chore(ce-work-beta): remove beta Codex-delegation skill (#1013)

Author: tmchow

README.md

@@ -105,7 +105,7 @@ The first pass tightens recent branch changes before review. The targeted pass i
 
 After installing, run `/ce-setup` in any project. It checks repo-local config, reports optional tool capabilities, and helps keep machine-local CE settings safely gitignored.
 
-The `compound-engineering` plugin currently ships 27 skills and 0 standalone agents. Specialist review, research, and workflow behavior lives inside the owning skills as skill-local prompt assets.
+The `compound-engineering` plugin currently ships 26 skills and 0 standalone agents. Specialist review, research, and workflow behavior lives inside the owning skills as skill-local prompt assets.
 
 ### Full Skill Inventory
 
@@ -136,7 +136,6 @@ The `compound-engineering` plugin currently ships 27 skills and 0 standalone age
 | `/ce-polish` | Start a dev server and iterate on UX polish |
 | `/ce-proof` | Create, edit, and share Proof documents |
 | `/ce-dogfood-beta` | Diff-scoped browser QA of the active branch |
-| `/ce-work-beta` | Experimental execution workflow with Codex delegation mode |
 | `/lfg` | Full autonomous engineering workflow |
 
 ---

docs/plans/2026-06-26-001-chore-remove-ce-work-beta-plan.html

@@ -18,16 +18,17 @@ tags:
   - batching
   - orchestration-cost
   - prompt-engineering
-  - ce-work-beta
 ---
 
 # Codex Delegation Best Practices
 
 ## Context
 
-Over six iterations of evaluation building Codex delegation into `ce-work-beta`, we collected quantitative data on the token economics of orchestrating work between Claude Code (the orchestrator) and Codex (the delegated executor). The core question: when does delegating plan units to Codex actually save Claude tokens, and what architectural patterns control the cost?
+> **Note:** This is a retrospective. The experimental delegation skill it studied (`ce-work-beta`) has since been removed from the plugin. The findings below are preserved as general guidance for designing external-model delegation in any orchestrator skill, not as documentation for a live feature.
 
-The delegation model: `ce-work-beta` receives a plan with N implementation units, then decides whether to execute them directly (standard mode) or delegate them to Codex via `codex exec`. Delegation has a fixed orchestration overhead per batch (prompt file write, codex exec invocation, result classification, commit) of approximately 4-5k Claude tokens. Each unit of code Claude does not write saves roughly 3-5k tokens. The crossover depends on how many units are batched per delegation call.
+Over six iterations of evaluation building Codex delegation into an experimental `ce-work` delegation mode, we collected quantitative data on the token economics of orchestrating work between Claude Code (the orchestrator) and Codex (the delegated executor). The core question: when does delegating plan units to Codex actually save Claude tokens, and what architectural patterns control the cost?
+
+The delegation model: the delegating skill receives a plan with N implementation units, then decides whether to execute them directly (standard mode) or delegate them to Codex via `codex exec`. Delegation has a fixed orchestration overhead per batch (prompt file write, codex exec invocation, result classification, commit) of approximately 4-5k Claude tokens. Each unit of code Claude does not write saves roughly 3-5k tokens. The crossover depends on how many units are batched per delegation call.
 
 The evaluation spanned iterations 1-6, testing small (1-2 units), medium (4 units), large (7 units), and extra-large (10 units) plans in both delegation and standard modes, with real code implementation and test verification in isolated worktrees.