refactor

name	refactor
description	Intelligent refactor command. Triggers: refactor, refactoring, cleanup, restructure, extract, simplify, modernize.

Codex Harness Tool Compatibility

This skill may include examples copied from the OpenCode harness. In Codex, do not call OpenCode-only tools such as call_omo_agent(...), task(...), background_output(...), or team_*(...) literally. Translate those examples to Codex native tools:

OpenCode example	Codex tool to use
call_omo_agent(subagent_type="explore", ...)	multi_agent_v1.spawn_agent({"message":"TASK: act as an explorer. ...","agent_type":"explorer","fork_context":false})
call_omo_agent(subagent_type="librarian", ...)	multi_agent_v1.spawn_agent({"message":"TASK: act as a librarian. ...","agent_type":"librarian","fork_context":false})
task(subagent_type="plan", ...)	multi_agent_v1.spawn_agent({"message":"TASK: act as a planning agent. ...","agent_type":"plan","fork_context":false})
task(subagent_type="oracle", ...) for final verification	multi_agent_v1.spawn_agent({"message":"TASK: act as a rigorous reviewer. ...","agent_type":"lazycodex-gate-reviewer","fork_context":false})
task(category="...", ...) for implementation or QA	multi_agent_v1.spawn_agent({"message":"TASK: act as an implementation or QA worker. ...","fork_context":false})
background_output(task_id="...")	multi_agent_v1.wait_agent(...) for mailbox signals
team_*(...)	Use Codex native subagents via multi_agent_v1.spawn_agent, multi_agent_v1.send_input, multi_agent_v1.wait_agent, and multi_agent_v1.close_agent

Role-specific behavior must be described in a self-contained message. Use fork_context: false to start the child with only the initial prompt (no parent history); use fork_context: true only when full parent history is truly required. Include any required conversation context, files, diffs, constraints, and requested skill names directly in the spawned agent's message. OMO installs these selectable agent roles into ~/.codex/agents/: explorer, librarian, plan, momus, metis, lazycodex-code-reviewer, lazycodex-qa-executor, and lazycodex-gate-reviewer - pass the matching name as agent_type so the child gets that role's model and instructions. If the spawn tool exposes no agent_type parameter, omit it and describe the role inside message. If a code block below conflicts with this section, this section wins.

On multi_agent_v2 sessions the same agent_type applies (the OMO installer exposes it) with fork_turns instead of fork_context. If a code block below conflicts with this section, this section wins.

When translating load_skills=[...], include the requested skill names in the spawned agent's message. If a code block below conflicts with this section, this section wins.

For work likely to exceed one wait cycle, require the child to send WORKING: <task> - <current phase> before long passes and BLOCKED: <reason> only when progress stops. A multi_agent_v1.wait_agent timeout only means no new mailbox update arrived. Treat a running child as alive. Fallback only when the child is completed without the deliverable, ack-only after followup, explicitly BLOCKED:, or no longer running.

export const REFACTOR_TEMPLATE = `# Intelligent Refactor Command

Usage

``` /refactor [--scope=<file|module|project>] [--strategy=<safe|aggressive>]

Arguments: refactoring-target: What to refactor. Can be: - File path: src/auth/handler.ts - Symbol name: "AuthService class" - Pattern: "all functions using deprecated API" - Description: "extract validation logic into separate module"

Options: --scope: Refactoring scope (default: module) - file: Single file only - module: Module/directory scope - project: Entire codebase

--strategy: Risk tolerance (default: safe) - safe: Conservative, maximum test coverage required - aggressive: Allow broader changes with adequate coverage ```

What This Command Does

Performs intelligent, deterministic refactoring with full codebase awareness. Unlike blind search-and-replace, this command:

1. Understands your intent - Analyzes what you actually want to achieve
2. Maps the codebase - Builds a definitive codemap before touching anything
3. Assesses risk - Evaluates test coverage and determines verification strategy
4. Plans meticulously - Creates a detailed plan with Plan agent
5. Executes precisely - Step-by-step refactoring with LSP and AST-grep
6. Verifies constantly - Runs tests after each change to ensure zero regression

---

PHASE 0: INTENT GATE (MANDATORY FIRST STEP)

BEFORE ANY ACTION, classify and validate the request.

Step 0.1: Parse Request Type

Signal	Classification	Action
Specific file/symbol	Explicit	Proceed to codebase analysis
"Refactor X to Y"	Clear transformation	Proceed to codebase analysis
"Improve", "Clean up"	Open-ended	MUST ask: "What specific improvement?"
Ambiguous scope	Uncertain	MUST ask: "Which modules/files?"
Missing context	Incomplete	MUST ask: "What's the desired outcome?"

Step 0.2: Validate Understanding

Before proceeding, confirm:

• Target is clearly identified
• Desired outcome is understood
• Scope is defined (file/module/project)
• Success criteria can be articulated

If ANY of above is unclear, ASK CLARIFYING QUESTION:

``` I want to make sure I understand the refactoring goal correctly.

What I understood: [interpretation] What I'm unsure about: [specific ambiguity]

Options I see:

1. [Option A] - [implications]
2. [Option B] - [implications]

My recommendation: [suggestion with reasoning]

Should I proceed with [recommendation], or would you prefer differently? ```

Step 0.3: Create Initial Todos

IMMEDIATELY after understanding the request, create todos:

``` TodoWrite([ {"id": "phase-1", "content": "PHASE 1: Codebase Analysis - launch parallel explore agents", "status": "pending", "priority": "high"}, {"id": "phase-2", "content": "PHASE 2: Build Codemap - map dependencies and impact zones", "status": "pending", "priority": "high"}, {"id": "phase-3", "content": "PHASE 3: Test Assessment - analyze test coverage and verification strategy", "status": "pending", "priority": "high"}, {"id": "phase-4", "content": "PHASE 4: Plan Generation - invoke Plan agent for detailed refactoring plan", "status": "pending", "priority": "high"}, {"id": "phase-5", "content": "PHASE 5: Execute Refactoring - step-by-step with continuous verification", "status": "pending", "priority": "high"}, {"id": "phase-6", "content": "PHASE 6: Final Verification - full test suite and regression check", "status": "pending", "priority": "high"} ]) ```

---

PHASE 1: CODEBASE ANALYSIS (PARALLEL EXPLORATION)

Mark phase-1 as in_progress.

1.1: Launch Parallel Explore Agents (BACKGROUND)

Fire ALL of these simultaneously using `call_omo_agent`:

``` // Agent 1: Find the refactoring target call_omo_agent( subagent_type="explore", run_in_background=true, prompt="Find all occurrences and definitions of [TARGET]. Report: file paths, line numbers, usage patterns." )

// Agent 2: Find related code call_omo_agent( subagent_type="explore", run_in_background=true, prompt="Find all code that imports, uses, or depends on [TARGET]. Report: dependency chains, import graphs." )

// Agent 3: Find similar patterns call_omo_agent( subagent_type="explore", run_in_background=true, prompt="Find similar code patterns to [TARGET] in the codebase. Report: analogous implementations, established conventions." )

// Agent 4: Find tests call_omo_agent( subagent_type="explore", run_in_background=true, prompt="Find all test files related to [TARGET]. Report: test file paths, test case names, coverage indicators." )

// Agent 5: Architecture context call_omo_agent( subagent_type="explore", run_in_background=true, prompt="Find architectural patterns and module organization around [TARGET]. Report: module boundaries, layer structure, design patterns in use." ) ```

1.2: Direct Tool Exploration (WHILE AGENTS RUN)

While background agents are running, use direct tools:

LSP Tools for Precise Analysis:

```typescript // Find definition(s) LspGotoDefinition(filePath, line, character) // Where is it defined?

// Find ALL usages across workspace LspFindReferences(filePath, line, character, includeDeclaration=true)

// Get file structure LspDocumentSymbols(filePath) // Hierarchical outline LspWorkspaceSymbols(filePath, query="[target_symbol]") // Search by name

// Get current diagnostics lsp_diagnostics(filePath) // Errors, warnings before we start ```

AST-Grep Skill for Pattern Analysis:

```bash // Find structural patterns python3 scripts/ast_grep_helper.py search 'function $NAME($$$) { $$$ }' --lang ts src/

Preview refactoring first

sg --pattern '[old_pattern]' --rewrite '[new_pattern]' --lang ts src/ ```

Grep for Text Patterns:

``` grep(pattern="[search_term]", path="src/", include="*.ts") ```

1.3: Collect Background Results

``` background_output(task_id="[agent_1_id]") background_output(task_id="[agent_2_id]") ... ```

Mark phase-1 as completed after all results collected.

---

PHASE 2: BUILD CODEMAP (DEPENDENCY MAPPING)

Mark phase-2 as in_progress.

2.1: Construct Definitive Codemap

Based on Phase 1 results, build:

```

CODEMAP: [TARGET]

Core Files (Direct Impact)

• `path/to/file.ts:L10-L50` - Primary definition
• `path/to/file2.ts:L25` - Key usage

Dependency Graph

``` [TARGET] ├── imports from: │ ├── module-a (types) │ └── module-b (utils) ├── imported by: │ ├── consumer-1.ts │ ├── consumer-2.ts │ └── consumer-3.ts └── used by: ├── handler.ts (direct call) └── service.ts (dependency injection) ```

Impact Zones

Zone	Risk Level	Files Affected	Test Coverage
Core	HIGH	3 files	85% covered
Consumers	MEDIUM	8 files	70% covered
Edge	LOW	2 files	50% covered

Established Patterns

• Pattern A: [description] - used in N places
• Pattern B: [description] - established convention ```

2.2: Identify Refactoring Constraints

Based on codemap:

• MUST follow: [existing patterns identified]
• MUST NOT break: [critical dependencies]
• Safe to change: [isolated code zones]
• Requires migration: [breaking changes impact]

Mark phase-2 as completed.

---

PHASE 3: TEST ASSESSMENT (VERIFICATION STRATEGY)

Mark phase-3 as in_progress.

3.1: Detect Test Infrastructure

```bash

Check for test commands

cat package.json | jq '.scripts | keys[] | select(test("test"))'

Or for Python

ls -la pytest.ini pyproject.toml setup.cfg

Or for Go

ls -la *_test.go ```

3.2: Analyze Test Coverage

``` // Find all tests related to target call_omo_agent( subagent_type="explore", run_in_background=false, // Need this synchronously prompt="Analyze test coverage for [TARGET]:

1. Which test files cover this code?
2. What test cases exist?
3. Are there integration tests?
4. What edge cases are tested?
5. Estimated coverage percentage?" ) ```

3.3: Determine Verification Strategy

Based on test analysis:

Coverage Level	Strategy
HIGH (>80%)	Run existing tests after each step
MEDIUM (50-80%)	Run tests + add safety assertions
LOW (<50%)	PAUSE: Propose adding tests first
NONE	BLOCK: Refuse aggressive refactoring

If coverage is LOW or NONE, ask user:

``` Test coverage for [TARGET] is [LEVEL].

Risk Assessment: Refactoring without adequate tests is dangerous.

Options:

1. Add tests first, then refactor (RECOMMENDED)
2. Proceed with extra caution, manual verification required
3. Abort refactoring

Which approach do you prefer? ```

3.4: Document Verification Plan

```

VERIFICATION PLAN

Test Commands

• Unit: `bun test` / `npm test` / `pytest` / etc.
• Integration: [command if exists]
• Type check: `tsc --noEmit` / `pyright` / etc.

Verification Checkpoints

After each refactoring step:

1. lsp_diagnostics → zero new errors
2. Run test command → all pass
3. Type check → clean

Regression Indicators

• [Specific test that must pass]
• [Behavior that must be preserved]
• [API contract that must not change] ```

Mark phase-3 as completed.

---

PHASE 4: PLAN GENERATION (PLAN AGENT)

Mark phase-4 as in_progress.

4.1: Invoke Plan Agent

``` Task( subagent_type="plan", prompt="Create a detailed refactoring plan:

Refactoring Goal

[User's original request]

Codemap (from Phase 2)

[Insert codemap here]

Test Coverage (from Phase 3)

[Insert verification plan here]

Constraints

• MUST follow existing patterns: [list]
• MUST NOT break: [critical paths]
• MUST run tests after each step

Requirements

1. Break down into atomic refactoring steps
2. Each step must be independently verifiable
3. Order steps by dependency (what must happen first)
4. Specify exact files and line ranges for each step
5. Include rollback strategy for each step
6. Define commit checkpoints" ) ```

4.2: Review and Validate Plan

After receiving plan from Plan agent:

1. Verify completeness: All identified files addressed?
2. Verify safety: Each step reversible?
3. Verify order: Dependencies respected?
4. Verify verification: Test commands specified?

4.3: Register Detailed Todos

Convert Plan agent output into granular todos:

``` TodoWrite([ // Each step from the plan becomes a todo {"id": "refactor-1", "content": "Step 1: [description]", "status": "pending", "priority": "high"}, {"id": "verify-1", "content": "Verify Step 1: run tests", "status": "pending", "priority": "high"}, {"id": "refactor-2", "content": "Step 2: [description]", "status": "pending", "priority": "medium"}, {"id": "verify-2", "content": "Verify Step 2: run tests", "status": "pending", "priority": "medium"}, // ... continue for all steps ]) ```

Mark phase-4 as completed.

---

PHASE 5: EXECUTE REFACTORING (DETERMINISTIC EXECUTION)

Mark phase-5 as in_progress.

5.1: Execution Protocol

For EACH refactoring step:

Pre-Step

1. Mark step todo as `in_progress`
2. Read current file state
3. Verify lsp_diagnostics is baseline

Execute Step

Use appropriate tool:

For Symbol Renames: ```typescript lsp_prepare_rename(filePath, line, character) // Validate rename is possible lsp_rename(filePath, line, character, newName) // Execute rename ```

For Pattern Transformations: ```bash // Preview first sg --pattern '[pattern]' --rewrite '[rewrite]' --lang ts path/to/file.ts

// If preview looks good, execute python3 scripts/ast_grep_helper.py replace '[pattern]' '[rewrite]' --lang ts path/to/file.ts --apply ```

For Structural Changes: ```typescript // Use Edit tool for precise changes edit(filePath, oldString, newString) ```

Post-Step Verification (MANDATORY)

```typescript // 1. Check diagnostics lsp_diagnostics(filePath) // Must be clean or same as baseline

// 2. Run tests bash("bun test") // Or appropriate test command

// 3. Type check bash("tsc --noEmit") // Or appropriate type check ```

Step Completion

1. If verification passes → Mark step todo as `completed`
2. If verification fails → STOP AND FIX

5.2: Failure Recovery Protocol

If ANY verification fails:

1. STOP immediately
2. REVERT the failed change
3. DIAGNOSE what went wrong
4. OPTIONS:
   • Fix the issue and retry
   • Skip this step (if optional)
   • Consult oracle agent for help
   • Ask user for guidance

NEVER proceed to next step with broken tests.

5.3: Commit Checkpoints

After each logical group of changes:

```bash git add [changed-files] git commit -m "refactor(scope): description

[details of what was changed and why]" ```

Mark phase-5 as completed when all refactoring steps done.

---

PHASE 6: FINAL VERIFICATION (REGRESSION CHECK)

Mark phase-6 as in_progress.

6.1: Full Test Suite

```bash

Run complete test suite

bun test # or npm test, pytest, go test, etc. ```

6.2: Type Check

```bash

Full type check

tsc --noEmit # or equivalent ```

6.3: Lint Check

```bash

Run linter

eslint . # or equivalent ```

6.4: Build Verification (if applicable)

```bash

Ensure build still works

bun run build # or npm run build, etc. ```

6.5: Final Diagnostics

```typescript // Check all changed files for (file of changedFiles) { lsp_diagnostics(file) // Must all be clean } ```

6.6: Generate Summary

```markdown

Refactoring Complete

What Changed

• [List of changes made]

Files Modified

• `path/to/file.ts` - [what changed]
• `path/to/file2.ts` - [what changed]

Verification Results

• Tests: PASSED (X/Y passing)
• Type Check: CLEAN
• Lint: CLEAN
• Build: SUCCESS

No Regressions Detected

All existing tests pass. No new errors introduced. ```

Mark phase-6 as completed.

---

CRITICAL RULES

NEVER DO

• Skip lsp_diagnostics check after changes
• Proceed with failing tests
• Make changes without understanding impact
• Use `as any`, `@ts-ignore`, `@ts-expect-error`
• Delete tests to make them pass
• Commit broken code
• Refactor without understanding existing patterns

ALWAYS DO

• Understand before changing
• Preview before applying (sg --pattern ... --rewrite ... --lang ...)
• Verify after every change
• Follow existing codebase patterns
• Keep todos updated in real-time
• Commit at logical checkpoints
• Report issues immediately

ABORT CONDITIONS

If any of these occur, STOP and consult user:

• Test coverage is zero for target code
• Changes would break public API
• Refactoring scope is unclear
• 3 consecutive verification failures
• User-defined constraints violated

---

Tool Usage Philosophy

You already know these tools. Use them intelligently:

LSP Tools

Leverage LSP tools for precision analysis. Key patterns:

• Understand before changing: `LspGotoDefinition` to grasp context
• Impact analysis: `LspFindReferences` to map all usages before modification
• Safe refactoring: `lsp_prepare_rename` → `lsp_rename` for symbol renames
• Continuous verification: `lsp_diagnostics` after every change

AST-Grep

Use `ast-grep` skill helper or `sg` CLI for structural transformations. Critical: Always preview first, review, then execute.

Agents

• `explore`: Parallel codebase pattern discovery
• `plan`: Detailed refactoring plan generation
• `oracle`: Read-only consultation for complex architectural decisions and debugging
• `librarian`: Use proactively when encountering deprecated methods or library migration tasks. Query official docs and OSS examples for modern replacements.

Deprecated Code & Library Migration

When you encounter deprecated methods/APIs during refactoring:

1. Fire `librarian` to find the recommended modern alternative
2. DO NOT auto-upgrade to latest version unless user explicitly requests migration
3. If user requests library migration, use `librarian` to fetch latest API docs before making changes

---

Remember: Refactoring without tests is reckless. Refactoring without understanding is destructive. This command ensures you do neither.

$ARGUMENTS `

export const REFACTOR_TEAM_MODE_ADDENDUM = `

Team Mode Protocol (active when team_* tools are present)

Team mode is enabled for this session. The rules below override Phase 4-6 above. Follow this protocol instead of the in-session step-by-step execution.

Phase 4 override: Plan agent staffing requirement

When invoking the Plan agent in Phase 4.1, append this additional requirement to the prompt:

``` 7. (REQUIRED when team mode is active) Output a Team Staffing Recommendation section with these fields — missing fields fail Phase 5.0:

• total_atomic_steps: integer
• file_independent_steps: integer (parallelizable, no cross-file blocker)
• cross_file_dependent_steps: integer (has blockers)
• per_step_assignment: [{step_id, assigned_to: 'quick' | 'unspecified-low', blockedBy: [step_ids], rationale}]
• dispatch_path_recommendation: 'team' | 'legacy' with reason
• rationale for the composition ```

Classification rules the plan agent must apply to each step:

• `quick`: mechanical edits — LSP rename, extract variable, inline, simple move, signature change without call-site logic.
• `unspecified-low`: logic-preserving refactors that need reasoning — extract function, restructure conditional, pattern transformation, cross-file API change.
• Recommend `team` path when `file_independent_steps >= 3`; recommend `legacy` otherwise.

Phase 5 override: Dispatch path selection

Read the Team Staffing Recommendation from Phase 4. If any required field is missing, fail here and re-request the plan with the exact missing field names. Do not proceed with a partial plan.

Then choose the path:

• Team path (5.1-T): when the plan recommends `team` AND `file_independent_steps >= 3`. Members execute in parallel, Lead orchestrates, a `deep` verifier lives outside the team.
• Legacy path (5.1-L): otherwise. Use the original 5.1 / 5.2 / 5.3 flow from above.

Record the chosen path in the TodoWrite list.

Phase 5.1-T: `refactor-squad` team execution

Precondition checks (fail hard if any step fails):

1. Load the `team-mode` skill via the `skill` tool for lifecycle, message protocol, and limits.
2. Call `team_list` and verify no active `refactor-squad` run exists; if one does, shutdown + delete the orphan before proceeding.
3. If `~/.omo/teams/refactor-squad/config.json` is missing, write it using the spec below.

Team spec (`~/.omo/teams/refactor-squad/config.json`):

```json { "name": "refactor-squad", "lead": { "kind": "subagent_type", "subagent_type": "sisyphus" }, "members": [ { "kind": "category", "category": "quick", "prompt": "You handle mechanical refactoring steps (LSP rename, extract variable, inline, simple move, signature change). Use LSP tools for correctness. Apply the task description's per-step instructions verbatim — no scope expansion. After edits, run lsp_diagnostics on touched files. Report via team_send_message(teamRunId=, to="lead", summary=, body=<lsp status + diff summary>) + team_task_update(status=completed). Never run tests — the external verifier handles that. Never git add, never --continue." }, { "kind": "category", "category": "quick", "prompt": "Same contract as peer quick worker." }, { "kind": "category", "category": "unspecified-low", "prompt": "You handle logic-preserving refactors that need reasoning (extract function, restructure conditional, pattern transformation, cross-file API change). Read the task description's plan step carefully. Use the ast-grep skill helper or sg CLI to preview structural rewrites first, review the preview, then execute. If the step is ambiguous or would require out-of-scope changes, STOP and send team_send_message(teamRunId=, to="lead", summary="UNCLEAR", body=) + team_task_update(status=pending). Same reporting contract as peer quick workers. Never run tests." }, { "kind": "category", "category": "unspecified-low", "prompt": "Same contract as peer unspecified-low worker." } ] } ```

Rationale for this composition:

• 4 workers = team mode's parallel cap. 5+ just queues.
• No verifier team member. Verification needs `deep` reasoning (or `unspecified-high` fallback). In-team category routing downcasts to sisyphus-junior, which is weaker than required — the verifier runs OUTSIDE the team as a `task(category="deep")`.
• quick × 2 for mechanical edits, unspecified-low × 2 for reasoning edits — mirrors the plan's split.

Team lifecycle (one team, reused until Phase 6 cleanup):

1. `team_create(teamName="refactor-squad")`. Record `teamRunId`.
2. Broadcast the refactor Intent Card ONCE (keep task descriptions slim): ``` team_send_message( teamRunId=, to="*", kind="announcement", summary="refactor-intent", body=<codemap summary + constraints + established patterns from Phase 2> ) ```
3. Broadcast the verification spec ONCE: ``` team_send_message( teamRunId=, to="*", kind="announcement", summary="verify-spec", body=<exact test/typecheck/lint commands + expected pass counts + regression indicators from Phase 3.4> ) ```
4. For each plan step, `team_task_create(teamRunId=, subject="refactor step : ", description=<per-step instructions from plan, including target files and line ranges, rollback strategy>, blockedBy=<from plan's per_step_assignment>)`.

Lead monitoring loop:

While any team task is `pending | claimed | in_progress`:

• Wait for `` or member messages. Avoid tight polling; a single `team_status` check is acceptable if no notification arrives within roughly 10 seconds of expected completion.
• On a worker completion report, immediately dispatch an external verifier — verification runs OUTSIDE the team because team-member category routing downcasts to sisyphus-junior: ``` task( category="deep", load_skills=[], run_in_background=true, description="verify step ", prompt=<files touched + verify-spec commands + instruction to return "PASS" or "FAIL:<failing test + specific error + suggested revert hunks>"> ) ``` If `deep` is unavailable, fall back to `category="unspecified-high"`. Do not create a commit checkpoint until the verifier returns PASS.
• On a verifier PASS: make the commit checkpoint for that step (see original 5.3). Proceed.
• On a verifier FAIL: Lead decides:
  • Retry with fix hint: `team_task_update(status=pending)` on the original step + `team_send_message(teamRunId=, to=, summary="retry", body=)`. Runtime reassigns.
  • Escalate: after three FAIL cycles on the same step, STOP and consult the user with full evidence.
• On a member UNCLEAR message: re-harvest context via a targeted `task()` outside the team, broadcast an updated Intent Card fragment, then reassign.

Proceed to Phase 6 only when every team task is `completed` AND every paired verifier task returned PASS.

Phase 6 override: Team cleanup before summary

If Phase 5 used the team path, dismantle `refactor-squad` BEFORE producing the 6.6 summary. Every exit path — success, escalation, abort — must cleanup; orphan teams poison the next session's precondition check.

1. `team_shutdown_request` for each member, then `team_approve_shutdown` if members do not self-approve within a reasonable window.
2. `team_delete(teamRunId=)`.
3. `team_list` to confirm no residual `refactor-squad` run.

The `~/.omo/teams/refactor-squad/config.json` declaration stays on disk; next session reuses it.

Append to the 6.6 summary a "Dispatch path" line and, when team path was used, team metrics (teamRunId, tasks created, verifier runs, team lifetime).

MUST NOT (team mode)

• Lead never edits files directly — orchestrate only.
• Do not inline the Intent Card or verify-spec into task descriptions — rely on the broadcasts.
• Do not recreate the team mid-session.
• Do not run tests from Lead — the external verifier owns that lane.
• Do not put `oracle` / `librarian` / `deep` into the team spec — oracle/librarian are team-ineligible, and `deep` under category routing downcasts to sisyphus-junior. Use them via `task()` outside the team when needed. `