.claude/skills/env-reference/SKILL.md
Full environment variable reference for SAM. Use when adding, modifying, or documenting environment variables, configuring deployment, or working with Worker secrets.
npx skillsauth add raphaeltm/simple-agent-manager env-referenceInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Uses GH_* prefix because GitHub Actions reserves GITHUB_* for its own use.
| Type | Name | Required |
| -------- | -------------------------- | -------- |
| Variable | BASE_DOMAIN | Yes |
| Variable | RESOURCE_PREFIX | No (default: sam) |
| Variable | PULUMI_STATE_BUCKET | No (default: sam-pulumi-state) |
| Secret | CF_API_TOKEN | Yes |
| Secret | CF_ACCOUNT_ID | Yes |
| Secret | CF_ZONE_ID | Yes |
| Secret | R2_ACCESS_KEY_ID | Yes |
| Secret | R2_SECRET_ACCESS_KEY | Yes |
| Secret | PULUMI_CONFIG_PASSPHRASE | Yes |
| Secret | GH_CLIENT_ID | Yes |
| Secret | GH_CLIENT_SECRET | Yes |
| Secret | GH_APP_ID | Yes |
| Secret | GH_APP_PRIVATE_KEY | Yes |
| Secret | GH_APP_SLUG | Yes |
| Secret | ENCRYPTION_KEY | No (auto-generated) |
| Secret | JWT_PRIVATE_KEY | No (auto-generated) |
| Secret | JWT_PUBLIC_KEY | No (auto-generated) |
configure-secrets.sh)GitHub Secret -> Cloudflare Worker Secret
GH_CLIENT_ID -> GITHUB_CLIENT_ID
GH_CLIENT_SECRET -> GITHUB_CLIENT_SECRET
GH_APP_ID -> GITHUB_APP_ID
GH_APP_PRIVATE_KEY -> GITHUB_APP_PRIVATE_KEY
GH_APP_SLUG -> GITHUB_APP_SLUG
See apps/api/.env.example for the full list. Key variables:
WRANGLER_PORT — Local dev port (default: 8787)BASE_DOMAIN — Set automatically by sync scriptsMAX_NODES_PER_USER — Runtime node capMAX_AGENT_SESSIONS_PER_WORKSPACE — Runtime session capMAX_PROJECTS_PER_USER — Runtime project capMAX_TASKS_PER_PROJECT — Runtime task cap per projectMAX_TASK_DEPENDENCIES_PER_TASK — Runtime dependency-edge cap per taskTASK_LIST_DEFAULT_PAGE_SIZE — Default task/project list page sizeTASK_LIST_MAX_PAGE_SIZE — Maximum task/project list page sizeTASK_CALLBACK_TIMEOUT_MS — Timeout budget for delegated-task callback processingTASK_CALLBACK_RETRY_MAX_ATTEMPTS — Retry budget for delegated-task callback processingNODE_HEARTBEAT_STALE_SECONDS — Staleness threshold for node healthNODE_AGENT_READY_TIMEOUT_MS — Max wait for freshly provisioned node-agent healthNODE_AGENT_READY_POLL_INTERVAL_MS — Polling interval for fresh-node readiness checksHETZNER_API_TIMEOUT_MS — Timeout for Hetzner Cloud API calls (default: 30000)CF_API_TIMEOUT_MS — Timeout for Cloudflare DNS API calls (default: 30000)NODE_AGENT_REQUEST_TIMEOUT_MS — Timeout for Node Agent HTTP requests (default: 30000)WHISPER_MODEL_ID — Workers AI model for transcription (default: @cf/openai/whisper-large-v3-turbo)MAX_AUDIO_SIZE_BYTES — Maximum audio upload size (default: 10485760)MAX_AUDIO_DURATION_SECONDS — Maximum recording duration (default: 60)RATE_LIMIT_TRANSCRIBE — Rate limit for transcription requestsRATE_LIMIT_CLIENT_ERRORS — Rate limit per hour per IP (default: 200)MAX_CLIENT_ERROR_BATCH_SIZE — Max errors per request (default: 25)MAX_CLIENT_ERROR_BODY_BYTES — Max request body size (default: 65536)MAX_VM_AGENT_ERROR_BODY_BYTES — Max VM agent error request body (default: 32768)MAX_VM_AGENT_ERROR_BATCH_SIZE — Max VM agent errors per request (default: 10)CONTAINER_USER — Optional docker exec -u override; when unset, auto-detects effective devcontainer userGIT_EXEC_TIMEOUT — Timeout for git commands via docker exec (default: 30s)GIT_WORKTREE_TIMEOUT — Timeout for git worktree create/remove (default: 30s)WORKTREE_CACHE_TTL — Cache duration for parsed git worktree list results (default: 5s)MAX_WORKTREES_PER_WORKSPACE — Max worktrees allowed per workspace (default: 5)GIT_FILE_MAX_SIZE — Max file size for git/file endpoint (default: 1048576)FILE_LIST_TIMEOUT — Timeout for file listing commands (default: 10s)FILE_LIST_MAX_ENTRIES — Max entries per directory listing (default: 1000)FILE_FIND_TIMEOUT — Timeout for recursive file index (default: 15s)FILE_FIND_MAX_ENTRIES — Max entries returned by file index (default: 5000)ERROR_REPORT_FLUSH_INTERVAL — Background error flush interval (default: 30s)ERROR_REPORT_MAX_BATCH_SIZE — Immediate flush threshold (default: 10)ERROR_REPORT_MAX_QUEUE_SIZE — Max queued error entries (default: 100)ERROR_REPORT_HTTP_TIMEOUT — HTTP POST timeout for error reports (default: 10s)ACP_MESSAGE_BUFFER_SIZE — Max buffered messages per SessionHost for late-join replay (default: 5000)ACP_VIEWER_SEND_BUFFER — Per-viewer send channel buffer size (default: 256)ACP_PING_INTERVAL — WebSocket ping interval for stale connection detection (default: 30s)ACP_PONG_TIMEOUT — WebSocket pong deadline after ping (default: 10s)ACP_PROMPT_TIMEOUT — Max ACP prompt runtime for workspace sessions; 0 = no timeout (default: 0)ACP_TASK_PROMPT_TIMEOUT — Max ACP prompt runtime for task-driven sessions (default: 6h)ACP_PROMPT_CANCEL_GRACE_PERIOD — Grace wait after cancel before force-stop (default: 5s)ACP_IDLE_SUSPEND_TIMEOUT — Idle timeout before auto-suspending agent session (default: 30m)ACP_NOTIF_SERIALIZE_TIMEOUT — Max wait for previous session/update processing before delivering next (default: 5s)MAX_NODE_EVENTS — Max node-level events retained in memory (default: 500)MAX_WORKSPACE_EVENTS — Max workspace-level events retained in memory (default: 500)SYSINFO_DOCKER_TIMEOUT — Timeout for Docker CLI commands during system info collection (default: 10s)SYSINFO_VERSION_TIMEOUT — Timeout for version-check commands (default: 5s)SYSINFO_CACHE_TTL — Cache duration for system info results (default: 5s)development
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
tools
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
data-ai
Orchestrate multi-step workflows by decomposing into subtasks, dispatching them, and monitoring via foreground polling loops. Prevents session timeout kills during long-running orchestration. Use when coordinating multiple agents or running multi-phase work that takes more than a few minutes.
development
Marketing strategy and positioning. Builds positioning documents, messaging guides, content calendars, channel strategy, and gap analyses. Trigger when asked about positioning, messaging, marketing gaps, content planning, or channel strategy.