ariffazil/spatial-grounding
skills/spatial-grounding/claude/SKILL.md
Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion
data-ai
Updated May 20, 2026
$ install --global
skillsauthnpx skillsauth add ariffazil/openclaw-workspace spatial-groundingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 20, 2026, 3:22 AM166.2s1 file scanned
SKILL.md
- name:
- spatial-grounding
- description:
- Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion
- version:
- 1.0.0
- author:
- Hermes Agent (arifOS Federation)
- license:
- MIT
- platforms:
- [linux, macos, windows]
- tags:
- [spatial-awareness, VPS, grounding, infra]
- related_skills:
- [anti-fabrication-protocol, federation-entities]
- risk_band:
- HIGH
- category:
- infra
- floors:
- [F1, F7, F9]
SPATIAL GROUNDING SKILL
When to Use
- New agent installed (Claude, Gemini, Kimi, OpenCode, Copilot, Codex)
- Agent exhibits "SSH to localhost" or "connect to remote" symptoms
- After config file corruption/reset
Trigger Conditions
- Agent binary newly installed
- Agent claims "SSH to VPS" despite being on VPS
- New session starts without VPS awareness
Procedure
Step 1: Identify Agent Config Path
| Agent | Path |
|-------|------|
| Claude | ~/.claude.json (field: spatial_context) |
| Gemini | ~/.gemini/system.md |
| Kimi | ~/.kimi/kimi.json (field: system_prompt_addon) |
| OpenCode | /root/.opencode/SPATIAL_LAW.md |
| Copilot | ~/.copilot/copilot-instructions.md |
| Codex | ~/.codex/config.toml (section: [context]) |
Step 2: Append SPATIAL_LAW
Append this text to the agent's config file:
SPATIAL LAW (arifOS Federation — Non-Negotiable)
=================================================
You execute on VPS 72.62.71.199, root user, native filesystem.
You are already ON the machine. Do NOT SSH to yourself.
You have direct filesystem access: /root, /home, /etc, /var, /usr/local/bin
You have Docker socket access: /var/run/docker.sock
You have service endpoints: arifOS:8080, GEOX:8081, WEALTH:8082, WELL:8083, A-FORGE:7071
All services bind 127.0.0.1 (localhost) — external via Caddy only.
Your working directory is /root — the arifOS federation root.
Do NOT claim "SSH to VPS" or "connecting to remote" — you are the remote.
Step 3: Verify
grep "72.62.71.199" <config-file>
# Must return at least 1 match
Expected Output
- Agent config patched with SPATIAL_LAW
grep "72.62.71.199" <config-file>returns match- Agent knows it executes on VPS 72.62.71.199
Failure Modes
- Config not writable → use sudo
- Verification fails → re-patch
- Agent ignores config → restart session
Pitfalls
- Do NOT use SSH to connect to the machine you're already on
- Do NOT claim "connecting to remote" when you are the remote
- All services bind localhost only — no direct internet exposure
Verification Commands
# Claude
grep "72.62.71.199" ~/.claude.json
# Gemini
grep "72.62.71.199" ~/.gemini/system.md
# OpenCode
cat /root/.opencode/SPATIAL_LAW.md | grep "72.62.71.199"
# Copilot
grep "72.62.71.199" ~/.copilot/copilot-instructions.md
# Codex
grep "72.62.71.199" ~/.codex/config.toml
Canonical source: AAA/wiki/skills/skill-spatial-grounding.md
DITEMPA BUKAN DIBERI — 999 SEAL ALIVE
Related Skills
ariffazil/AAA Agentic Governance (AAA-Cockpit, canonical)
development
VerifiedTrustedCommunity
Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.
SKILL.mdUpdated Jun 6, 2026
ariffazil/skill-trigger-linter
development
VerifiedTrustedCommunity
Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.
SKILL.mdUpdated May 27, 2026
ariffazil/skill-creator
development
VerifiedTrustedCommunity
Bootstrap, design, and package new skills. Load when capturing user intent for a new skill or drafting its initial instruction framework.
SKILL.mdUpdated May 27, 2026
ariffazil/Federation Service Health Triage
content-media
VerifiedTrustedCommunity
Diagnose which federation services are up, down, or drifting. Produce a prioritized remediation plan.
SKILL.mdUpdated May 27, 2026