Quick Start with Halos Deployment Skill#
The agentic alternative to the manual profile guides (Base Profile and Quick Start Guide). Instead of running the steps yourself, drive the bring-up from natural language with a coding agent and the hoisa-deploy-profile skill.
The skill ships in the repo you cloned, at skills/hoisa-deploy-profile/. It is a developer-side tool following the agentskills.io specification: a coding agent (Claude Code, Codex, Cursor, or any agentskills.io-compatible host) loads it and operates the system for you. It reads the repo’s compose files, profiles, and configs, brings up the VSS Warehouse 3.2 perception backend first, then deploys the profile you ask for: base runs the Safety Core on the existing feed (overlay only), while sil adds the full closed loop (Isaac Sim, comm-layer, MediaMTX) and runs the test scenario.
Prerequisites#
In addition to the requirements in your profile’s guide (Base Profile or Prerequisites):
A coding agent on the host: Claude Code, Codex, or any agentskills.io-compatible host.
The Halos Outside-In Safety repo cloned on the host.
An NGC API key with access to
nvidia/halos-outside-in(the PSF image, plus the sil-data tarball forsil).
Install (recommended: ask your coding agent)#
Open the cloned repo in your agent and paste this prompt. It reads the skill manifests and symlinks them into the right place for your host:
Read skills/README.md and every SKILL.md under skills/, then install each skill
for this host by symlinking its folder into the host's skills directory:
- Claude Code: ~/.claude/skills/<name>/
- Codex: ~/.codex/skills/<name>/
- agentskills.io: ~/.agents/skills/<name>/
Symlink the folder rather than copying it, so a git pull here keeps installs
current. Also install the vss-deploy-profile skill from the VSS Blueprint
repository; the perception backend is deployed first. When done, list the
skills you registered and the directory you used.
Verify with /skills in your agent: hoisa-deploy-profile (and vss-deploy-profile) should be listed.
Note
Prefer to do it by hand? Symlink the skill yourself, using the absolute path to your checkout (ln -s resolves the target from the link’s directory, not your current directory):
mkdir -p ~/.claude/skills
ln -sfn /abs/path/to/halos-outside-in-safety/skills/hoisa-deploy-profile \
~/.claude/skills/hoisa-deploy-profile
Verify with ls ~/.claude/skills/hoisa-deploy-profile/SKILL.md.
Run#
Ask your agent in natural language. Pick the profile you want.
base (Safety Core on an existing VSS feed, overlay only):
Deploy the Halos Outside-In Safety base profile on this machine: bring up VSS
Warehouse 3.2 as the perception backend, deploy the base profile, and confirm
the halo_safety overlay reacts.
sil (full single-host closed loop with Isaac Sim):
Deploy the Halos Outside-In Safety sil profile on this machine: set up the VSS
Warehouse 3.2 perception backend, deploy the closed-loop stack, run the test
scenario, and show me the safety command output.
Deployment is long-running (NGC image pulls, the perception TensorRT engine build, and for sil the Isaac Sim shader compile), so use a high-context model at maximum effort. The agent pauses for host-level input it cannot do for you: sudo / system installs, the NGC API key, and the GPU / profile choice. If it has been silent for more than two minutes, scroll up; there is a question waiting.
Important
“Complete” means the safety decision reacts to the scene, not merely that all containers are up: for base the VST halo_safety overlay flips between Standard and Efficient Mode; for sil sim-driven MUTE / UNMUTE transitions appear in the logs.
Fallback#
If a coding agent is not available or the skill fails on a step, follow the manual guide for your profile (Base Profile or Quick Start Guide). The skill writes the same .env files the manual route uses, so a partial skill run can be resumed manually.
Next Steps#
Deployment Overview — Deployment overview and the profile model
Base Profile — base profile (x86 / IGX Thor)
Quick Start Guide — SIL closed-loop quickstart