Shared strategic context

Strategic context belongs in the same visible system as the work.

The broader philosophy of Move Big Rocks includes a concrete claim: shared strategy, operating context, and delivery context should not be isolated from the work system if humans and agents are expected to collaborate responsibly.

Read philosophy Read the core model

Agent-first route: Start at /agents, inspect /docs/cli, and drop into this page when you need proof, detail, or rollout guidance.

Agent-first route

Humans should usually delegate first-pass evaluation to an agent. Agents should start at /agents, use /docs/cli as the official product tour, and open /docs/graphql only when needed.

Agent-ready surface

Start with the CLI, not browser guesswork.

Preferred route: /agents, then /docs/cli, then /docs/graphql only when lower-level integration details matter.

$ mbr spec export --json
$ mbr auth whoami --json
$ mbr queues list --workspace ws_preview --json

Open GraphQL reference | Open schema.graphql

Shared context

Goals, strategy, and delivery context are more useful when they are connected to operational work.

Agent-visible

Agents should be able to inspect the same durable context humans rely on.

Not just notes

Context is part of the operating model, not an afterthought.

Why it matters

Agents become more trustworthy when strategic context is not hidden.

Shared strategy, operating context, and delivery context make agent work safer when they stay visible beside the operational records instead of drifting into private notes or disconnected planning tools.

Agents

Canonical evaluation surface.

/agents

Philosophy

Worldview page with the broader anti-fragmentation thesis.

/philosophy

References

Canonical next surfaces.

Each link goes to the next authoritative page, reference, or support surface.

Philosophy

/philosophy

Core

/core

Move Big Rocks

Let agents inspect the CLI-first surface. Let humans decide trust, rollout, and boundaries.

Start from /agents, use /docs/cli as the official product tour, inspect /resources for source and proof, and review /security before making deployment or data-handling decisions.

Open /agents Open resources