devlyn-cli 1.12.2 → 1.12.3

package/CLAUDE.md

@@ -72,7 +72,7 @@ Optional flags:
 - `--skip-review` — skip team-review phase
 - `--skip-clean` — skip clean phase
 - `--skip-docs` — skip update-docs phase
-- `--engine auto|codex|claude` — intelligent model routing. `auto` routes each phase and team role to the optimal model (Claude or Codex GPT-5.4) based on benchmark data. `codex` forces Codex for implementation, Claude for evaluation. `claude` (default) uses Claude for everything. Requires codex-mcp-server.
+- `--engine auto|codex|claude` — intelligent model routing. `auto` (default) routes each phase and team role to the optimal model (Claude or Codex GPT-5.4) based on benchmark data. `codex` forces Codex for implementation, Claude for evaluation. `claude` uses Claude for everything. Requires codex-mcp-server for `auto` and `codex` modes.
 - `--with-codex [evaluate|review|both]` — (legacy, superseded by `--engine`) use OpenAI Codex as cross-model evaluator/reviewer (requires codex-mcp-server)
 
 ## Preflight Check (Post-Roadmap Verification)

package/README.md

@@ -111,7 +111,7 @@ Install the Codex MCP server during setup, then:
 
 **`--engine auto`** routes each pipeline phase and team role to the optimal model (Claude Opus 4.6 or GPT-5.4) — validated through A/B testing, not just benchmarks.
 
-> `--engine auto` (recommended) · `--engine codex` (force Codex for build) · `--engine claude` (default, Claude only)
+> `--engine auto` (default, recommended) · `--engine codex` (force Codex for build) · `--engine claude` (Claude only)
 
 Works across the full pipeline:
 

package/config/skills/devlyn:auto-resolve/SKILL.md

@@ -34,10 +34,10 @@ This pipeline runs hands-free. The user launches it to walk away and come back t
    - `--skip-build-gate` (false) — skip the deterministic build gate (Phase 1.4). Not recommended — the build gate is the primary defense against "tests pass locally, breaks in CI/Docker/production" class of bugs.
    - `--build-gate MODE` (auto) — controls build gate behavior. `auto`: detect project type and run appropriate build/typecheck/lint commands; if Dockerfile(s) are present, Docker builds are included automatically. `strict`: auto + treat warnings as errors. `no-docker`: auto but skip Docker builds even if Dockerfiles exist (for faster iteration). `skip`: same as --skip-build-gate.
    - `--with-codex` (false) — use OpenAI Codex as a cross-model evaluator/reviewer via `mcp__codex-cli__*` MCP tools. Accepts: `evaluate`, `review`, or `both` (default when flag is present without value). When enabled, Codex provides an independent second opinion from a different model family, creating a GAN-like dynamic where Claude builds and Codex critiques. **Ignored if `--engine` is set** (engine routing subsumes this).
-   - `--engine MODE` (claude) — controls which model handles each pipeline phase and team role. Modes:
-     - `claude` (default): all phases use Claude subagents. Current behavior, no Codex calls.
+   - `--engine MODE` (auto) — controls which model handles each pipeline phase and team role. Modes:
+     - `auto` (default): each phase and team role routes to the optimal model based on benchmark data. Requires Codex MCP server. Subsumes `--with-codex both`.
      - `codex`: Codex handles implementation/analysis phases, Claude handles orchestration, evaluation, and Chrome MCP.
-     - `auto`: each phase and team role routes to the optimal model based on benchmark data. Recommended when Codex MCP server is available. Subsumes `--with-codex both`.
+     - `claude`: all phases use Claude subagents. No Codex calls.
 
    Flags can be passed naturally: `/devlyn:auto-resolve fix the auth bug --max-rounds 3 --skip-docs`
    Engine examples: `--engine auto`, `--engine codex`, `--engine claude`
@@ -58,7 +58,7 @@ Cross-model evaluation (Codex): [evaluate / review / both / disabled / subsumed
 
 ## PHASE 1: BUILD
 
-**Engine routing**: If `--engine` is `auto` or `codex`, read `references/engine-routing.md` "How to Spawn a Codex BUILD/FIX Agent" section. Call `mcp__codex-cli__codex` with `model: "gpt-5.4"`, `reasoningEffort: "xhigh"`, `sandbox: "workspace-write"`, `fullAuto: true`, and the full agent prompt below as the `prompt` parameter. If `--engine` is `claude` (default), spawn a Claude subagent as described below.
+**Engine routing**: If `--engine` is `auto` or `codex`, read `references/engine-routing.md` "How to Spawn a Codex BUILD/FIX Agent" section. Call `mcp__codex-cli__codex` with `model: "gpt-5.4"`, `reasoningEffort: "xhigh"`, `sandbox: "workspace-write"`, `fullAuto: true`, and the full agent prompt below as the `prompt` parameter. If `--engine` is `claude`, spawn a Claude subagent as described below.
 
 Spawn a subagent using the Agent tool with `mode: "bypassPermissions"` to investigate and implement the fix. The subagent does NOT have access to skills, so include all necessary instructions inline.
 

package/config/skills/devlyn:auto-resolve/references/engine-routing.md

@@ -197,7 +197,7 @@ mcp__codex-cli__codex({
 
 ## Override Behavior
 
-- `--engine claude` → all roles and phases use Claude (current default behavior, no Codex calls)
+- `--engine claude` → all roles and phases use Claude (no Codex calls)
 - `--engine codex` → all phases use Codex for implementation/analysis, Claude only for orchestration and Chrome MCP
 - `--engine auto` → each role and phase routes to the optimal model per this table
 - `--engine auto` is the recommended default when Codex MCP server is available

package/config/skills/devlyn:ideate/SKILL.md

@@ -25,10 +25,10 @@ Concretely:
 Parse these from the user's invocation message:
 
 - `--with-codex` (default: off) — bare flag. When set, OpenAI Codex runs an independent rubric pass during Phase 3.5 CHALLENGE via `mcp__codex-cli__*` MCP tools, using the same rubric as the solo pass. Codex always runs at `reasoningEffort: "xhigh"` — the entire reason for the flag is maximum reasoning from a second model family. **Ignored if `--engine` is set** (engine routing subsumes this).
-- `--engine MODE` (claude) — controls which model handles each ideation phase. Modes:
-  - `claude` (default): all phases use Claude. Current behavior.
+- `--engine MODE` (auto) — controls which model handles each ideation phase. Modes:
+  - `auto` (default): Claude handles FRAME/EXPLORE/CONVERGE/DOCUMENT (ambiguous intent, writing quality), Codex runs the CHALLENGE rubric pass as critic (GAN dynamic). Subsumes `--with-codex`. Requires Codex MCP server.
   - `codex`: Codex handles FRAME/EXPLORE/CONVERGE/DOCUMENT, Claude runs CHALLENGE (role reversal — builder and critic are always different models).
-  - `auto`: Claude handles FRAME/EXPLORE/CONVERGE/DOCUMENT (ambiguous intent, writing quality), Codex runs the CHALLENGE rubric pass as critic (GAN dynamic). Subsumes `--with-codex`. Recommended when Codex MCP is available.
+  - `claude`: all phases use Claude. No Codex calls.
 
 **If `--engine` is `auto` or `codex`**: call `mcp__codex-cli__ping` to verify the Codex MCP server is available. If ping fails, warn the user and offer: [1] Continue with `--engine claude`, [2] Abort. Also read `references/challenge-rubric.md` up front. The engine routing table is defined in the auto-resolve skill's `references/engine-routing.md` under "Pipeline Phase Routing (ideate)".
 

package/config/skills/devlyn:preflight/SKILL.md

@@ -44,10 +44,10 @@ Parse from `<preflight_config>`:
 - `--autofix` — auto-promote all findings to roadmap items and run auto-resolve on each
 - `--skip-browser` — skip browser validation
 - `--skip-docs` — skip documentation audit
-- `--engine MODE` (claude) — controls which model handles audit phases. Modes:
-  - `claude` (default): all auditors use Claude subagents.
+- `--engine MODE` (auto) — controls which model handles audit phases. Modes:
+  - `auto` (default): code-auditor uses Codex (SWE-bench Pro +11.7pp for code analysis), docs-auditor uses Claude (writing quality), browser-auditor uses Claude (Chrome MCP). Requires Codex MCP server.
   - `codex`: code-auditor uses Codex, docs-auditor and browser-auditor use Claude.
-  - `auto`: code-auditor uses Codex (SWE-bench Pro +11.7pp for code analysis), docs-auditor uses Claude (writing quality), browser-auditor uses Claude (Chrome MCP). Recommended when Codex MCP is available.
+  - `claude`: all auditors use Claude subagents. No Codex calls.
 
 Example: `/devlyn:preflight --phase 2 --skip-browser`
 Example with engine: `/devlyn:preflight --engine auto`

package/config/skills/devlyn:team-resolve/SKILL.md

@@ -147,7 +147,7 @@ Codex roles cannot use TeamCreate/SendMessage — the Team Lead (you) relays the
 
 **For Dual roles** (e.g., security-auditor): Run BOTH a Claude Agent teammate AND a `mcp__codex-cli__codex` call in parallel with the same prompt. Merge findings per `engine-routing.md` "How to Spawn a Dual Role" section.
 
-If `--engine claude` or no `--engine` flag: all roles use Claude Agent teammates (current default behavior).
+If `--engine auto` or no `--engine` flag: routes each role to the optimal model based on benchmark data (see `engine-routing.md`). If `--engine claude`: all roles use Claude Agent teammates.
 
 ### Teammate Prompts
 

package/config/skills/devlyn:team-review/SKILL.md

@@ -83,7 +83,7 @@ Codex reviewers cannot use TeamCreate/SendMessage — the Review Lead (you) coll
 
 **For Dual roles** (e.g., security-reviewer): Run BOTH a Claude Agent reviewer AND a `mcp__codex-cli__codex` call in parallel with the same prompt. Merge findings per `engine-routing.md` "How to Spawn a Dual Role" section.
 
-If `--engine claude` or no `--engine` flag: all roles use Claude Agent reviewers (current default behavior).
+If `--engine auto` or no `--engine` flag: routes each reviewer role to the optimal model based on benchmark data (see `engine-routing.md`). If `--engine claude`: all roles use Claude Agent reviewers.
 
 ### Reviewer Prompts
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "devlyn-cli",
-  "version": "1.12.2",
+  "version": "1.12.3",
   "description": "AI development toolkit for Claude Code — ideate, auto-resolve, and ship with context engineering and agent orchestration",
   "homepage": "https://github.com/fysoul17/devlyn-cli#readme",
   "bin": {