Skip to content

Built-in Agents

Plugin

The plugin ships two built-in agents. They are focused, narrow specialists with the MCP tools they need and nothing more.

You rarely invoke agents directly — skills call them. But it helps to know what each does so you can reason about what’s happening when a skill delegates.

A universal read/write agent for complex multi-document tasks.

RoleRequirements engineering, multi-document planning, relation graph management.
ToolsAll 8 MCP tools (list_documents, get_document, create_document, update_document, remove_document, add_relation, remove_relation, list_relations), plus Read, Grep, Glob.
Max turns20
SafetyEvery .archcore/ write goes through MCP. Direct Write/Edit calls are not in its toolbox.
  • ISO track — building the full BRS → StRS → SyRS → SRS cascade.
  • Architecture track — wiring ADR → spec → plan with the right relations.
  • Large-scope refactors of .archcore/ across many files.
  • Keeping the relation graph consistent across five or ten documents at once.
  • Respecting document-type templates — filling the right sections, not just pasting prose.
  • Recovering from partial failures (a single validate error doesn’t blow up the whole track).

A read-only auditor for documentation health reviews.

RoleDetects coverage gaps, orphaned documents, stale statuses, consistency issues.
Toolslist_documents, get_document, list_relations, plus Read, Grep, Glob.
Max turns15
SafetyRead-only by design — cannot create, update, or delete documents.
  • Returning structured audit reports — not prose summaries.
  • Finding orphans: documents with no incoming or outgoing relations that probably should have some.
  • Spotting naming inconsistencies, tag hygiene issues, and missing frontmatter.

Separating the write-capable agent from the read-only one is a deliberate safety boundary. The auditor runs on every review, so it handles more documents and more contexts per week than the assistant does. Keeping it read-only means a review session can never accidentally mutate state.

  • Intent commands — the user-facing commands that call these agents.
  • Tracks — multi-step flows that use archcore-assistant.
  • Troubleshooting — issues you might see with agent invocations.