Skip to main content

Commander

Commander is BattleGrid’s conversational control surface. You speak in plain language; it reads and writes the platform through the same capability catalogue external tools use over MCP.

It does not replace the Strategy Builder or the agent forms. When you need every dial laid out — metrics, conditions, signal rules, levels, exits, brain, risk — author there. Use Commander when you want to move faster in words, then refine in those surfaces.

The market is a battlefield. Commander is how you brief the grid without walking every panel first.

What it is for

IntentWhat Commander does
StrategiesDraft / tighten a playbook, then compile → review → apply
AgentsCommission, rebind, check risk rails, halt / resume
DeployPut agents on Radar or into Arena
Market & accountRegime, leaders, crowding, balance, slots, coverage
TradesQualification reads, open protections, debriefs, pending approvals

Create still ≠ deploy. Commissioning an agent does not put it on duty; Radar / Arena / the trade terminal are separate decisions.

Where it runs

One engine, several mounts:

SurfaceRole
Commander (main)Full conversations and the lander starters
Strategy hostDock beside the Strategy Builder — bound to the strategy you are editing
Agent hostLane beside an agent’s trade work — bound to that agent

A host conversation stays latched to that resource for the session. Host context shapes what Commander may safely change (for example, agent-host conversations refuse strategy-mutating writes that would surprise the builder). Other channels (where enabled) drive the same run runtime — same tools, same guards — with different identity plumbing.

How a turn works

  1. You send an ask (or pick a starter).
  2. Commander activates skills as needed — each skill widens the active tool families for that conversation.
  3. It calls platform tools (reads first; writes only when the ask requires them).
  4. Answers land as shaped cards (plans, reviews, confirmations) plus prose — not raw tool JSON.
  5. Spending or standing-authority actions ask for explicit confirmation before they commit.

Core families (account, market, agent discovery, and related reads) are always available. Heavier families — strategy studio, Radar wager, live trade control, and so on — unlock when a skill that needs them activates. That gating keeps ordinary chats cheap without hiding power once you ask for it.

Skills (intent packs)

Skills are playbooks Commander loads mid-conversation. Starters and freeform asks cue them. Common packs include:

Skill (examples)Typical work
strategy-authoring / strategy-examplesBuild, port, or tighten a playbook
agent-managementCommission, risk, bind
radar-deploymentOn-duty policies, “why isn’t it firing?”
strategy-doctorWhy an agent is quiet / halted
market-analysisRegime, leaders, crowding, levels
trade-analysis / trade-proposalPositions, debriefs, find a setup

You do not have to name a skill. Naming the outcome is enough; Commander activates what it needs.

Strategy changes: compile → apply

Strategy authoring through Commander follows a fixed contract (same as MCP):

  1. Compile a CREATE / UPDATE / RESTORE request into an approved plan + review context (column contracts, report preview, blast radius, revision diagnostics). Compilation does not mutate the live strategy; it parks a plan for apply.
  2. Review the plan — diffs, viability, bound-agent impact. Plan tokens expire after five minutes; recompile after expiry, catalog drift, revision drift, or a changed bound-agent fence.
  3. Apply only with the exact planToken and confirmation. The server re-derives dense scorecard / revision checks and rejects a mangled or stale token. There is no client-side rebuild of the plan body.

Focused one-rule edits and fork / archive / restore still use their own revision and confirm rules. Field guides: Strategies overview (identity, Briefing vs Policy, lifecycle) · Metrics · Conditions · Policy axes under Strategies.

Money and standing authority

Anything that moves funds, submits a wager, or grants standing autonomous authority (Radar policy upsert/delete, Arena deployment upsert/delete, halt/resume that changes whether capital can commit, close position, accept a pending entry, submit a grid) requires your confirmation in Commander — and, on MCP, the mcp:wager scope.

Reads, strategy configuration (non-financial), and agent setup that does not deploy capital stay on the read / configuration side. Details: MCP.

Limits that keep runs honest

Every run is bounded. When a bound hits, Commander stops visibly (a typed guard), never with a silent truncation:

Guard (concept)Meaning
Step capToo many tool steps in one run
Cost stopPer-run spend ceiling
Op budgetPer-user daily tool-execution budget (resets 00:00 UTC)
Run / chunk timeoutWall-clock or silence bound
Output limitOutput capped before a tool could run
Mutating tool interruptedA write may have completed — do not blind-retry
User stoppedYou pressed Stop — completed work still stands

One active run per conversation. Credits must clear the floor before a stream opens.

Conversations

Transcripts persist. Soft-delete hides a conversation without erasing transcript or billing rows — the audit trail stays. Reloading a conversation replays original messages and tool results; prompt-side compaction does not rewrite stored history.

Commander vs the rest of the product

LayerOwns
Commander / MCPPlain-language and programmatic control of the same catalogue
StrategiesThe playbook (briefing + policy)
AgentsBrain, bind, risk, account slot
Radar / Arena / TerminalWhere that agent works

Next: Prompt formula · MCP