- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add galleonlabs/hypergrok-trading-desk --skill desk-incident-response -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add galleonlabs/hypergrok-trading-desk --skill desk-incident-response -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add galleonlabs/hypergrok-trading-desk --skill desk-incident-response -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add galleonlabs/hypergrok-trading-desk --skill desk-incident-response -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/galleonlabs/hypergrok-trading-desk/tree/HEAD/skills/desk-incident-responseDe l'éditeur
An incident is any moment when the exchange record and the desk's expectation disagree, or when the desk cannot see the exchange at all. The reflex is: stop adding, look, contain with approval, then review. Never widen the harm by improvising.
Any Bot can declare an incident. Post on the floor:
INCIDENT INC-20260817-01 | 11:40 UTC | HG-20260817-02 | send timeout, result unknown | owner: Execution Trader
The Desk Lead confirms an owner (usually the Execution Trader for order/position incidents, the Risk Manager for exposure incidents, the Desk Lead for access incidents). New proposals pause until the incident is contained.
orderStatus by cloid; openOrders; userFills since the send; clearinghouseState.expiresAfter deadline has passed, then reconcile again. Expiry prevents later acceptance; it does not cancel an order accepted before the deadline or remove its fills.desk-execution-protocol: a noop needs an exact recovery ticket, Risk PASS, approval by id and native-gate coverage, and must use the original exact signed nonce, the same API wallet signer and network. Only the Execution Trader sends it, once. Confirm noop acceptance and reconcile the original; a newer nonce cannot invalidate it, and a nonce-reuse rejection does not prove what happened. Missing original nonce or an unconfirmed noop leaves the send reserved and new risk paused; escalate to the Desk Lead and user.error): quote it, map it via hyperliquid-api-reference (price precision, minimum notional, insufficient margin, reduce-only would increase position, invalid tif...). Fix is a new ticket, not a tweak-and-resend.normalTpsl children were never placed (children appear only when the parent fills fully, or is partially filled and then margin-cancelled), so the filled part is unprotected: report the actual size and get a stop for that size placed at priority (playbook D).clearinghouseState and userFills for the last hour; establish the exact state.normalTpsl children.desk.md, or a valid standing mandate covers this account and network, the Execution Trader places it under that authority and journals it. Under a mandate this is an alert to the user, not a suspension of the mandate. This is the one standing approval the desk actively recommends the user grant at setup, on every network, because it can only ever reduce risk.desk.md (fifteen minutes is a reasonable default), and when that passes, tell the user plainly that the fastest fix is theirs - close or protect the position in the Hyperliquid app - rather than continuing to ping a channel nobody is reading.desk.md. Confirm from openOrders.orderStatus; check whether it is a trigger child of a grouped order; try cancelByCloid if cancel by oid fails; if still stuck, report with the exact response and stop./info failing or slow: mark the desk blind; no new tickets; watches log the outage; check https://api.hyperliquid.xyz/info with a tiny allMids call every minute; report when back.userRateLimit for the account's remaining budget.hyperliquid-websocket's gap/restart procedure: restore account and detailed order snapshots, recover overlapping fills, reconcile reservations and protection, then let Risk recheck capacity before new risk resumes. A successful public price read or a restarted process cannot lift the account pause. Protection and exits still use verified live state and the normal approval gates.Signs: orders or fills the desk did not send, leverage changes nobody approved, unfamiliar cloids.
/API) - the desk cannot do this for them and must not delay them.historicalOrders and userFills since the last known-good time; Risk Manager assesses exposure; emergency reduce or protection tickets as needed after the user creates a fresh API wallet and re-provisions it through the secure secret store.Remember the shared computer: every Bot could read the key's environment; that is why only an API wallet key (trade-only, cannot withdraw) is ever provisioned, and why testnet comes first.
Not an incident, but handled like one: Risk Manager posts it, desk.md gets status: no-new-risk, protective and exit tickets continue, new risk waits for the user's written reset. A standing mandate's own daily loss stop suspends the mandate for the rest of the UTC day instead: the Trade Reviewer journals mandate suspended mandate <written> reason daily-loss-stop, the user is alerted, and new sends need approval by id until 00:00 UTC.
A rejected order, stale or unreadable data, or a position without a resting stop does not suspend a standing mandate. Alert the user and handle the affected ticket with the playbooks above: a rejection voids its ticket, stale data REJECTs it for missing input, and a missing stop gets protection at priority. An unknown send result is never resent, whatever the mandate allows. Only the mandate's daily loss stop, its expiry, deleting the block or standing mandate: revoked end or suspend it.
desk.md, or a valid standing mandate when the action is inside it).The Trade Reviewer writes the incident review (desk-post-trade-review), the Desk Lead lifts the proposal pause and records the corrective action and its owner in desk.md.
What the desk does when something goes wrong on Hyperliquid - unknown send results, unexpected fills or positions, unprotected positions, stuck or orphaned orders, API outages, rate limiting, and susp
---name: desk-incident-responsedescription: What the desk does when something goes wrong on Hyperliquid - unknown send results, unexpected fills or…---# skills/desk-incident-response/SKILL.mdVue d'ensemble
What the desk does when something goes wrong on Hyperliquid - unknown send results, unexpected fills or positions, unprotected positions, stuck or orphaned orders, API outages, rate limiting, and suspected API wallet compromise. Contain first, reconcile from the exchange record, act only through approved tickets, then review. Use the moment anything does not match the ticket.
FAQ
Téléchargez skills/desk-incident-response/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/galleonlabs/hypergrok-trading-desk.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.