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
165 lines
2.6 KiB
Text
165 lines
2.6 KiB
Text
# Claude Code
|
|
.claude/*
|
|
!.claude/agents/
|
|
!.claude/skills/
|
|
CLAUDE.local.md
|
|
|
|
# Local dev data (copied from server for testing)
|
|
dev_data/
|
|
session-analysis/
|
|
|
|
# CLI sync artifacts (local parquets + DuckDB)
|
|
server/
|
|
user/
|
|
|
|
# Environment variables
|
|
.env
|
|
.env.local
|
|
.env.development
|
|
.env.test
|
|
.env.production
|
|
.env*.local
|
|
|
|
# Operating System
|
|
.DS_Store
|
|
.DS_Store?
|
|
._*
|
|
.Spotlight-V100
|
|
.Trashes
|
|
ehthumbs.db
|
|
Thumbs.db
|
|
*.swp
|
|
*.swo
|
|
*~
|
|
|
|
# IDEs and Editors
|
|
.vscode/
|
|
.idea/
|
|
*.sublime-project
|
|
*.sublime-workspace
|
|
.project
|
|
.classpath
|
|
.settings/
|
|
*.iml
|
|
|
|
# Python
|
|
__pycache__/
|
|
*.py[cod]
|
|
*$py.class
|
|
*.so
|
|
.Python
|
|
build/
|
|
develop-eggs/
|
|
dist/
|
|
downloads/
|
|
eggs/
|
|
.eggs/
|
|
lib/
|
|
lib64/
|
|
!cli/lib/
|
|
parts/
|
|
sdist/
|
|
var/
|
|
wheels/
|
|
*.egg-info/
|
|
.installed.cfg
|
|
*.egg
|
|
MANIFEST
|
|
.pytest_cache/
|
|
.coverage
|
|
.coverage.*
|
|
htmlcov/
|
|
.tox/
|
|
.nox/
|
|
.mypy_cache/
|
|
.dmypy.json
|
|
dmypy.json
|
|
.pyre/
|
|
venv/
|
|
.venv/
|
|
env/
|
|
ENV/
|
|
env.bak/
|
|
venv.bak/
|
|
|
|
# Node.js
|
|
node_modules/
|
|
npm-debug.log*
|
|
yarn-debug.log*
|
|
yarn-error.log*
|
|
.npm
|
|
.yarn/cache
|
|
.yarn/unplugged
|
|
.yarn/build-state.yml
|
|
.yarn/install-state.gz
|
|
.pnp.*
|
|
|
|
# Logs
|
|
logs/
|
|
*.log
|
|
|
|
# Temporary files
|
|
*.tmp
|
|
*.temp
|
|
.cache/
|
|
prototypes/*
|
|
scripts/metadata_writer/proposals/*
|
|
|
|
# Build outputs
|
|
dist/
|
|
build/
|
|
out/
|
|
target/
|
|
|
|
# SSH keys
|
|
.ssh/
|
|
|
|
# Instance configuration (contains secrets and instance-specific values)
|
|
config/instance.yaml
|
|
config/data_description.md
|
|
|
|
# Instance-specific data description (generated per-instance)
|
|
docs/data_description.md
|
|
|
|
# Project-specific: Data directory
|
|
# Downloaded source data - never commit
|
|
data/
|
|
|
|
# Metadata tooling - entire folder
|
|
# Tooling for metadata enrichment - not part of main application
|
|
metadata_tooling/
|
|
|
|
# Internal notes (not for git)
|
|
temp/
|
|
docs/schema.yml
|
|
docs/datasets/*/schema.yml
|
|
|
|
# Agent-generated reports (not part of codebase)
|
|
.audit/
|
|
docs/AGENT-REPORTS/
|
|
|
|
# Git worktrees
|
|
.worktrees/
|
|
|
|
# Internal transcripts and meeting notes
|
|
docs/ZS_PADAK_*
|
|
.github/workflows/ci.yml
|
|
/auth/
|
|
/tmp/
|
|
|
|
# GCP service account keys — never commit
|
|
*-key.json
|
|
/agnes-deploy-*.json
|
|
|
|
# Vendor-loaded design mocks pulled into the worktree for plan-phase reference.
|
|
# These contain customer-specific tokens (hostnames, plugin names, brand strings)
|
|
# and cannot ship in OSS commit history per CLAUDE.md vendor-agnostic policy.
|
|
# Sanitize and replace with placeholders before committing any reference content.
|
|
docs/brainstorms/agnes-home-mock-*.html
|
|
|
|
# Brainstorms + plans authored against this repo. They typically reference
|
|
# customer-specific mocks, plugin names, or org context that has not been
|
|
# generalized for OSS. Keep them local; lift sanitized excerpts into
|
|
# docs/operator/ or docs/decisions/ when ready to ship.
|
|
docs/brainstorms/
|
|
docs/plans/
|