('fs'); eval('('+fs.readFileSync(process.env.HOME+'/.openclaw/openclaw.json','utf8')+')'); console.log('Config valid ✅')"

Check Prompt Cache hit rate after a few conversations with /status.

Priority Order (highest impact first)

1. tools.profile → full (broken without this)
2. SOUL.md core constraints (脚本优先 / API 优先 / 做完才说完)
3. Slim workspace files
4. Prompt Caching (cacheRetention: long)
5. Gemini web search (fixes search)
6. Gemini embeddings (fixes non-English memory recall)
7. Security hardening (firewall + permissions audit)
8. Context Pruning + Compaction (ttl aligned to heartbeat)
9. Install proactive-agent
10. qmd (after files accumulate)