650ea3c804
Four knowledge skills auto-load into the main agent's context when their description matches the work; invokable explicitly via Skill(<name>): - agnes-orchestrator — extract.duckdb ATTACH flow, query_mode semantics, _remote_attach, rebuild lock - agnes-rbac — require_admin vs require_resource_access, ResourceType registration - agnes-connectors — _meta contract, three connector shapes, new-connector checklist - agnes-release-process — CHANGELOG discipline, release-cut, version bump, post-merge auto-rollback Three reviewer subagents fire in parallel at end of PR work; one releaser subagent handles pre-merge release-cut + post-merge tag / GitHub Release: - agnes-reviewer-rules — CHANGELOG bullet, vendor-agnostic scan, AI attribution, commit hygiene (always fires) - agnes-reviewer-rbac — endpoint gates, ResourceType registration (fires on app/api/, app/auth/ diffs) - agnes-reviewer-architecture — extract.duckdb invariants, schema migrations, rebuild lock (fires on src/, connectors/ diffs) - agnes-releaser — Phase 1 pre-merge release-cut commit; Phase 2 post-merge tag + GitHub Release .gitignore un-ignores .claude/agents/ and .claude/skills/ while keeping the rest of .claude/ local-only. CLAUDE.md gets a new 'Specialized agents and skills' section pointing at the two directories. Source of truth for the rules these encode remains CLAUDE.md + docs/RELEASING.md — skills explicitly defer to the master docs on conflict. Design rationale: docs/superpowers/specs/2026-05-15-agnes-agents-design.md Implementation plan: docs/superpowers/plans/2026-05-15-agnes-agents.md |
||
|---|---|---|
| .. | ||
| admin | ||
| archive | ||
| examples | ||
| HOWTO | ||
| metrics | ||
| operator | ||
| setup | ||
| superpowers | ||
| testing | ||
| ADR-corporate-memory-v1.md | ||
| agent-setup-prompt.md | ||
| agent-workspace-prompt.md | ||
| architecture.md | ||
| auth-google-oauth.md | ||
| auth-groups.md | ||
| CONFIGURATION.md | ||
| corporate-memory-governance.md | ||
| curated-marketplace-format.md | ||
| DATA_SOURCES.md | ||
| DEPLOYMENT.md | ||
| development.md | ||
| HEADLESS_USAGE.md | ||
| initial-workspace-override.md | ||
| llm-routing.md | ||
| local-development.md | ||
| marketplace.md | ||
| observability.md | ||
| ONBOARDING.md | ||
| PLATFORM_SETUP.md | ||
| QUICKSTART.md | ||
| RBAC.md | ||
| README.md | ||
| RELEASE_CHECKLIST.md | ||
| RELEASING.md | ||
| sample-data.md | ||
| state-dir.md | ||
| STORE_GUARDRAILS.md | ||
| theme-reference.html | ||
Agnes documentation
Index of all documentation, organized by who needs it. New here? Start with the row that matches your role.
| You are… | Start with |
|---|---|
| Analyst — using Agnes to query data | QUICKSTART.md, then HOWTO/ |
| Operator — deploying & running an instance | PLATFORM_SETUP.md |
| Developer — working on Agnes itself | ../ARCHITECTURE.md + architecture.md |
For analysts
Using the platform to analyze data.
QUICKSTART.md— local setup + first syncHOWTO/— task-oriented cookbook (querying, snapshots, common workflows)DATA_SOURCES.md— data source connectors (Keboola, BigQuery, CSV) and how tables surfacemetrics/— canonical business-metric definitions (YAML)HEADLESS_USAGE.md— PAT auth for CI / headless clients
For operators
Deploying, configuring, and running an Agnes instance.
PLATFORM_SETUP.md— the consolidated operator playbook (bootstrap, TLS, marketplaces, scheduler, telemetry)ONBOARDING.md— end-to-end Terraform deployment into a new GCP projectDEPLOYMENT.md— picks between the Terraform and Docker Compose pathsCONFIGURATION.md—instance.yaml, env vars, per-instance optionsstate-dir.md— persistent data layout (data+statetiers, mount layouts, migration)RBAC.md— access control: groups, members, resource grantsauth-google-oauth.md— Google OAuth setup + operator gotchasauth-groups.md— Google Workspace group syncadmin/query-modes.md— table registration query modesagent-setup-prompt.md— customize the/setuppage banneragent-workspace-prompt.md— customize the generated analystCLAUDE.mdinitial-workspace-override.md— per-instance analyst-workspace skeleton overridecurated-marketplace-format.md— authoringmarketplace-metadata.jsonfor curated marketplacesobservability.md— PostHog integration (exceptions, tracing, session replay)operator/news-content-guide.md— editorial guidelines for in-app news content
For developers
Working on the Agnes codebase.
../ARCHITECTURE.md— high-level system overview (the summary)architecture.md— detailed architecture reference (module map, extract.duckdb contract, components)../CLAUDE.md— project instructions for AI agents working in this repodevelopment.md— logging, request correlation, debug toolbarlocal-development.md—LOCAL_DEV_MODEsetup (what's mocked vs. real)RELEASING.md— release process, deploy workflows, CI quirksRELEASE_CHECKLIST.md— pre-merge checks for bootstrap-path changestesting/— test plans (clean-analyst bootstrap, VM test)marketplace.md— Claude Code marketplace ingestion + re-serving internalsSTORE_GUARDRAILS.md— flea-market upload guardrails (static checks + LLM review)corporate-memory-governance.md— knowledge-distribution governance designADR-corporate-memory-v1.md— ADR: corporate-memory v1 decisionsllm-routing.md— design: provider-agnostic LLM routingsample-data.md— sample data generator (e-commerce schema, size presets)theme-reference.html— web UI theme/color reference../dev_docs/— server/developer-internal docs (not synced to analyst machines): server ops, disaster recovery, security audit, desktop app, design system, Telegram bot
Code-adjacent READMEs: ../connectors/jira/README.md,
../services/corporate_memory/README.md,
../scripts/README.md.
Agent skill files: ../cli/skills/.
Other
../CHANGELOG.md— full change history (Keep-a-Changelog format)archive/— historical planning artifacts and superseded docs; not maintained, seearchive/README.md