liquefy-token-guard
Skill22 starsChanged 40 days agoMITView on GitHub
Token usage auditor and budget guard for OpenClaw agents — scans traces for waste (duplicate prompts, oversized context, model overkill), writes budgets, and builds a compact context capsule so the next run starts lean.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- context-capsuleSkill
- liquefy-archiveSkill
- liquefy-openclawSkill
- parad0x-mcp-serverSkill
- openclaw-x402-gateSkill
- openclaw-x402-paySkill
The file
Files
Liquefy Token Guard
Finds where your agents are wasting tokens and gives concrete fixes. Does NOT
silently rewrite prompts or guess costs — every report declares its truth mode
(exact, estimated, manual, or unavailable).
build_capsule is deterministic. It keeps the sharp parts and measures the
reduction — no LLM summary, no invented numbers.
Commands
| Command | Description |
scan_now | Scan trace directory, update token ledger |
audit_now | Detect waste: duplicate prompts, oversized context, model overkill |
set_budget | Write/update token and cost budgets |
build_capsule | Build a compact context capsule (deterministic, measured reduction) |
prime_next_run | Install capsule bootstrap for the next run |
status | Combined scan + report + audit summary |
recommend | Action-focused fixes from current waste findings |
daily_guard | Full scan/audit cycle, compact summary |
Install
cp -r skills/liquefy_token_guard ~/.openclaw/skills/Pairs with Liquefy Archive — Token Guard finds waste, Archive moves cold
artifacts into verified .null vaults.
Source
github.com/Parad0x-Labs/openclaw-skills/tree/main/skills/liquefy_token_guard
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.