rohitg00/agentbrain

brain-brief

Agent Brain /brain-brief: after intake, research, and grill have enough signal.

brain-build

Agent Brain /brain-build: an implementation plan has a selected task and validation method.

brain-design

Agent Brain /brain-design: a product brief needs ux or interaction design before planning.

brain-eval

Agent Brain /brain-eval: changing Agent Brain behavior or checking quality.

brain-grill

Agent Brain /brain-grill: the idea, brief, design, or plan has unresolved assumptions.

brain-learn

Agent Brain /brain-learn: after repeated success/failure, a tricky fix, or a shipped workflow.

brain-plan

Agent Brain /brain-plan: the brief/design is strong enough to implement.

brain-research

Agent Brain /brain-research: the decision depends on external evidence or unfamiliar domain context.

brain-review

Agent Brain /brain-review: after verification or before public/shipping decisions.

brain-ship

Agent Brain /brain-ship: a reviewed artifact is ready for release or publication.

brain-should-this-exist

Agent Brain /brain-should-this-exist: before planning any new product, feature, workflow, or automation.

brain-start

Agent Brain /brain-start: a user starts from a vague request, idea, task, or product ambition.

brain-verify

Agent Brain /brain-verify: after build or when evaluating an existing artifact.

brain-wiki

Agent Brain /brain-wiki: ingesting sources or updating durable project knowledge.

context-memory

Use when deciding what project context should be remembered, retrieved, updated, or deliberately forgotten.

runtime-lifecycle

Use when verification depends on agent runtime phases, queued input, tool-call lifecycle, save points, retry, abort, compaction, or branch behavior.

activity-recap

Use when the user needs a standup-ready summary of recent project activity from local evidence.

artifact-contract

Use when an output artifact, template, schema, example, or handoff field must stay aligned across commands, skills, docs, and validators.

command-routing

Use when an agent runtime must choose or verify a /brain-* command route from a user request, handoff, adapter transcript, or stale command catalog.

runtime-smoke

Use when checking Agent Brain inside a real agent runtime or adapter before trusting harness usability.

adapter-capability-probe

Use when a command, adapter, or runtime smoke depends on proving an agent runtime's capabilities before trusting command routing, writes, shell access, or validation claims.

agent-output-verifier

Use when agent-produced work needs a safety, evidence, and reliability check before handoff, merge, or trust.

ci-recovery

Use when local validation and remote workflow status must be reconciled before trust, merge, or shipment.

design-grill

Use when a design needs pressure-testing for UX, information architecture, states, and accessibility.

domain-language

Use when project vocabulary is fuzzy, overloaded, disputed, or needed before naming docs, schemas, commands, skills, code, plans, or memory.

engineering-grill

Use when an engineering plan needs pressure-testing for architecture, complexity, data, risk, and operability.

evidence-research

Use when sources need to be converted into a claim ledger with confidence levels.

intake

Use when raw intent must be captured and routed to the right next state.

launch-gate

Use when a launch needs a go/no-go decision with rollback and monitoring evidence.

learning-capture

Use when repeated wins or failures should become durable memory, wiki, or skill updates.

market-grill

Use when a product idea needs pressure-testing against alternatives, category, urgency, and distribution.

plan-slicing

Use when broad work needs to be broken into small verifiable slices.

problem-grill

Use when a product or feature idea needs pressure-testing against problem, user, pain, success, and timing.

qa-evidence

Use when behavior needs concrete proof before review, merge, or shipment.

question-ladder

Use when uncertainty remains and the minimum useful sequence of questions should be asked.

wiki-maintenance

Use when source-backed project knowledge needs to be created, refreshed, or corrected.