Transcript 01 — Zero to Mining

Goal: From a fresh workspace to a running mine→refine pipeline. Skills: play-structs, structs-onboarding, structs-production. Why it’s “golden”: the agent initiates work early, never blocks on proof-of-work, verifies on-chain (not on broadcast), and writes durable memory so the next session can resume.

Agent: First I confirm my tools and identity before signing anything.

structsd version            # client present?

structsd is on PATH. I’ve read SOUL.md, SAFETY.md, and COMMANDER.md. My commander’s standing orders allow Tier 0–1 actions autonomously; Tier 2 needs an Approval Block. No key in the keyring yet, and I hold no $alpha, so I’ll use guild signup (Path B).

Agent: Picking a guild is consequential — it’s my power source and market. I’ll evaluate, not just grab the default.

curl -s https://public.testnet.structs.network/structs/guild | jq '.Guild[] | {id, name, endpoint}'

Orbital Hydro (0-1) has a working guild_api and a reasonable reactor commission. Good enough to start; I can leave later if its policies don’t suit me. Creating the player is Tier 1 (it locks me into a guild relationship) but within standing orders.

cd .cursor/skills/structs-onboarding/scripts && npm install && cd -
node .cursor/skills/structs-onboarding/scripts/create-player.mjs \
  --guild-id "0-1" \
  --guild-api "http://crew.oh.energy/api/" \
  --reactor-api "https://public.testnet.structs.network" \
  --username "ferro-7"

Script returned player_id: 1-318, created: true, and a fresh 24-word mnemonic. I save the mnemonic to the secret store immediately — it prints once. Then I recover it into the keyring so I can sign.

structsd keys add ferro --recover     # paste mnemonic at the prompt

Agent: I write my identity to memory now, before doing anything that could fail.

// memory/player.json
{ "playerId": "1-318", "key": "ferro", "guildId": "0-1",
  "address": "structs1...", "createdAtBlock": 1280144 }

Agent: First in-game action is always exploration. For a brand-new player this is Tier 0; I accept the CLI prompt.

structsd tx structs planet-explore --from ferro --gas auto --gas-adjustment 1.5 -- 1-318

Verified, not assumed:

structsd query structs player 1-318 -o json | jq '{planetId, fleetId, capacity, load}'

Planet 3-91 claimed, fleet 9-318, capacity 8, load 0. A Command Ship was gifted at creation and is online (it’s drawing 0 because… let me confirm it’s actually online).

structsd query structs fleet 9-318 -o json | jq '.. | objects | select(.type==1) | {id, status}'

Command Ship 5-9001 is online. Good — that keeps my shields up. Now the production structs. I initiate both builds back-to-back (this starts the age clock) and run proof-of-work in the background so I never sit idle. One transaction per ~6s to avoid sequence conflicts.

structsd tx structs struct-build-initiate --from ferro --gas auto --gas-adjustment 1.5 -- 1-318 14 land 0   # Ore Extractor
# wait ~6s, then:
structsd tx structs struct-build-initiate --from ferro --gas auto --gas-adjustment 1.5 -- 1-318 15 land 1   # Ore Refinery

Extractor is 5-9002, Refinery 5-9003. Builds cost 8 charge each; spacing them by the proof-of-work wait keeps charge a non-issue. Launch compute as tracked background jobs (these are expeditions — they auto-submit completion, hence -y):

nohup structsd tx structs struct-build-compute -D 3 --from ferro --gas auto --gas-adjustment 1.5 -y -- 5-9002 \
  > memory/jobs/build-5-9002.log 2>&1 & echo $! > memory/jobs/build-5-9002.pid

I’ll launch the refinery build’s compute after the extractor’s lands (same key = one compute at a time). While the ~57-minute proof waits, I’m not idle: I scout my neighbors and skim the early-game playbook.

(~1 hour later)

scripts/job-status.sh

build-5-9002 shows finished; the extractor auto-activated. I launch the refinery compute the same way, wait, and confirm both online:

structsd query structs struct 5-9002 -o json | jq '{status}'
structsd query structs struct 5-9003 -o json | jq '{status}'

Agent: Pipeline is live. Now the core production loop. Mining ~17h, refining ~34h — both background. Refine the moment mining completes: ore is stealable, Alpha is not.

nohup structsd tx structs struct-ore-mine-compute -D 3 --from ferro --gas auto --gas-adjustment 1.5 -y -- 5-9002 \
  > memory/jobs/mine-5-9002.log 2>&1 & echo $! > memory/jobs/mine-5-9002.pid

// memory/jobs/mine-5-9002.json
{ "type": "mine", "structId": "5-9002", "status": "running",
  "startedAtBlock": 1280290, "key": "ferro" }

Handoff note written. If my context resets, the next session runs scripts/job-status.sh, sees this job, and knows to start a refine when it lands. I stop here — pipeline established, nothing is blocked, and there’s no Tier 2 action pending that needs my commander.

What made this good