--- name: hypergrok-bootstrap description: Build and verify a HyperGrok autonomous desk from the pinned public release. Use for first-run setup, repair, or a readiness check. Starts with a live zero-key Opening Bell, installs the seven role profiles and twenty-four shared skills, prepares the Trading Floor, and returns an evidence receipt. Read-only by default; never requests a wallet or places an order. license: MIT metadata: version: "2.3.0" author: Galleon Labs category: desk --- # HyperGrok bootstrap Turn a fresh shared **Desk Lead** into a working HyperGrok desk. Finish with evidence, not a claim that setup probably worked. ## Safety boundary Bootstrap is research-only. - Do not request, read or store an API wallet, private key, seed phrase or exchange secret. - Do not call Hyperliquid `/exchange`, create an order, alter leverage, move funds or change approval settings. - Public `POST /info` market reads are allowed. State mainnet, request type and UTC time. - Local writes are limited to `/workspace/hypergrok` and `/workspace/trading-desk`. - Creating the seven named Bots and the private Trading Floor group is in scope. Sharing anything publicly is not. - If a capability is unavailable, return the exact manual card or step and continue independent supported work. Do not pretend it happened or mark dependent checks complete. ## 1. Install the reviewed release If `/workspace/hypergrok` is already a Git checkout, read its `plugin.json` and run its check; do not overwrite it. Otherwise: ```bash mkdir -p /workspace && cd /workspace git clone --depth 1 --branch v2.4.0 https://github.com/swcstudiospace/hypergrok-autonomous-desk.git hypergrok cd /workspace/hypergrok git rev-parse HEAD bash scripts/check.sh ``` Stop if the structural check fails. Record the printed commit for `desk.md`. ## 2. Ring the Opening Bell Show useful output before asking the user configuration questions: ```bash cd /workspace/hypergrok python3 scripts/opening_bell.py --coin ETH ``` Return the output verbatim. It is a public market snapshot, not a signal. If it is unavailable, say so and continue offline; do not substitute stale or invented figures. ## 3. Prepare the desk ```bash mkdir -p /workspace/trading-desk/{proposals,briefs,research,strategies,data,journal/incidents,watch,autonomy} cp -r /workspace/hypergrok/template/strategies/hg-systematic /workspace/trading-desk/strategies/ cd /workspace/hypergrok python3 scripts/desk_doctor.py --desk-root /workspace/trading-desk ``` A warning for the not-yet-written desk record is expected at this stage. A failed repository or public API check is not. The copied strategy folder is the engine's rule set at `status: paper`; bootstrap copies it and never starts the engine, edits `params.json` or changes the status line. ## 4. Build the team Read `docs/ARCHITECTURE.md`, `skills/desk-operating-model/SKILL.md`, every file in `agents/`, and `skills/README.md`. Create one Bot from each agent file's **Bot profile** and **System prompt**: 1. Desk Lead 2. Market Analyst 3. Research Analyst 4. Strategist 5. Risk Manager 6. Execution Trader 7. Trade Reviewer Use `assets/mascot.jpg` as the avatar when the product supports it. Do not add unrelated memories, conversation history or private files. If Bot creation is unavailable, return seven clearly labelled copy-and-paste cards and ask the user to create them. Continue independent local preparation and checks; keep Bot and group readiness pending until their existence is verified. Inspect the shared skills before installing anything. A Desk Lead added from the public HyperGrok template already carries the reviewed skill set; do not create duplicate skills. For each of the twenty-four `skills/*/SKILL.md` files: 1. If a shared skill with the exact `name` already exists and its instructions match this release, enable it for the Desk Lead and record `template`. 2. If it is missing, save the file unchanged and record `installed`. 3. If the product cannot save the full file, save a pointer skill that reads `/workspace/hypergrok/skills//SKILL.md` and record `pointer`. 4. If the name exists but the instructions differ and cannot be replaced with this release's reviewed file, record `mismatch` and fail readiness. Never claim a skill is current from its name alone. The final receipt must contain exactly twenty-four unique skill names and one status for each: `template`, `installed`, `pointer` or `mismatch`. Create a private group chat named **Trading Floor** with Desk Lead, Market Analyst, Research Analyst, Strategist, Risk Manager and Execution Trader. The Trade Reviewer stays in DM. Post the floor welcome message from `SETUP.md` section 6. ## 5. Record the research desk Unless the user explicitly selects testnet or mainnet, create a research desk: ```markdown # Desk record - created: - instructions commit: - engagement level: research - network: mainnet-for-reads - account: none - bots: Desk Lead, Market Analyst, Research Analyst, Strategist, Risk Manager, Execution Trader, Trade Reviewer - group chats: Trading Floor (6) - risk limits: not yet written - standing approvals: none - unprotected position deadline: not applicable - autonomy: off (autonomy.json not yet written) - status: research-only; no API wallet provisioned ``` Write it to `/workspace/trading-desk/desk.md`. Do not provision trading access during bootstrap. ## 6. Verify and return the receipt Run: ```bash cd /workspace/hypergrok python3 scripts/desk_doctor.py --desk-root /workspace/trading-desk python3 scripts/opening_bell.py --coin BTC ``` Then perform the five role checks in `SETUP.md` section 9. Return: - release tag and installed commit - Opening Bell source, network and UTC time - each Bot: created or manual card returned - each skill: full or pointer install - Trading Floor membership - desk doctor results, including warnings - five role-check results - exact local paths for `desk.md` and the repository - this sentence: **Setup stayed read-only: no key requested and no order created or sent.** Do not say the desk is ready if a required check failed. Name the failed check and the next safe action. ## 7. Autonomy is switched on later Bootstrap never writes `autonomy.json`, never creates `autonomy/gate.key`, never re-scopes an approval rule and never creates a routine. The desk it leaves behind is a research desk that reads. When the user wants the desk to trade on its own, they follow `desk-autonomous-loop` section 3 (Claude Code: copy the templates, edit the policy, run one cycle by hand, then schedule `scripts/autonomy_cycle.py`) or section 4 (Grok Bot: API wallet, `autonomy.json` confirmed by the user, Require Approval rule re-scoped, one Desk Lead routine on `cycle_interval_minutes`), and then `desk-multi-runtime` for starting the strategy engine on their runtime. Every step there is the user's, in that order, on testnet first. If the user asks bootstrap to "just turn it on", say which section to follow and stop.