agentheim

Launch, stop, or check the status of the local Agentheim dashboard web UI.

Cross-cutting technical specialist. Handles decisions that span bounded contexts or involve infrastructure: persistence choice, messaging, transport, deployment topology, library choice, integration with external systems, cross-cutting concerns (auth, observability, caching, rate limiting). Called when a task's shape depends on a tech decision bigger than a single BC's implementation.

Routes modeling and execution work to the right specialist agents. Called by the modeling skill (for refinement and capture) and the work skill (for task execution). Takes a task or question plus project context, decides which specialist(s) to consult, runs them (in parallel when the work is independent), aggregates results, and returns refined tasks / implementation plans / ADRs.

Fresh-eyes auditor for a researcher's just-written report. Reads the report and the original question — not the researcher's reasoning trail — and independently re-verifies the decision-critical checkable claims against primary sources via its own WebSearch/WebFetch. Emits a PASS / FAIL / SKIP verdict that determines whether `research` ships the report or re-dispatches the researcher. Has no Write or Edit tools — never edits the report, only judges it. Called by the `research` skill's post-write gate, once per report the researcher returns.

Web research specialist. Given a question or topic, runs WebSearch and WebFetch to gather information from external sources, cross-checks claims, and produces a citation-rich markdown report in .agentheim/knowledge/research/. Called by the research skill directly, and by other specialists or skills when they need outside knowledge to proceed.

Strategic DDD specialist. Identifies bounded contexts from vision and features, names them, classifies them (core / supporting / generic), and maps their relationships. Called when a feature crosses or reshapes context boundaries, when a context map needs to be created or updated, or when the question is "what belongs where".

Use whenever the user wants to start a new project, create a vision, do a Socratic modeling or discovery session, explore a problem space from scratch, or set up an initial context map and bounded contexts. Triggers on phrases like "let's brainstorm", "start a new project", "create a vision", "I want to build X", "model this out from scratch", "help me think through", "what should the shape of this be". Produces .agentheim/vision.md (and context-map.md if the domain is complex enough to warrant bounded contexts), and closes with an architecture foundation pass that unconditionally creates an `infrastructure/` BC (the standing home for globally-true tech concerns), emits decision tasks (globally-true → infrastructure BC, BC-local → originating BC), a walking-skeleton spike, and (when the vision implies frontend) a styleguide task. Deliberately produces no code — every output is markdown the user can review before `work` runs. Supports six switchable conversational modes (Interrogator [default], Suggestor, Challenger, Storyteller, Facilitator, Synthesizer) — see references/modes.md.

Answer a question about the codebase of an Agentheim-managed project — how a feature works, where something lives, what was decided and why, or whether something is built yet — by reading the project's own structure (the index, the bounded-context READMEs, the ADRs, the task boards) and verifying against the actual source. Read-only. Invoke it directly when you want a thorough, code-grounded answer that separates what's decided from what's actually implemented.

Use whenever the user wants to capture an idea, bug, feature request, refinement, or change to an existing bounded context — anything from "the button should be green" to "we need a whole new subscription subsystem". Also use when the user wants to refine existing backlog items or promote refined items to ready-to-work. Triggers on phrases like "I have an idea", "let's model this", "let's do some modeling", "capture this", "add this to the backlog", "refine the auth backlog", "promote X to todo", "we should also", "what if we added", "there's a bug", "change the color of", "the domain needs to handle". Creates task markdown files in the appropriate bounded context with the right status, and can spawn deeper modeling sessions via the orchestrator. Supports six switchable conversational modes (Interrogator [default], Suggestor, Challenger, Storyteller, Facilitator, Synthesizer) during CAPTURE and REFINE — see references/modes.md.

Use whenever the user wants to dump an idea, bug, or feature into the backlog FAST — no conversation, no questions, no refinement. This is the quick-jot entry point: the user is offloading a thought and wants to keep moving, not think it through. Triggers on phrases like "capture this", "jot this down", "quick capture", "note for later", "dump this in the backlog", "just file it", "add this without discussing", "brain-dump", "stick this in <bc>", "log this idea", "don't ask, just record it", and on rapid-fire multi-idea lists ("three things: A, B, C"). Routes each idea to the best-fit bounded context, writes one backlog task per idea, and reports where each landed in a single line — then gets out of the way. If the user instead wants to think an idea through, refine it, or talk it over, that's `modeling`, not this. Quick-capture never asks clarifying questions and never writes to todo — captured tasks are deliberately raw and always need a later refinement pass.

Use whenever the `research` skill is about to ship a researcher's report — between the researcher's return and the report being treated as citable knowledge. Triggers internally from `research`'s post-write gate. Spawns the `research-reviewer` agent with fresh context (no exposure to the researcher's reasoning) to re-verify the report's decision-critical checkable claims against primary sources and either PASS, FAIL with re-dispatch, or label the survivors unverified. Doctrine document; the operational steps live in `research`'s flow.