Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Parad0x-Labs/openclaw-skills --skill liquefy-openclawgit clone --depth 1 https://github.com/Parad0x-Labs/openclaw-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/parad0x-labs/openclaw-skills/liquefy-openclaw)<a href="https://agentmods.dev/skills/parad0x-labs/openclaw-skills/liquefy-openclaw"><img src="https://agentmods.dev/badge/skills/parad0x-labs/openclaw-skills/liquefy-openclaw/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/parad0x-labs/openclaw-skills/liquefy-openclaw"><img src="https://agentmods.dev/badge/skills/parad0x-labs/openclaw-skills/liquefy-openclaw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.01112 |
| Opus 5 | $0.00030 | $0.00556 |
| Sonnet 5 | $0.00012 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
liquefy-openclaw scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Liquefy OpenClaw
Data handling (v0.1.1): This skill passes workspace paths and policy values through an inline vault-scan gate before any data reaches the Liquefy CLI. The gate strips API keys, tokens, credentials, PII, and card numbers and replaces them with typed placeholders. No matched values are logged — only category counts. Workspace files are processed locally by the Liquefy CLI; nothing is transmitted to external services.
Use this skill when the user wants to:
- scan or pack an OpenClaw workspace with Liquefy
- install or inspect Liquefy inside OpenClaw itself
- vault OpenClaw session/state directories
- search or restore from an existing Liquefy vault
- understand why Liquefy denied a path
- run OpenClaw with rollback, context budgeting, replay blocking, or restore-on-failure
- protect OpenClaw state or pulled history before risky actions
Start Here
- Plugin tools:
liquefy_scanfor read-only workspace inspectionliquefy_pack_applyfor explicit pack/apply
- Local CLI:
liquefy openclaw --jsonliquefy openclaw run --jsonpython tools/openclaw_tracevault.pypython tools/liquefy_openclaw_plugin.py hook install|uninstall|statusliquefy searchliquefy restoreliquefy safe-run --jsonliquefy context-gate compile --jsonliquefy context-gate history --jsonliquefy state-guard ...liquefy history-guard ...
Current truth:
- the plugin wrapper exposes
scanandapply - hook integration, session vaulting, restore/search, state-guard, history-guard, guarded run, context gate, and replay history are local Liquefy flows, not plugin tools
Hard Rules
- Prefer read-only scan before any write/apply action.
- Do not ask for
--include-secretsor risky allow-category overrides unless the user explicitly wants denied paths included. - Do not pretend the OpenClaw plugin exposes guarded execution. For runtime protection, use local Liquefy CLI/native integration.
- If the user asks for protection on the next OpenClaw run, do not use raw
openclaw run; preferliquefy openclaw runorliquefy safe-run. - If
context-gatereportsblocked=true, stop and explainblock_reasoninstead of trying to route around it. - If secure pack/apply is requested, ensure
LIQUEFY_SECRETexists before enabling--secure.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 93 lines · 59 tokens per session scan A 26ee998762fa
liquefy-openclaw is a skill published in the GitHub repository Parad0x-Labs/openclaw-skills (22 stars, last pushed 9d ago), licensed MIT. It adds 59 tokens to every session and 1,112 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
engraphis-memory
Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…
memorywhale
Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…
card-refresh
Use when refreshing stale Brigade memory cards from the care refresh queue - category allowlist, grounded edits that cite on-disk sources of truth, archive-only retention, and reinforce-in-place instead of near-duplicate siblings (#724). Never delete, remove, or prune.
furl
How the Furl context-compression plugin works in Claude Code and Codex — the furlcompress / furlretrieve / furlstats / furlpurge / furlsearch / furllist MCP tools, the > retrieval flow, and Claude Code's optional automatic hooks. Use when the user asks what Furl is doing, how to compress or retrieve content, why…
help
Show how to use Cortex persistent memory. Use when the user asks about Cortex, memory, storing decisions, or recalling past work.
recall
Search Cortex memory for past decisions, conventions, and lessons. Use when the user asks about previous work, past decisions, or what they learned about something.