Hyperloom Setup

What it does

When your agent uses it

• Tasks that involve Containers
• Tasks that involve LLM inference and serving

Example prompts

• “Use the hyperloom-setup skill to configure Hyperloom after pip install --target . An agent skill from AMD-AGI/Hyperloom”
• “/hyperloom-setup”

Requirements

• Python 3
• Docker
• A credential in ANTHROPIC_API_KEY

Workflow steps

7 steps, taken from the step headings in SKILL.md.

1. 1Confirm Workspace
2. 2Ask Configuration Questions
3. 3Write .env
4. 4Run Setup Backend
5. 5Confirm Detected Framework
6. 6Report Result
7. 7Hand Off to a Demo Skill

What it can do on your machine

Read from SKILL.md and the folder at commit f2b32cd. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python3
  • docker
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.anthropic.com
  • llm-api.amd.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • ANTHROPIC_API_KEY
  • HYPERLOOM_KB_TOKEN
  • HYPERLOOM_GLOBAL_KB_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hyperloom Setup loads about 7.2k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 3,832 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~73

When it runs · the whole SKILL.md, loaded when a task matches

~7.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:3

  t baremetal or Docker execution, writing .env, deploying the workspace's local Experience KB service, and running the se

• NoteMentions a .env fileSKILL.md:21

  that setup may create or update `.env` in that directory.

• NoteMentions a .env fileSKILL.md:25

  on the host; in `docker` mode it writes `.env`

• NoteMentions a .env fileSKILL.md:34

  - `docker`: writes `.env` and records the run mode; the example (workload) skill

• NoteMentions a .env fileSKILL.md:43

  selected mode recorded in the workspace `.env`, if the shell value is unset or empty.

• NoteMentions a .env fileSKILL.md:54

  writing `.env`, write `.env`, read it back for validation, and continue to the

• NoteMentions a .env fileSKILL.md:92

  Explain that secrets must be edited in `.env`, not pasted into chat.

• NoteMentions a .env fileSKILL.md:94

  - Create `.env` with placeholders for secret values.

• NoteMentions a .env fileSKILL.md:95

  - Ask the user to edit `.env` directly and replace placeholders.

• NoteMentions a .env fileSKILL.md:123

  valid choice in the shell or workspace `.env`; confirm and use that choice.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 3,832 words (~7,177 tokens).

name

hyperloom-setup

Read the full SKILL.md on GitHub

Files

Just SKILL.md in src/hyperloom/skills/hyperloom-setup of AMD-AGI/Hyperloom.

Open the folder on GitHubat commit f2b32cd