code-diligence

Plugin code-diligence in AeyeOps/aeo-diligence-marketplace. Commands read from the repo's manifest — 22 days ago.

Skills (6)

• aeo-diligence-ask

  Answer exploratory follow-up questions about an ingested code-diligence target using its warehouse and repository evidence. For tool-output mappings use aeo-diligence-tool-output.

• aeo-diligence-axes

  Reference for the People / Product / Process taxonomy, card-to-table mappings, confidence model, and narrative-writing contract (headline-first, cite warehouse numbers, state evidence gaps). Use when interpreting what a dashboard card measures, writing or updating narrative rows, understanding confi

• aeo-diligence-dashboard

  Build or rebuild the Observable dashboard from an existing code-diligence warehouse, including after curation or narrative changes. Does not refresh source repositories.

• aeo-diligence-ingest

  Set up a new code-diligence target or ingest its repositories for the first time. For a target that already has a warehouse, use aeo-diligence-refresh.

• aeo-diligence-refresh

  Refresh an existing code-diligence target after its source repositories change, preserving analyst-confirmed curations. Applies to requests to rerun or update target data, not to rebuild only the dashboard.

• aeo-diligence-tool-output

  Reference for mapping raw tool output (code-maat, hercules, git-of-theseus, git-fame, git-truck, repowise) to warehouse tables, tool-specific quirks, and cross-check rules. Use when debugging warehouse mismatches, investigating why two tools report different values for the same metric, deciding whic

Subagents (2)

• diligence-asker

  Conversational drill-down analyst for code-diligence. Read-only access to a target's warehouse and cloned repos. Use when the user invokes /code-diligence:aeo-diligence-ask, or when they ask exploratory follow-up questions about a target after running ingest.

• diligence-narrator

  Generates evidence-grounded narrative summaries for code-diligence dashboard cards. Use when called by the code-diligence ingest or refresh skill at the end of a tier; not user-invoked.

MCP servers (1)

• diligence-warehouse

  runs: ${CLAUDE_PLUGIN_ROOT}/bin/run --directory ${CLAUDE_PLUGIN_ROOT}/mcp/diligence-warehouse python -m server --warehouse ${DILIGENCE_WAREHOUSE_PATH}

Hooks (2)

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/rebuild_dashboard.sh"

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/hooks/session_start.sh"