remove update job

Author: nhorton

.deepwork/jobs/deepwork_jobs/steps/fix_jobs.md

@@ -203,6 +203,6 @@ For each job in `.deepwork/jobs/`, check:
 
 ## Important Notes
 
-1. **Don't modify standard jobs directly** - If `deepwork_jobs` is out of date, run `deepwork install --platform claude` to get the latest version
+1. **Don't modify standard jobs directly** - If `deepwork_jobs` is out of date, run `deepwork install` to get the latest version
 2. **Preserve custom logic** - When migrating hooks, preserve the prompt content
 3. **Test after changes** - Validate YAML syntax after each job fix to catch errors early

.deepwork/jobs/update/job.yml

@@ -18,7 +18,7 @@ When creating or modifying jobs in this repository, you MUST understand which ty
 **Editing rules**:
 - Source of truth is ALWAYS in `src/deepwork/standard_jobs/`
 - NEVER edit the installed copies in `.deepwork/jobs/` directly
-- After editing, run `deepwork install --platform claude` to sync
+- After editing, run `deepwork install` to sync
 
 ### 2. Library Jobs (`library/jobs/`)
 

.deepwork/jobs/update/steps/job.md

@@ -7,47 +7,32 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+
+### Changed
+
+### Fixed
+
+## [0.7.0] - 2026-02-05
+
 ### Added
 - **MCP Server Architecture** - New Model Context Protocol server for checkpoint-based workflow execution
-  - `deepwork serve` command starts the MCP server with stdio or SSE transport
-  - Three MCP tools: `get_workflows`, `start_workflow`, `finished_step`
-  - Session state persisted to `.deepwork/tmp/session_[id].json` for resumability
-  - Quality gate evaluates step outputs against quality criteria using Claude Code subprocess
-  - Nested workflow support with stack-based execution model
-  - `abort_workflow` tool for canceling workflows and returning to parent
-  - Comprehensive Pydantic schemas for all tool inputs/outputs in `src/deepwork/mcp/schemas.py`
-  - Documentation in `doc/mcp_interface.md` and `doc/architecture.md` Part 4
-- New `deepwork_jobs` steps for MCP-based workflow management
-  - `iterate` - Quick iteration on existing jobs without full define/implement cycle
-  - `errata` - Document known issues and quirks discovered during job execution
-  - `test` - Run manual tests to validate job behavior
-  - `fix_jobs` - Repair malformed job.yml files
-  - `fix_settings` - Repair platform settings files
+- Improved `deepwork_jobs` steps for workflow management
 - JSON Schema for job.yml validation (`src/deepwork/schemas/job.schema.json`)
 - Reference documentation for calling Claude in print mode (`doc/reference/calling_claude_in_print_mode.md`)
 - Migrated to uv2nix for reproducible Python builds in flake.nix
 
 ### Changed
 - **BREAKING**: Simplified skill generation to single `/deepwork` entry point skill
-  - The generator now produces only `skill-deepwork.md.jinja` that directs agents to MCP tools
-  - Removed individual step skill generation (`skill-job-step.md.jinja`, `skill-job-meta.md.jinja`)
-  - Workflow orchestration moved from skill files to MCP server
 - **BREAKING**: Workflow execution now happens through MCP tool calls instead of slash commands
-  - Agents call `start_workflow` → execute step → `finished_step` → repeat
-  - Quality gates enforce output requirements before proceeding
 - Streamlined `deepwork_jobs.define` and `deepwork_jobs.implement` for MCP workflow
 - Updated `deepwork_jobs.learn` with simplified instructions
 - Simplified adapter templates - removed complex skill templates
 - MCP server registered in `.claude/settings.json` during install
 
 ### Removed
-- **BREAKING**: Entire rules system removed
-  - Removed `rules_parser.py`, `rules_queue.py`, `pattern_matcher.py`, `rules_check.py`
-  - Removed `.deepwork/rules/` directory and all rule definition files
-  - Removed `command_executor.py` for command action execution
-  - Removed `deepwork_rules` standard job and `/deepwork_rules.define` skill
-  - Removed rules-related hooks (`user_prompt_submit.sh`, `capture_prompt_work_tree.sh`)
-  - Removed rules documentation (`doc/rules_syntax.md`, `doc/rules_system_design.md`)
+- **BREAKING**: Rules system removed
+- **BREAKING**: Removed per-step skill generation templates and logic
 - Removed per-step skill generation templates and logic
 - Removed `commit` job from library (was example job)
 - Removed `manual_tests/` directory and `manual_tests` job
@@ -56,7 +41,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Removed Gemini per-step skill templates (`.gemini/skills/` now only has entry point)
 
 ### Migration Guide
-- Run `deepwork install --platform claude` to get the new MCP server configuration
+- Run `deepwork install` to get the new MCP server configuration
 - Workflows are now executed via `/deepwork` which uses MCP tools internally
 - Rules system is completely removed - consider implementing validation logic in quality criteria instead
 - Existing job definitions still work but are executed through MCP checkpoints

AGENTS.md

@@ -259,7 +259,7 @@ Since you installed DeepWork in editable mode, the `deepwork` command uses your
 
 ```bash
 # Run the install command
-deepwork install --platform claude
+deepwork install
 
 # Verify installation
 ls -la .deepwork/
@@ -273,7 +273,7 @@ Any changes you make to the DeepWork source code will be immediately reflected:
 ```bash
 # Make changes in ~/deepwork/src/deepwork/...
 # Then test in your test project
-deepwork install --platform claude
+deepwork install
 
 # Or test the CLI directly
 deepwork --help
@@ -306,7 +306,7 @@ nix run github:Unsupervisedcom/deepwork/feature-branch-name -- --help
 nix develop github:Unsupervisedcom/deepwork/feature-branch-name
 
 # Run a specific command from a feature branch
-nix develop github:Unsupervisedcom/deepwork/feature-branch-name --command deepwork install --platform claude
+nix develop github:Unsupervisedcom/deepwork/feature-branch-name --command deepwork install
 
 # Test against a specific commit
 nix run github:Unsupervisedcom/deepwork/abc1234 -- --version
@@ -321,7 +321,7 @@ For example, to test a branch named `feat/new-parser`:
 
 ```bash
 # Quick test of the CLI
-nix run github:Unsupervisedcom/deepwork/feat/new-parser -- install --platform claude --dry-run
+nix run github:Unsupervisedcom/deepwork/feat/new-parser -- install --dry-run
 
 # Or enter a full development shell to run tests and run a specific test
 nix develop github:Unsupervisedcom/deepwork/feat/new-parser --command pytest tests/unit/core/test_parser.py -v
@@ -466,7 +466,7 @@ mypy src/
 ```bash
 # Create or use a test project
 cd ~/test-project/
-deepwork install --platform claude
+deepwork install
 
 # Verify your changes work as expected
 ```

CHANGELOG.md

@@ -83,8 +83,7 @@ When running in Claude Code on the web (not local installations), the `deepwork`
 pip install -e .
 
 # Then run commands normally
-deepwork install --platform claude
-deepwork sync
+deepwork install
 ```
 
 **Note**: In web environments, you may also need to install dependencies like `jsonschema`, `pyyaml`, `gitpython`, `jinja2`, and `click` if they're not already available.
@@ -211,7 +210,7 @@ Instead, follow this workflow:
    - `steps/*.md` - Step instruction files
    - `hooks/*` - Any hook scripts
 
-2. **Run `deepwork install --platform claude`** to sync changes to `.deepwork/jobs/` and `.claude/skills/`
+2. **Run `deepwork install`** to sync changes to `.deepwork/jobs/` and `.claude/skills/`
 
 3. **Verify** the changes propagated correctly to all locations
 

CONTRIBUTING.md

@@ -91,7 +91,7 @@ deepwork --help
 nix run github:Unsupervisedcom/deepwork -- --help
 
 # Run a specific command
-nix run github:Unsupervisedcom/deepwork -- install --platform claude
+nix run github:Unsupervisedcom/deepwork -- install
 ```
 
 ### Building the Package

claude.md

@@ -203,6 +203,5 @@ For each job in `.deepwork/jobs/`, check:
 
 ## Important Notes
 
-1. **Don't modify standard jobs directly** - If `deepwork_jobs` is out of date, run `deepwork install --platform claude` to get the latest version
-2. **Preserve custom logic** - When migrating hooks, preserve the prompt content
-3. **Test after changes** - Validate YAML syntax after each job fix to catch errors early
+1. **Preserve custom logic** - When migrating hooks, preserve the prompt content
+2. **Test after changes** - Validate YAML syntax after each job fix to catch errors early