docs(post-mortem): Apply session start checklists and edit tool warnings

From gui_decoupling_controller track post-mortem:

workflow.md:
- Add mandatory session start checklist (6 items)
- Add code style section with 1-space indentation enforcement
- Add native edit tool warning with MCP alternatives

AGENTS.md:
- Add critical native edit tool warning
- Document MCP tool alternatives for file editing

tier1-orchestrator.md:
- Add session start checklist

tier2-tech-lead.md:
- Add session start checklist
- Add tool restrictions section (allowed vs forbidden)
- Add explicit delegation pattern

tier3-worker.md:
- Add task start checklist

tier4-qa.md:
- Add analysis start checklist

.opencode/agents/tier1-orchestrator.md

@@ -40,6 +40,18 @@ You MUST use Manual Slop's MCP tools. Native OpenCode tools are unreliable.
 |-------------|----------|
 | `bash` | `manual-slop_run_powershell` |
 
+## Session Start Checklist (MANDATORY)
+
+Before ANY other action:
+1. [ ] Read `conductor/workflow.md`
+2. [ ] Read `conductor/tech-stack.md`
+3. [ ] Read `conductor/product.md`, `conductor/product-guidelines.md`
+4. [ ] Read relevant `docs/guide_*.md` for current task domain
+5. [ ] Check `TASKS.md` for active tracks
+6. [ ] Announce: "Context loaded, proceeding to [task]"
+
+**BLOCK PROGRESS** until all checklist items are confirmed.
+
 ## Primary Context Documents
 Read at session start: `conductor/product.md`, `conductor/product-guidelines.md`
 

.opencode/agents/tier2-tech-lead.md

@@ -44,6 +44,37 @@ You MUST use Manual Slop's MCP tools. Native OpenCode tools are unreliable.
 |-------------|----------|
 | `bash` | `manual-slop_run_powershell` |
 
+## Session Start Checklist (MANDATORY)
+
+Before ANY other action:
+1. [ ] Read `conductor/workflow.md`
+2. [ ] Read `conductor/tech-stack.md`
+3. [ ] Read `conductor/product.md`
+4. [ ] Read relevant `docs/guide_*.md` for current task domain
+5. [ ] Check `TASKS.md` for active tracks
+6. [ ] Announce: "Context loaded, proceeding to [task]"
+
+**BLOCK PROGRESS** until all checklist items are confirmed.
+
+## Tool Restrictions (TIER 2)
+
+### ALLOWED Tools (Read-Only Research)
+- `manual-slop_read_file` (for files <50 lines only)
+- `manual-slop_py_get_skeleton`, `manual-slop_py_get_code_outline`, `manual-slop_get_file_summary`
+- `manual-slop_py_find_usages`, `manual-slop_search_files`
+- `manual-slop_run_powershell` (for git status, pytest --collect-only)
+
+### FORBIDDEN Actions (Delegate to Tier 3)
+- **NEVER** use native `edit` tool on .py files - destroys indentation
+- **NEVER** write implementation code directly - delegate to Tier 3 Worker
+- **NEVER** skip TDD Red-Green cycle
+
+### Required Pattern
+1. Research with skeleton tools
+2. Draft surgical prompt with WHERE/WHAT/HOW/SAFETY
+3. Delegate to Tier 3 via Task tool
+4. Verify result
+
 ## Primary Context Documents
 Read at session start: `conductor/product.md`, `conductor/workflow.md`, `conductor/tech-stack.md`
 

.opencode/agents/tier3-worker.md

@@ -46,6 +46,14 @@ You MUST use Manual Slop's MCP tools. Native OpenCode tools are unreliable.
 You operate statelessly. Each task starts fresh with only the context provided.
 Do not assume knowledge from previous tasks or sessions.
 
+## Task Start Checklist (MANDATORY)
+
+Before implementing:
+1. [ ] Read task prompt - identify WHERE/WHAT/HOW/SAFETY
+2. [ ] Use skeleton tools for files >50 lines (`manual-slop_py_get_skeleton`, `manual-slop_get_file_summary`)
+3. [ ] Verify target file and line range exists
+4. [ ] Announce: "Implementing: [task description]"
+
 ## Task Execution Protocol
 
 ### 1. Understand the Task

.opencode/agents/tier4-qa.md

@@ -43,6 +43,14 @@ You MUST use Manual Slop's MCP tools. Native OpenCode tools are unreliable.
 You operate statelessly. Each analysis starts fresh.
 Do not assume knowledge from previous analyses or sessions.
 
+## Analysis Start Checklist (MANDATORY)
+
+Before analyzing:
+1. [ ] Read error output/test failure completely
+2. [ ] Identify affected files from traceback
+3. [ ] Use skeleton tools for files >50 lines (`manual-slop_py_get_skeleton`)
+4. [ ] Announce: "Analyzing: [error summary]"
+
 ## Analysis Protocol
 
 ### 1. Understand the Error