ArchitectureA guided teardown of the harness
The mission is the unit of work. Agents are workers inside it.
One durable loop holds the objective, your approved plan, isolated specialists, execution surfaces, and the memory the next mission can use.
Interactive cutaway · hover a layer to inspectOne objective passes through all five
A mission is a state machine, not a chat.
The objective is the durable thing. Its state survives the session, plan mode blocks for approval, and bounded specialist work stays attached to the same local mission.
- state
- persisted beyond the session
- gate
- human approval is a state, not a popup
- review
- separate mutation-disabled profile
- to
- repo agent 1 of 4
- model slot
- “frontier” · routed by you
- repository
- api-gateway · branch mission/rl-311
- objective slice
- enforce per-tenant limits at the edge
- pinned contract
- rate-limit headers v1 · read-only
tools granted
out of bounds: unassigned repositories · unrelated credentials · reviewer mutation
exit: bounded work complete · ready for review
The packet is the whole world that agent sees.
Specialists get a packet, not the keys.
The orchestrator splits the plan into work orders: one repository, one objective slice, the pinned contract, an allowed toolset, and a model slot. Everything outside the packet does not exist for that agent.
- isolation
- one boundary per agent
- contract
- pinned before any code changes
- verifier
- independent · writes no code
One mission across every available surface.
Code, browser, terminal, monitors, automations, and personal memory remain attached to the same objective instead of becoming unrelated sessions.
Repositories
local git
readsregistered checkouts · files · history
writesisolated specialist worktrees
localBrowser
mission surface
readsvisible and interactive page state
writesclick · type · navigate when allowed
availableTerminal
local process
readsstdout · stderr · exit state
writescommands within role capability
availableMonitors
mission schedule
readsrecurring check results
writesstatus attached to the mission
availableAutomations
local harness
readstask and prior execution context
writesscheduled engineering work
availableMemory
local service
readsscoped · cited · relevant records
writesreview · accept · dismiss · forget
reviewedAutonomy with an observed impact map.
Four standing rules bound every mission. They are not settings buried in a menu — they are how the loop itself is built, and every one of them leaves a trace you can replay.
- default
- read-only until the plan says otherwise
- approvals
- consequence-triggered · yours to widen
- audit
- every action attributable
- reviewer proof
- agent-profiles.test.ts
Start read-only
Every mission opens in discovery. Writes are explicit, later states.
Gate on consequence
Plan mode blocks until you approve the implementation boundary.
Execute locally
Agents run on your linked Mac with your repositories and local credentials.
Record everything
Actions, prompts, and approvals land in the mission log, replayable.
audit / rl-311
t+00:06plan proposed · implementation blocked
t+00:09plan approved · boundary pinned
t+00:33read-only reviewer report attached
+outcomerate limits enforced at api-gateway · limits.yaml per plan tier
+constraint429 responses must carry Retry-After · v1 clients surface it
~ownershipplatform-infra owns the redis cluster (updated)
The machine gets smarter on the way out.
Completion is a write, not a wrap-up. Outcomes, constraints, and ownership facts are committed with evidence links — so the next mission recalls instead of rediscovers.
Pick the next panel to open.
Watch it run
One real mission, phase by phase, timestamps included.
Open the mission replay
knowledgeWhat it keeps
The recall console: shared engineering knowledge plus agent memory.
Open the knowledge system
plansWhat it costs
Free on Desktop with your keys. The harness is the product.
Open the spec sheet
Questions
The machine, precisely.
Short answers about trust boundaries and moving parts. For the running system, watch a mission replay.
01What persists?+
The mission objective and state survive the session, so work can continue without becoming a new chat-shaped project.
02When does implementation start?+
Plan mode blocks until you approve the plan. The approved boundary then guides specialist work.
03What can specialists use?+
The current harness exposes code, browser, terminal, monitors, and automations according to each role's capabilities.
04What does independent review mean?+
The reviewer receives only file.read, file.search, and agent.report, receives read-only capability operations, and has mutationAllowed set to false.
Housing back on
Now give it an objective.
Skyflo Desktop is free with your own API keys or local models. The whole machine — loop, agents, bus, knowledge — arrives in one install.
Local execution, with no markup on BYOK or provider-direct usage.