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 agentmods add instructions/parad0x-labs/openclaw-skills/agents-mdgit clone --depth 1 https://github.com/Parad0x-Labs/openclaw-skillsWhat 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 | $0.09914 | $0.09914 |
| Opus 5 | $0.04957 | $0.04957 |
| Sonnet 5 | $0.01983 | $0.01983 |
| Haiku 4.5 | $0.00991 | $0.00991 |
Grade C, and why
openclaw-skills AGENTS.md scanned grade C with 1 finding 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 yesterday.
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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- **forbidden_path** (critical) — `.ssh/`, `.gnupg/`, `.aws/credentials`, `.kube/config` How it starts
The opening of the file, as written. The whole thing — 891 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Liquefy — AI Agent Interface
You are an AI agent. This file tells you everything you need to operate Liquefy. Read this FIRST. It replaces reading the README, docs, or source code for 95% of tasks.
One-Line Setup
macOS / Linux:
make setup
Or if make isn't available:
bash install.sh
Windows (PowerShell):
.\setup.ps1
Windows (CMD):
setup.bat
pip install (into existing project):
pip install git+https://github.com/Parad0x-Labs/openclaw-skills.git
Optional extras: pip install "liquefy-openclaw[vision,cloud,anchor,api,all] @ git+https://..."
Docker:
docker compose run liquefy tools/tracevault_pack.py ./data --org default --out ./vault/output --json
All paths create a virtualenv, install dependencies, run a smoke test, and print "READY".
What Liquefy Does
Liquefy compresses, redacts, and vaults AI agent workspace data (session logs, JSONL traces, artifacts, screenshots, memory files). It has 24 specialized compression engines that auto-detect data format and pick the best one. Everything is verified bit-perfect (MRTV — Mandatory Round-Trip Verification).
Quick Commands (Copy-Paste Ready)
All commands work from the repo root after make setup.
Compress a directory into a vault
make quick DIR=./path/to/data
Or explicitly:
python tools/tracevault_pack.py ./path/to/data --org default --out ./vault/output
Compress an OpenClaw workspace
python tools/liquefy_openclaw.py --workspace ~/.openclaw --out ./vault/openclaw --json
Works with any agent framework
Liquefy is framework-agnostic. OpenClaw, NanoClaw, LangChain, CrewAI, Claude Agent SDK, custom scripts — if it writes files, Liquefy handles it. No adapter needed.
# NanoClaw container output
python tools/tracevault_pack.py ./nanoclaw-runs/latest --org dev --out ./vault/latest
# LangChain traces
python tools/tracevault_pack.py ./langchain-output --org dev --out ./vault/latest
# Any agent output directory
make quick DIR=./my-agent-output
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.
- yesterday First seen · 891 lines · 9,914 tokens per session scan C c34dfa8d8620
openclaw-skills AGENTS.md is an instructions file published in the GitHub repository Parad0x-Labs/openclaw-skills (22 stars, last pushed 7d ago), licensed MIT. It adds 9,914 tokens to every session, about $0.0496 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
DeepSpeed AGENTS.md
AGENTS.md instructions for deepspeedai/DeepSpeed, covering deepspeed project rules, commit & ci requirements, code change discipline, tool caveats and edit tool auto-formatter.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
barkeep AGENTS.md
Instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.
blz AGENTS.md
Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.
CrewClaw AGENTS.md
Instructions for staruhub/CrewClaw, covering agents.md, project, boundaries (charter, 2026-07-10), commands and employee package rules.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.