Use this skill to optimize OpenClaw token usage with a local CLI that performs analysis, compression snapshots, health checks, cleanup planning, and preflight token budgeting.
$OPENCLAW_SKILLS_DIR/token-optimizer/scripts/token-optimize --analyze --period 7d
1) Enable local optimizer config:
$OPENCLAW_SKILLS_DIR/token-optimizer/scripts/token-optimize --enable
2) Optimization analysis:
$OPENCLAW_SKILLS_DIR/token-optimizer/scripts/token-optimize --analyze --period 7d
3) Force context compression snapshot:
$OPENCLAW_SKILLS_DIR/token-optimizer/scripts/token-optimize --compress --threshold 0.7 --session agent:main:main
4) Session health check:
$OPENCLAW_SKILLS_DIR/token-optimizer/scripts/token-optimize --health-check --active-minutes 120
5) Auto-cleanup planning and apply:
$OPENCLAW_SKILLS_DIR/token-optimizer/scripts/token-optimize --cleanup
$OPENCLAW_SKILLS_DIR/token-optimizer/scripts/token-optimize --cleanup --apply
Use preflight planning before expensive task batches:
$OPENCLAW_SKILLS_DIR/token-optimizer/scripts/token-optimize \
--preflight /path/to/actions.json \
--session-limit 180000
actions.json should be a JSON array of planned operations, for example:
[
{"type": "web_search", "query": "..."},
{"type": "web_fetch", "url": "..."},
{"type": "summarize", "target": "youtube"}
]
$OPENCLAW_WORKSPACE/token-usage/compressed/--format json --output /path/file.json--enable): $OPENCLAW_WORKSPACE/token-usage/token-optimizer.config.jsonDefault behavior is configured in:
config/defaults.jsonOverride with:
$OPENCLAW_SKILLS_DIR/token-optimizer/scripts/token-optimize --config /path/custom.json --analyze
scripts/token_optimize.py: main CLIsrc/optimizer.py: core optimization enginesrc/models.py: model selection logicsrc/compression.py: context compression helperssrc/cleanup.py: session hygiene evaluationreferences/operating-notes.md: implementation details and safe-operating guidancepython3 $OPENCLAW_SKILLS_DIR/.system/skill-creator/scripts/quick_validate.py \
$OPENCLAW_SKILLS_DIR/token-optimizer
共 1 个版本