@elevasis/sdk 0.4.16 → 0.5.0

package/reference/framework/agent.mdx

@@ -18,90 +18,73 @@ The file is instruction-driven by design. Non-technical developers should never
 
 The generated `CLAUDE.md` contains these sections:
 
-- **Session Initialization** -- Instructs the agent to read `memory/index.md` silently at session start, drill into `memory/profile/skills.md` for adaptive behavior, suggest `/meta init` if memory does not exist, and notify the user if the template version is outdated.
-- **What This Is** -- Project orientation: what an Elevasis SDK project is and how it deploys to the platform.
-- **Project Structure** -- Which files contain resources, documentation, and configuration.
-- **CLI Reference** -- All `elevasis` commands with flags, including deploy, exec, env, and execution inspection.
-- **SDK Patterns** -- Working code examples for resource definitions, Zod schemas, multi-step workflows, platform tools, and execution context.
-- **Rules** -- Project-specific constraints. Starts empty; grows as the agent promotes recurring error patterns.
-- **Maintaining Memory** -- Hierarchical scaling pattern, pruning rules, and promotion criteria for the `memory/` directory.
-- **SDK Reference Documentation** -- Paths to bundled SDK reference docs in `node_modules/@elevasis/sdk/reference/`.
-- **Adaptive Guidance** -- Behavior rules for Beginner, Intermediate, and Advanced tiers based on skill levels read from `memory/profile/skills.md`.
+- **Session Initialization** -- Checks the `<!-- initialized: false -->` auto-init flag; if false, runs `/meta init` automatically. Otherwise reads `memory/profile/skills.md` for adaptive behavior, reads `memory/index.md` for project context, checks if the template version is current, and suggests `/tutorial` for TypeScript beginners.
+- **Identity** -- Project orientation: what an Elevasis SDK project is, the developer's role, and how to adapt to non-technical users.
+- **Navigation** -- A table mapping concepts to file paths with load conditions (when to load each file). Includes SDK reference docs, credential model, error history, `docs/project-map.mdx`, and `docs/priorities.mdx`.
+- **Rules** -- Points to auto-loaded rule files in `.claude/rules/`. SDK patterns load automatically; project-specific patterns live in `workspace-patterns.md`. Includes error handling protocol.
+- **Interaction Guidance** -- Per-dimension behavior rules derived from `memory/profile/skills.md`. Covers vocabulary, code completeness, explanation depth, and growth logging.
+- **Commands** -- Table of the 4 slash commands with one-line purpose descriptions.
+- **Skills** -- Auto-trigger conditions for the `creds` skill.
+- **Maintaining Memory** -- Hierarchical structure, pruning rules, and what belongs in memory vs. `docs/` vs. `.claude/rules/`.
 
 ### Session Initialization
 
 At the start of every session the agent runs these steps silently before responding:
 
-1. Read `.claude/memory/index.md` if it exists -- scan what project context has been recorded, including profile, error patterns, deployment state, and decisions. Drill into `memory/profile/skills.md` to personalize responses based on experience level.
-2. If `.claude/memory/` does not exist, suggest running `/meta init` to set up the project.
-3. Check the installed `@elevasis/sdk` template version against `templateVersion` in `elevasis.config.ts`. If the SDK has a newer version, notify the user and suggest running `/meta update`.
+0. Check the `<!-- initialized: ... -->` flag at the top of `CLAUDE.md`. If `false`, run the `/meta init` flow automatically. If `true`, proceed with steps below.
+1. Read `.claude/memory/profile/skills.md` -- adapt all responses to the user's assessed skill levels (see Interaction Guidance below).
+2. Read `.claude/memory/index.md` if it exists -- drill into relevant topic files as needed, balancing context relevance against token usage.
+3. Check the installed `@elevasis/sdk` template version against `templateVersion` in `elevasis.config.ts`. If the SDK has a newer version, notify the user and suggest running `/meta fix`.
+4. If `.claude/memory/` does not exist, suggest running `/meta init` to set up the project.
+5. If the user's TypeScript level is beginner (from skills.md) and `.claude/memory/tutorial-progress.md` does not exist, suggest `/tutorial`.
 
 ## Slash Commands
 
 Slash commands are short Markdown instruction files in `.claude/commands/`. When you type `/command-name` in a Claude Code session, the agent reads the corresponding file and follows its instructions.
 
-Ten commands and one skill are scaffolded by `elevasis init` and committed to version control so collaborators get the same experience:
+Four commands and one skill are scaffolded by `elevasis init` and committed to version control so collaborators get the same experience:
 
 | Command | File | Purpose |
 | --- | --- | --- |
-| `/meta` | `meta.md` | Project lifecycle management -- init, status, update, fix, deploy, health, develop |
-| `/docs` | `docs.md` | Documentation lifecycle -- create, checkpoint, cleanup, resume, verify |
-| `/database` | `database.md` | Database operations -- init, status, add, browse, schema, import |
-| `/resource` | `resource.md` | Scaffolds a new workflow or agent resource in `src/` |
-| `/templates` | `templates.md` | Workflow template discovery and scaffolding |
-| `/agent` | `agent.md` | Agent development (placeholder for future agent runtime) |
-| `/tutorial` | `tutorial.md` | Progressive learning path for new developers |
-| `/help` | `help.md` | Displays the full command tree and navigation map |
-| `/profile` | `profile.md` | Views and updates the developer profile in `memory/profile/` |
-| `/work` | `work.md` | In-progress task tracking -- save, resume, list |
+| `/meta` | `meta.md` | Project lifecycle -- init, status, fix, deploy, health |
+| `/docs` | `docs.md` | Documentation lifecycle -- create, review, verify |
+| `/work` | `work.md` | Task tracking -- create, save, resume, complete |
+| `/tutorial` | `tutorial.md` | Progressive 7-lesson learning path |
 
 The `/creds` skill (`.claude/skills/creds/SKILL.md`) is also scaffolded. It auto-triggers when the agent detects credential-related context and manages credential storage and retrieval.
 
 ### `/meta` Command
 
-The `/meta` command namespace manages the full project lifecycle. It has seven operations:
+The `/meta` command namespace manages the full project lifecycle. It has five operations:
 
-- **`/meta init`** -- First-run guided setup. Runs after `elevasis init` to install dependencies, configure `.env`, run the 6-question onboarding flow, seed `memory/profile/`, verify the project, and optionally do a first deploy.
-- **`/meta`** (no arguments) -- Project health status. Shows current template version, SDK version, profile summary, and a quick drift check.
-- **`/meta update`** -- Upgrade the SDK and merge template changes. Runs `pnpm update @elevasis/sdk`, then `elevasis update`, then intelligently merges flagged files and reports what changed.
-- **`/meta fix`** -- Repair drift without a version upgrade. Checks for missing commands, missing gitignore entries, missing CLAUDE.md sections, broken memory links, and broken doc cross-references.
-- **`/meta deploy`** -- Full 9-step deploy pipeline: validate, type-check, verify docs, commit, deploy, bump version, verify platform, update deployment state, and optionally push.
+- **`/meta init`** -- First-run guided setup. Runs after `elevasis init` to install dependencies, configure `.env`, run the competency assessment onboarding flow, seed `memory/profile/`, verify the project, and optionally do a first deploy.
+- **`/meta`** (no arguments) -- Project health status. Shows current template version, SDK version, profile summary, a quick drift check, and last deployment status.
+- **`/meta fix`** -- SDK upgrade check and drift repair. Step 0 offers to run `pnpm update @elevasis/sdk` and merge template changes. Steps 1-8 repair drift: missing managed files, gitignore entries, CLAUDE.md sections, memory structure, doc cross-references, settings, rules health, and project map freshness.
+- **`/meta deploy`** -- Full 9-step deploy pipeline: validate, type-check, verify docs, commit, deploy (auto-regenerates `docs/project-map.mdx`), verify platform, update deployment state, and optionally push.
 - **`/meta health`** -- Execution debugging and resource status; shows recent executions, analyzes failures, and checks environment connectivity.
-- **`/meta develop`** -- Development navigation hub that loads the resource map, SDK reference, and project state; replaces the old standalone `/workflow`, `/tools`, and `/examples` commands.
 
 ### `/docs` Command
 
-The `/docs` command manages the full documentation lifecycle. It has six operations:
+The `/docs` command manages documentation in `docs/`. It has four operations:
 
-- **`/docs`** (no arguments) -- Show current documentation status: pages in progress, recent changes, and any stale entries flagged for review.
-- **`/docs create`** -- Create a new documentation page. Prompts for title, description, and location, then scaffolds an MDX file with proper frontmatter.
-- **`/docs checkpoint`** -- Save current work progress for session resume. Creates or updates `docs/in-progress/<topic>.mdx` with current state, decisions made, remaining work, and blockers. Also updates `docs/priorities.mdx`.
-- **`/docs cleanup`** -- Move completed documents from `docs/in-progress/` to their final location. Reviews each in-progress doc, relocates complete ones, and rebuilds `docs/navigation.mdx`.
-- **`/docs resume`** -- Start-of-session review of in-progress docs, priorities, and recent deployment state. Offers to continue work on the highest-priority item.
-- **`/docs verify`** -- Cross-reference documentation with the codebase. Reads the specified doc (or all docs if no path provided) and reports discrepancies against actual resource IDs, schema fields, and platform tools.
+- **`/docs`** (no arguments) -- Review existing `docs/` files and suggest improvements. Identifies undocumented resources, missing descriptions, and structural gaps.
+- **`/docs create <page-name>`** -- Scaffold a new documentation page with correct frontmatter, populated from resource definitions in `src/`.
+- **`/docs review`** -- Review all `docs/` files for accuracy against actual resource definitions. Flags mismatches between documented schemas and code.
+- **`/docs verify [path]`** -- Cross-reference documentation with the codebase. Reads the specified doc (or all docs if no path provided) and reports discrepancies against actual resource IDs, schema fields, and platform tools.
 
-### `/database` Command
+### `/work` Command
 
-The `/database` command handles all database operations for projects that connect a Supabase project. It has six operations:
+The `/work` command manages in-progress task tracking across sessions. It uses `docs/in-progress/` for task documents with standardized frontmatter (`status: planned | in-progress | blocked | complete`). Operations:
 
-- **`/database init`** -- Connect a Supabase project. Prompts for project URL and anon key, writes connection config, and verifies connectivity.
-- **`/database`** (no arguments) -- Show database status: connection health, migration count, and a summary of tables.
-- **`/database add`** -- Create a migration script for a new table. Prompts for table name and columns, generates a typed migration, and updates schema documentation.
-- **`/database browse`** -- Query and display table contents in a readable format for quick inspection during development.
-- **`/database schema`** -- View or compare schema documentation against the live database. Highlights drift between documented schema and actual columns.
-- **`/database import`** -- Import CSV or JSON data into a table. Validates column mapping before writing.
+- **`/work`** (no arguments) -- List all task documents sorted by status and last updated.
+- **`/work create <description>`** -- Create a new task document with Objective, Plan, Progress, and Resume Context sections.
+- **`/work save`** -- Update the current task document with progress made this session. Useful before clearing context.
+- **`/work resume [<name>]`** -- Load a task document and continue from where it left off.
+- **`/work complete`** -- Mark the current task as complete and optionally move the doc to a `completed/` archive.
 
-### `/help` Command
+### `/tutorial` Command
 
-The `/help` command displays the complete command tree with one-line descriptions for every command and subcommand, plus navigation pointers to key project files (`docs/navigation.mdx`, `docs/priorities.mdx`, `memory/index.md`). It is the "I'm lost, what can I do?" entry point for command discovery and navigation.
-
-### `/profile` Command
-
-The profile command reads from and writes to `memory/profile/`. It has three modes:
-
-- **No arguments** -- Displays the current profile in readable format (organization, industry, experience levels, goals, known integrations, preferences) and asks if anything needs updating.
-- **`/profile update`** -- Walks through each profile section, shows current values, and updates only the fields the user wants to change. Writes changes to the appropriate `memory/profile/` file.
-- **`/profile level`** -- Assesses the user's current skill level based on project history (resources created, successful deploys, error handling patterns) and suggests updating `memory/profile/skills.md` if the assessment differs from the stored level.
+The `/tutorial` command runs a 7-lesson guided learning path adapted to the user's skill profile. Each lesson teaches a concept, guides the user to build something, and verifies it works. Lessons cover: project orientation, first custom workflow, schemas, platform tools, multi-step workflows, conditional routing, and going to production.
 
 ## Developer Profile
 
@@ -109,14 +92,11 @@ The developer profile is stored in `.claude/memory/profile/` as a set of markdow
 
 ### Onboarding Flow
 
-Profile data is created during `/meta init`. The command runs a 6-question onboarding conversation and writes the responses to `memory/profile/`:
+Profile data is created during `/meta init`. The command runs a competency assessment (5-7 questions with conditional skipping) and writes the responses to `memory/profile/`:
 
-1. What kind of business or team is this for? (industry, size)
-2. What are the main goals for this project? (automation goals)
-3. Which external tools or services will workflows integrate with? (integrations)
-4. How would you describe your experience with TypeScript? (beginner / intermediate / advanced)
-5. How familiar are you with AI automation and workflow concepts? (new / some experience / experienced)
-6. Do you prefer detailed explanations or concise responses? (detailed / concise)
+- **Identity & Goals (3 questions):** What the business does, what to automate, which tools are already in use.
+- **Competency (2-3 conditional questions):** Programming background, TypeScript experience (only asked if the user has written scripts or more), automation tool familiarity.
+- **Communication (1 question):** Step-by-step explanations vs. concise answers.
 
 ### Profile Structure
 
@@ -140,39 +120,33 @@ The agent updates `memory/profile/` files when it observes:
 
 The agent does not prompt for confirmation on minor updates. Major changes (level upgrades) are surfaced to the user before writing.
 
-## Adaptive Guidance
-
-The `CLAUDE.md` Adaptive Guidance section translates the skill levels from `memory/profile/skills.md` into concrete behavior rules. The agent checks the TypeScript level and automation level and applies the matching tier.
-
-### Beginner
-
-Applies when TypeScript level is `beginner` or automation level is `new`:
+## Rules System
 
-- Always show complete, working code -- never fragments
-- Explain every new concept the first time it appears (TypeScript types, Zod schemas, async/await)
-- After creating a resource, walk through deployment step by step
-- Proactively suggest next steps ("Now let's deploy this" or "Want to test it?")
-- When errors occur, explain both the fix and why it happened
-- Use `/help` to navigate to the relevant SDK reference before suggesting platform tools
+Six rule files are scaffolded in `.claude/rules/`. Rule files are auto-injected by Claude Code when their path patterns match the current file being edited -- no manual loading needed.
 
-### Intermediate
+| File | Type | When Injected | What It Covers |
+| --- | --- | --- | --- |
+| `sdk-patterns.md` | MANAGED | Any file in `src/` | SDK imports, source structure, runtime, typed adapter patterns |
+| `docs-authoring.md` | MANAGED | Any `.mdx` file in `docs/` | MDX escaping, frontmatter requirements, doc structure |
+| `memory-conventions.md` | MANAGED | Any file in `.claude/memory/` | What belongs in memory, structure, pruning |
+| `project-map.md` | MANAGED | `docs/project-map.mdx` | Auto-generated map conventions, do not edit manually |
+| `task-tracking.md` | MANAGED | Any file in `docs/in-progress/` | `/work` command, task doc format, status values |
+| `workspace-patterns.md` | INIT_ONLY | Any file in the project | Project-specific patterns (starts empty, grows via error promotion) |
 
-Applies when TypeScript level is `intermediate` and automation level is `some-experience`:
+MANAGED rules are updated by `elevasis update` when the SDK ships a new version. `workspace-patterns.md` is INIT_ONLY -- it belongs to the project and is never overwritten. When an error recurs 3+ times, the agent promotes a fix into this file so future sessions learn from past mistakes.
 
-- Show code with brief inline comments for non-obvious parts
-- Explain new concepts but not basics (Zod, async/await, TypeScript types)
-- Suggest deployment after resource creation but do not walk through it
-- When errors occur, provide the fix with a one-line explanation
+## Interaction Guidance
 
-### Advanced
+The `CLAUDE.md` Interaction Guidance section translates skill dimensions from `memory/profile/skills.md` into concrete behavior rules. Rather than fixed tiers, the agent adapts per dimension:
 
-Applies when TypeScript level is `advanced` and automation level is `experienced`:
+- **Match vocabulary to level.** Avoid jargon for beginners; be precise for experts. Define technical terms in parentheses the first time they appear.
+- **Show complete code for lower-programming users.** Users below intermediate programming level get full working files, never fragments they can't place.
+- **Explain "why" before "how" for users new to automation.** Users comfortable with code get SDK-specific pattern focus instead.
+- **Leverage domain expertise.** If the user knows sales but not code, ask for business process descriptions and translate.
+- **Log observed growth.** When the agent observes the user doing something they previously needed help with, add an entry to `skills.md` Growth Log.
 
-- Concise code, minimal explanation
-- Focus on edge cases and performance
-- Trust the user to deploy and test independently
-- When errors occur, provide the fix
+For detailed per-dimension adaptation rules, read `reference/developer/interaction-guidance.mdx`.
 
 ---
 
-**Last Updated:** 2026-03-02
+**Last Updated:** 2026-03-03

package/reference/framework/index.mdx

@@ -14,18 +14,21 @@ Running `elevasis init my-project` produces the following agent infrastructure a
 
 ```
 .claude/
-├── CLAUDE.md                   # Project instructions for Claude Code
 ├── settings.json               # autoCompact: false
-└── commands/
-    ├── docs.md                 # Documentation assistant
-    ├── resource.md             # Resource scaffolding assistant
-    ├── profile.md              # View and update developer profile
-    ├── meta.md                 # Project lifecycle (init, status, update, fix)
-    ├── help.md                 # Contextual help and concept explanations
-    ├── database.md             # Database schema and query assistant
-    ├── agent.md                # Agent scaffolding and configuration
-    ├── templates.md            # Template browsing and generation
-    └── tutorial.md             # Progressive 7-lesson learning path
+├── commands/
+│   ├── docs.md                 # Documentation lifecycle
+│   ├── meta.md                 # Project lifecycle (init, fix, deploy, health)
+│   ├── tutorial.md             # Progressive 7-lesson learning path
+│   └── work.md                 # Task tracking
+├── skills/
+│   └── creds/SKILL.md          # Credential management (auto-triggers)
+└── rules/
+    ├── sdk-patterns.md         # SDK patterns (auto-loaded for src/ files)
+    ├── docs-authoring.md       # MDX conventions (auto-loaded for docs/ files)
+    ├── memory-conventions.md   # Memory conventions (auto-loaded)
+    ├── project-map.md          # Project map conventions (auto-loaded)
+    ├── task-tracking.md        # Task tracking conventions (auto-loaded)
+    └── workspace-patterns.md   # Project-specific patterns (grows over time)
 ```
 
 The `memory/` directory is gitignored -- it is personal to each developer and not shared with collaborators. Everything else in `.claude/` is committed.
@@ -48,7 +51,7 @@ The agent reads `memory/index.md` at session start and drills into `memory/profi
 
 The `CLAUDE.md` file drives all agent behavior. It contains the session initialization instructions, adaptive guidance tiers, memory maintenance rules, and slash command definitions. No hooks, no code enforcement -- everything is instruction-driven so non-technical users never need to configure anything.
 
-The `/profile` slash command lets developers view and update their profile in `memory/profile/`. The `/meta` command manages the project lifecycle: `/meta init` for guided setup, `/meta update` for SDK upgrades, `/meta fix` for drift repair. Other commands give the agent structured entry points for common tasks: `/meta deploy` for deployments, `/resource` for scaffolding new resources, `/meta health` for debugging executions.
+The `/meta` command manages the project lifecycle: `/meta init` for guided setup, `/meta fix` for SDK upgrades and drift repair, `/meta deploy` for deployments, `/meta health` for debugging executions. `/docs` handles documentation maintenance, `/work` tracks tasks across sessions, and `/tutorial` guides new developers through a 7-lesson learning path. A `creds` skill auto-triggers when credential setup is needed.
 
 See [Agent System](agent.mdx) for CLAUDE.md sections, slash command reference, developer profile, and adaptive guidance tiers.
 
@@ -88,8 +91,8 @@ See [Agent System](agent.mdx) for the full assessment question set, dimensional
 
 ### Skills Auto-Update
 
-The Growth Log in `memory/profile/skills.md` keeps approximately 20 recent entries. The agent adds an entry whenever it observes the user performing something they previously needed help with. When a consistent pattern of growth is observed -- typically after several independent successes -- the agent promotes the observation to a level change in the relevant dimension. The `/profile` command lets developers view their current levels and trigger a fresh assessment at any time.
+The Growth Log in `memory/profile/skills.md` keeps approximately 20 recent entries. The agent adds an entry whenever it observes the user performing something they previously needed help with. When a consistent pattern of growth is observed -- typically after several independent successes -- the agent promotes the observation to a level change in the relevant dimension.
 
 ---
 
-**Last Updated:** 2026-02-27
+**Last Updated:** 2026-03-03

package/reference/framework/project-structure.mdx

@@ -54,7 +54,7 @@ Project-level configuration. The scaffolded file includes `templateVersion`, whi
 import type { ElevasConfig } from '@elevasis/sdk'
 
 export default {
-  templateVersion: 5,
+  templateVersion: 14,
   // defaultStatus: 'dev',     // Default status for new resources ('dev' | 'production')
   // dev: { port: 5170 },      // Local API port (internal development only)
 } satisfies ElevasConfig
@@ -82,11 +82,11 @@ order: 0
 
 Add more pages by creating additional `.mdx` files in `docs/`. Nested directories create sections: `docs/guides/setup.mdx` becomes a `guides/setup` page under your deployment's documentation.
 
-### `docs/navigation.mdx`
+### `docs/project-map.mdx`
 
-Auto-generated on the first `/meta deploy` and regenerated after each subsequent deploy. Contains a table of all deployed resources (resourceId, name, tools used, schema fields) and an index of all documentation pages. The agent reads this file during navigation to understand the current state of your workspace. You can also read it for a quick project overview.
+Auto-generated by `elevasis deploy` on every deploy and by `/meta fix` step 8. Contains a full project snapshot: organization, SDK version, template version, last deploy date, source domains, resource tables (workflows and agents), documentation index, SDK reference summary, commands/rules/skills, memory system listing, and configuration state. The agent reads this file at session start for project orientation.
 
-This file is MANAGED -- `elevasis update` ensures it exists but does not overwrite it. The actual content is generated by `/meta deploy`.
+This file is fully auto-generated -- do not edit manually. Changes are overwritten on the next deploy.
 
 ### `docs/priorities.mdx`
 
@@ -113,9 +113,9 @@ Only `src/` and `docs/` are scaffolded by `elevasis init`. The following directo
 | `src/shared/` | `elevasis init` (default) | Always -- cross-domain shared utilities (starts empty) |
 | `docs/` | `elevasis init` (default) | Always |
 | `docs/in-progress/` | Agent (on first `/docs checkpoint`) | When you save work-in-progress across sessions |
-| `docs/navigation.mdx` | Agent (on first `/meta deploy`) | Auto-generated and updated on each deploy |
+| `docs/project-map.mdx` | `elevasis deploy` | Auto-generated on every deploy |
 | `docs/priorities.mdx` | Agent (on first goal discussion) | When you discuss project goals or priorities |
-| `data/` | `/database init` command | When you connect a database |
+| `data/` | Agent (on demand) | When you connect a database |
 | `scripts/` | Agent (on demand) | When you need local scripts not deployed to the platform |
 | `src/lib/` | Agent (on demand) | When shared code exists between two or more workflows |
 
@@ -127,7 +127,7 @@ Legacy shared code directory. In v5+ projects, use `src/shared/` for cross-domai
 
 ### `data/`
 
-Created by `/database init`. Contains `schema.ts` which documents your database schema as TypeScript types. The agent reads this file to understand your data model when writing workflow steps that call the Supabase tool. Not deployed -- it is local documentation for the agent.
+Created by the agent when you connect a database. Contains `schema.ts` which documents your database schema as TypeScript types. The agent reads this file to understand your data model when writing workflow steps that call the Supabase tool. Not deployed -- it is local documentation for the agent.
 
 ### `scripts/`
 
@@ -229,48 +229,40 @@ This directory is gitignored -- it is personal to you and not shared with collab
 
 ## Slash Commands
 
-The `.claude/commands/` directory contains nine commands covering the core development loop. Invoke them in Claude Code with `/docs`, `/resource`, `/profile`, `/meta`, `/help`, `/database`, `/agent`, `/templates`, and `/tutorial`.
+The `.claude/commands/` directory contains four commands covering the core development loop. Invoke them in Claude Code with `/meta`, `/docs`, `/work`, and `/tutorial`.
 
-### `/docs` -- Documentation Lifecycle
-
-Manages documentation creation and maintenance for `docs/`. Six operations:
-
-- **No arguments** -- Show current documentation status: pages in progress, recent changes, and stale entries flagged for review
-- **`create <page-name>`** -- Scaffold a new documentation page with correct frontmatter, populated from your resource definitions
-- **`checkpoint`** -- Save current work progress for session resume. Creates or updates `docs/in-progress/` with current state, decisions made, remaining work, and blockers
-- **`cleanup`** -- Move completed documents from `docs/in-progress/` to their final location. Rebuilds `docs/navigation.mdx`
-- **`resume`** -- Start-of-session review of in-progress docs, priorities, and recent deployment state
-- **`verify`** -- Cross-reference documentation with the codebase. Reports discrepancies against actual resource IDs, schema fields, and platform tools
+### `/meta` -- Project Lifecycle
 
-### `/resource` -- Resource Scaffolding
+Manages the full lifecycle of your workspace. Five operations:
 
-Scaffolds new workflow definitions with proper types, Zod schemas, and step structure. Three operations:
+- **`init`** -- First-run guided setup: installs dependencies, configures `.env`, runs competency assessment to build your developer profile in `.claude/memory/`, and optionally deploys the starter workflow. Triggered automatically by the `<!-- initialized: false -->` flag in CLAUDE.md.
+- **No arguments** -- Project health status: shows template version, SDK version, profile summary, last deployment status, and a quick drift check for missing files.
+- **`fix`** -- SDK upgrade check and full drift repair. Step 0 offers to run `pnpm update @elevasis/sdk` and merge template changes. Steps 1-8 repair drift: missing managed files, gitignore entries, CLAUDE.md sections, memory structure, doc cross-references, settings, rules health, and project map freshness.
+- **`deploy`** -- Full 9-step deploy pipeline: validate, type-check, verify docs, commit, deploy (auto-regenerates `docs/project-map.mdx`), verify platform, update deployment state, and optionally push.
+- **`health`** -- Execution debugging and resource status; shows recent executions, analyzes failures, and checks environment connectivity.
 
-- **`workflow <name>`** -- Single-step workflow with Zod input/output schemas, config object, contract, step handler, and addition to the `OrganizationResources` export
-- **`multi-step <name>`** -- Multi-step workflow with `StepType.LINEAR` or `StepType.CONDITIONAL`, connected steps, and per-step schemas
-- **`tool-step <name>`** -- Step that calls a platform tool via `platform.call()` with `PlatformToolError` error handling and a credential note
+### `/docs` -- Documentation Lifecycle
 
-### `/meta` -- Project Lifecycle
+Manages documentation creation and maintenance for `docs/`. Four operations:
 
-Manages the full lifecycle of your workspace. Seven operations:
+- **No arguments** -- Review existing `docs/` files and suggest improvements. Identifies undocumented resources, missing descriptions, and structural gaps.
+- **`create <page-name>`** -- Scaffold a new documentation page with correct frontmatter, populated from your resource definitions.
+- **`review`** -- Review all `docs/` files for accuracy against actual resource definitions. Flags mismatches between documented schemas and code.
+- **`verify [path]`** -- Cross-reference documentation with the codebase. Reports discrepancies against actual resource IDs, schema fields, and platform tools.
 
-- **`init`** -- First-run guided setup: installs dependencies, configures `.env`, runs onboarding to build your developer profile in `.claude/memory/`, and optionally deploys the starter workflow. Run this once after `elevasis init`
-- **No arguments** -- Project health status: shows template version, SDK version, profile summary, and a quick drift check for missing files
-- **`update`** -- Full upgrade flow: runs `pnpm update @elevasis/sdk`, then `elevasis update` to add missing files, then reviews and merges any flagged template changes with your customizations intact
-- **`fix`** -- Repairs drift without a version upgrade: restores missing command files, appends missing `.gitignore` entries, verifies CLAUDE.md sections, and checks memory structure consistency
-- **`deploy`** -- Full 9-step deploy pipeline: validate, type-check, verify docs, commit, deploy, bump version, verify platform, update deployment state, and optionally push
-- **`health`** -- Execution debugging and resource status; shows recent executions, analyzes failures, and checks environment connectivity
-- **`develop`** -- Development navigation hub that loads the resource map, SDK reference, and project state
+### `/work` -- Task Tracking
 
-### `/templates` -- Workflow Templates
+Manages in-progress task tracking across sessions using `docs/in-progress/` task documents. Five operations:
 
-Applies pre-built workflow templates to your workspace. Three operations:
+- **No arguments** -- List all task documents sorted by status.
+- **`create <description>`** -- Create a new task document with Objective, Plan, Progress, and Resume Context sections.
+- **`save`** -- Update the current task document with progress made this session.
+- **`resume [<name>]`** -- Load a task document and continue from where it left off.
+- **`complete`** -- Mark the current task as complete.
 
-- **No arguments** -- List available template categories (Data Collection, Data Processing, Communication, CRM, Documents, AI, Scheduling)
-- **`<category>`** -- Show templates in a category with descriptions
-- **`apply <name>`** -- Generate a workflow from a template: writes to the appropriate domain directory, wires into the domain barrel, prompts for credential setup if needed, and runs `elevasis check` to validate
+### `/tutorial` -- Progressive Learning
 
-Templates are documentation files bundled with the SDK, not rigid copy-paste code. The agent reads the template and generates a workflow adapted to your existing schemas, credentials, and naming conventions.
+A 7-lesson guided learning path adapted to the user's skill profile. Lessons cover project orientation, writing workflows, schemas, platform tools, multi-step workflows, conditional routing, and production deployment.
 
 ---
 
@@ -278,19 +270,22 @@ Templates are documentation files bundled with the SDK, not rigid copy-paste cod
 
 Not all scaffolded files participate in template updates. Files fall into two categories:
 
-**SCAFFOLD_FILES total: 27**
+**SCAFFOLD_FILES total: 29**
 
-**INIT_ONLY** (14 files) -- Written once during `elevasis init`, never updated by `elevasis update`:
+**INIT_ONLY** (15 files) -- Written once during `elevasis init`, never updated by `elevasis update`:
 - `package.json`, `pnpm-workspace.yaml`, `tsconfig.json`
 - `.env`, `.env.example`, `.npmrc`
 - `src/index.ts`, `src/operations/platform-status.ts`, `src/operations/index.ts`, `src/example/echo.ts`, `src/example/index.ts`, `src/shared/.gitkeep`
 - `docs/index.mdx`, `docs/in-progress/.gitkeep`
+- `.claude/rules/workspace-patterns.md`
 
-**MANAGED** (13 files) -- Written during `elevasis init` and checked/updatable by `elevasis update`:
-- `elevasis.config.ts`, `.gitignore`, `CLAUDE.md`, `docs/navigation.mdx`
-- All nine command files: `docs.md`, `resource.md`, `profile.md`, `meta.md`, `help.md`, `database.md`, `agent.md`, `templates.md`, `tutorial.md`
+**MANAGED** (14 files) -- Written during `elevasis init` and checked/updatable by `elevasis update`:
+- `elevasis.config.ts`, `.gitignore`, `CLAUDE.md`, `.claude/settings.json`
+- Four command files: `.claude/commands/docs.md`, `.claude/commands/meta.md`, `.claude/commands/tutorial.md`, `.claude/commands/work.md`
+- One skill: `.claude/skills/creds/SKILL.md`
+- Five rule files: `.claude/rules/sdk-patterns.md`, `.claude/rules/docs-authoring.md`, `.claude/rules/memory-conventions.md`, `.claude/rules/project-map.md`, `.claude/rules/task-tracking.md`
 
-Run `elevasis update` after installing a new SDK version to bring managed files up to date. The command adds missing files directly and flags files that differ from the new template for agent-assisted review via `/meta update`.
+Run `elevasis update` after installing a new SDK version to bring managed files up to date. The command adds missing files directly and flags files that differ from the new template for agent-assisted review via `/meta fix`.
 
 ---
 
@@ -301,7 +296,7 @@ Run `elevasis update` after installing a new SDK version to bring managed files
 | `src/index.ts` | Adding or removing resources (the `/resource` command does this automatically) |
 | `src/<domain>/*.ts` | Writing and modifying workflow logic (organized by business domain) |
 | `docs/index.mdx` | Updating project documentation |
-| `docs/navigation.mdx` | Never -- auto-generated by `/meta deploy` |
+| `docs/project-map.mdx` | Never -- auto-generated by `elevasis deploy` |
 | `docs/priorities.mdx` | When goals or priorities change |
 | `elevasis.config.ts` | Changing project-level settings |
 | `.env` | Adding environment variables |
@@ -310,4 +305,4 @@ Run `elevasis update` after installing a new SDK version to bring managed files
 
 ---
 
-**Last Updated:** 2026-02-27
+**Last Updated:** 2026-03-03

package/reference/getting-started/index.mdx

@@ -29,23 +29,27 @@ elevasis init my-project
 cd my-project
 ```
 
-The command scaffolds 27 files covering configuration, source, documentation, and Claude Code integration:
+The command scaffolds 29 files covering configuration, source, documentation, and Claude Code integration:
 
 ```
 my-project/
 ├── CLAUDE.md                       # Project instructions for Claude Code
 ├── .claude/
 │   ├── settings.json               # autoCompact: false
-│   └── commands/
-│       ├── docs.md                 # Documentation lifecycle
-│       ├── resource.md             # Resource scaffolding
-│       ├── meta.md                 # Project lifecycle (init, deploy, health, develop)
-│       ├── help.md                 # Command tree and navigation
-│       ├── database.md             # Database setup and management
-│       ├── agent.md                # Agent development
-│       ├── templates.md            # Workflow templates
-│       ├── tutorial.md             # Progressive learning
-│       └── profile.md              # View and update user profile
+│   ├── commands/
+│   │   ├── docs.md                 # Documentation lifecycle
+│   │   ├── meta.md                 # Project lifecycle (init, fix, deploy, health)
+│   │   ├── tutorial.md             # Progressive learning
+│   │   └── work.md                 # Task tracking
+│   ├── skills/
+│   │   └── creds/SKILL.md          # Credential management (auto-triggers)
+│   └── rules/
+│       ├── sdk-patterns.md         # SDK imports, structure, runtime (auto-loaded)
+│       ├── docs-authoring.md       # MDX conventions (auto-loaded)
+│       ├── memory-conventions.md   # Memory system conventions (auto-loaded)
+│       ├── project-map.md          # Project map conventions (auto-loaded)
+│       ├── task-tracking.md        # Task tracking conventions (auto-loaded)
+│       └── workspace-patterns.md   # Project-specific patterns (you add these)
 ├── src/
 │   ├── index.ts                    # Registry entry point (aggregates domain barrels)
 │   ├── operations/
@@ -76,7 +80,7 @@ The scaffolded `elevasis.config.ts` includes a `templateVersion` field that trac
 import type { ElevasConfig } from '@elevasis/sdk'
 
 export default {
-  templateVersion: 5,
+  templateVersion: 14,
 } satisfies ElevasConfig
 ```
 

package/reference/index.mdx

@@ -53,7 +53,7 @@ export const resources: OrganizationResources = {
 ## What You Can Build
 
 - **Workflows** -- Step-based automation with typed inputs and outputs. Steps can be linear, conditional, or branching. Each step is a plain async function. Workflows are the primary resource type and are fully supported.
-- **Agents** -- Autonomous AI resources with access to platform tools. Agent definitions are accepted by the SDK and appear in the registry, but autonomous agent execution (multi-turn tool use loops) is deferred -- see Known Limitations below.
+- **Agents** -- Autonomous AI resources with access to platform tools. Agents run in the worker runtime with full LLM access and platform tool support. Use `--async` when executing agents to avoid HTTP timeout limits on long-running runs.
 
 ## Platform Tools
 
@@ -76,8 +76,8 @@ See [Platform Tools](platform-tools/index.mdx) for the full catalog.
 
 ## Known Limitations
 
-- **Agent execution is deferred** -- The worker runtime returns a failed status for agent resources. LLM calls are available via `platform.call`, but autonomous multi-turn agent loops are not yet supported.
 - **No streaming logs** -- Execution logs are returned in the response body after completion. Real-time log streaming is not available.
+- **Agent HTTP timeouts** -- Use `elevasis exec --async` for agent executions. Agents can run for minutes; the synchronous endpoint will time out for long-running runs. The `--async` flag returns an execution ID immediately and polls for the result.
 
 ## Documentation