agentheim

Plugin agentheim from marketplace agentheim in heimeshoff/Agentheim. Commands read from the repo's manifest — 11 days ago.

Skills (11)

• capture

  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 do

• brainstorm

  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 wan

• inquire

  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 ag

• modeling

  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 it

• quick-capture

  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 do

• research-review

  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'

• research

  Use whenever the user or another skill needs external information gathered from the web — state of the art on a topic, comparison of approaches, documentation for a library, domain knowledge from outside the codebase. Triggers on phrases like "research X", "find out about", "what's the state of the

• test-driven-development

  Use whenever a worker is about to implement a task with observable behavior — features, bug fixes, refactors that should preserve behavior, any change with acceptance criteria you could turn into an assertion. Triggers internally from the `worker` agent at the start of its third action ("do the work

• verification-before-completion

  Use whenever the `work` skill is about to commit a worker's `RESULT: SUCCESS` — between the worker's return and `git add/commit`. Triggers internally from `work`'s post-success gate. Spawns the `verifier` agent with fresh context (no exposure to the worker's reasoning) to inspect the diff against th

• whats-next

  Use whenever the user wants to know what to do next on an Agentheim project — they've just finished a batch of work, they're staring at an empty board, or they're simply not sure where to put their attention. Triggers on phrases like "what's next", "what should I do now", "what now", "where do I pic

• work

  Use whenever the user wants work executed on the todo backlog — running tasks, building features, implementing what has already been modeled. Triggers on phrases like "start working", "execute the todo", "work on it", "build it", "implement the backlog", "let's go", "run the workers", "pick up where

Slash commands (2)

• /agentheim:dashboard

  Pointer to the zero-token dashboard CLI. Run `/setup` once per machine, then use `agentheim-dashboard` directly from a shell.

• /agentheim:setup

  One-time, per-machine install of the zero-token Agentheim dashboard CLI and the VS Code bridge, and the choice of which bridge kind the dashboard uses. Re-runnable at any time.

Subagents (8)

• architect

  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 w

• orchestrator

  Routes modeling and execution work to the right specialist agents. Called by the modeling skill (for refinement and capture) and, for multi-specialist / conflict-surfacing questions, by workers during task execution — a worker facing a single-specialist question consults that specialist directly ins

• research-reviewer

  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 verdi

• researcher

  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

• strategic-modeler

  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 questi

• tactical-modeler

  Tactical DDD specialist inside a single bounded context. Reasons about aggregates, entities, value objects, domain events, commands, invariants, and the workflow / lifecycle inside a BC. Called when a feature or refinement needs the inner shape of a context worked out — not where it lives (that's st

• verifier

  Fresh-eyes auditor for a worker's just-completed task. Reads the task file's acceptance criteria, the diff produced by the worker, and the BC README. Runs the test suite. Emits a PASS / FAIL / SKIP verdict that determines whether `work` commits or re-dispatches. Has no Write or Edit tools — never ch

• worker

  Executes a single refined task end-to-end in its own git worktree, carrying source and tests only (ADR-0032/ADR-0038, amended by agentic-workflow-ghcaj — the conductor's mechanized batch claim already moved the task file from todo/ to doing/ on `main` before spawning). Consults a specialist directly

Similar plugins