PolyArch · SihaoLiu · Mar 13, 2026 · Mar 13, 2026 · Mar 13, 2026 · Mar 13, 2026
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
@@ -8,7 +8,7 @@
       "name": "humanize",
       "source": "./",
       "description": "Humanize - An iterative development plugin that uses Codex to review Claude's work. Creates a feedback loop where Claude implements plans and Codex independently reviews progress, ensuring quality through continuous refinement.",
-      "version": "1.15.2"
+      "version": "1.16.0"
     }
   ]
 }
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
 {
   "name": "humanize",
   "description": "Humanize - An iterative development plugin that uses Codex to review Claude's work. Creates a feedback loop where Claude implements plans and Codex independently reviews progress, ensuring quality through continuous refinement.",
-  "version": "1.15.2",
+  "version": "1.16.0",
   "author": {
     "name": "humania-org"
   },

diff --git a/.gitignore b/.gitignore
@@ -3,9 +3,12 @@ temp
 
 # Local Claude client settings
 /.claude/settings.json
+/.claude/scheduled_tasks.lock
 
 # Humanize state directories (runtime-generated, project-local)
 .humanize/
+.claude-flow/
+.swarm/
 
 # Python cache
 __pycache__/

diff --git a/README.md b/README.md
@@ -1,6 +1,6 @@
 # Humanize
 
-**Current Version: 1.15.2**
+**Current Version: 1.16.0**
 
 > Derived from the [GAAC (GitHub-as-a-Context)](https://github.com/SihaoLiu/gaac) project.
 
@@ -25,6 +25,7 @@ A Claude Code plugin that provides iterative development with independent AI rev
 
 The loop has two phases: **Implementation** (Claude works, Codex reviews summaries) and **Code Review** (Codex checks code quality with severity markers). Issues feed back into implementation until resolved.
 
+
 ## Install
 
 ```bash
@@ -45,7 +46,7 @@ Requires [codex CLI](https://github.com/openai/codex) for review. See the full [
    /humanize:gen-plan --input draft.md --output docs/plan.md
    ```
 
-2. **Refine an annotated plan** before implementation when reviewers add `CMT:` ... `ENDCMT` comments:
+2. **Refine an annotated plan** before implementation when reviewers add comments (`CMT:` ... `ENDCMT`, `<cmt>` ... `</cmt>`, or `<comment>` ... `</comment>`):
    ```bash
    /humanize:refine-plan --input docs/plan.md
    ```
@@ -55,10 +56,18 @@ Requires [codex CLI](https://github.com/openai/codex) for review. See the full [
    /humanize:start-rlcr-loop docs/plan.md
    ```
 
-4. **Monitor progress**:
+4. **Consult Gemini** for deep web research (requires Gemini CLI):
+   ```bash
+   /humanize:ask-gemini What are the latest best practices for X?
+   ```
+
+5. **Monitor progress (in another terminal, not inside Claude Code)**:
    ```bash
-   source <path/to/humanize>/scripts/humanize.sh
-   humanize monitor rlcr
+   source <path/to/humanize>/scripts/humanize.sh # Or just add it into your .bashec or .zshrc
+   humanize monitor rlcr       # RLCR loop
+   humanize monitor skill      # All skill invocations (codex + gemini)
+   humanize monitor codex      # Codex invocations only
+   humanize monitor gemini     # Gemini invocations only
    ```
 
 ## Monitor Dashboard

diff --git a/commands/cancel-pr-loop.md b/commands/cancel-pr-loop.md
diff --git a/commands/cancel-rlcr-loop.md b/commands/cancel-rlcr-loop.md
@@ -17,6 +17,7 @@ To cancel the active loop:
 2. Check the first line of output:
    - **NO_LOOP** or **NO_ACTIVE_LOOP**: Say "No active RLCR loop found."
    - **CANCELLED**: Report the cancellation message from the output
+   - **CANCELLED_METHODOLOGY_ANALYSIS**: Report the cancellation message from the output
    - **CANCELLED_FINALIZE**: Report the cancellation message from the output
    - **FINALIZE_NEEDS_CONFIRM**: The loop is in Finalize Phase. Continue to step 3
 
@@ -33,6 +34,6 @@ To cancel the active loop:
    - **If user chooses "No, let it finish"**:
      - Report: "Understood. The Finalize Phase will continue. Once complete, the loop will end normally."
 
-**Key principle**: The script handles all cancellation logic. A loop is active if `state.md` (normal loop) or `finalize-state.md` (Finalize Phase) exists in the newest loop directory.
+**Key principle**: The script handles all cancellation logic. A loop is active if `state.md` (normal loop), `methodology-analysis-state.md` (Methodology Analysis Phase), or `finalize-state.md` (Finalize Phase) exists in the newest loop directory.
 
 The loop directory with summaries, review results, and state information will be preserved for reference.
diff --git a/commands/refine-plan.md b/commands/refine-plan.md
@@ -34,7 +34,7 @@ The refined plan MUST reuse the existing `gen-plan` schema. Do not invent new to
 1. **Execution Mode Setup**: Parse CLI arguments and derive output paths
 2. **Load Project Config**: Resolve `alternative_plan_language` and mode defaults using `config-loader.sh` semantics
 3. **IO Validation**: Run `validate-refine-plan-io.sh`
-4. **Comment Extraction**: Scan the annotated plan and extract valid `CMT:` / `ENDCMT` blocks
+4. **Comment Extraction**: Scan the annotated plan and extract valid comment blocks (`CMT:`/`ENDCMT`, `<cmt>`/`</cmt>`, `<comment>`/`</comment>`)
 5. **Comment Classification**: Classify each extracted comment for downstream handling
 6. **Comment Processing**: Answer questions, apply requested plan edits, and perform targeted research
 7. **Plan Refinement**: Produce the comment-free refined plan while preserving the `gen-plan` structure
@@ -167,7 +167,7 @@ Handle exit codes exactly:
 - Exit code 0: Continue to Phase 2
 - Exit code 1: Report `Input file not found` and stop
 - Exit code 2: Report `Input file is empty` and stop
-- Exit code 3: Report `Input file has no CMT:/ENDCMT blocks` and stop
+- Exit code 3: Report `Input file has no comment blocks` and stop
 - Exit code 4: Report `Input file is missing required gen-plan sections` and stop
 - Exit code 5: Report `Output directory does not exist or is not writable - please fix it` and stop
 - Exit code 6: Report `QA directory is not writable` and stop
@@ -196,17 +196,32 @@ Track these states while scanning the validated input in document order:
 
 Extraction rules:
 
-1. Recognize `CMT:` as the start marker and `ENDCMT` as the end marker.
-2. Support both inline and multi-line blocks:
+1. Support three comment formats:
+   - Classic: `CMT:` as start marker and `ENDCMT` as end marker
+   - Short tag: `<cmt>` as start marker and `</cmt>` as end marker
+   - Long tag: `<comment>` as start marker and `</comment>` as end marker
+2. Support both inline and multi-line blocks for all formats:
    - Inline: `Text before CMT: comment text ENDCMT text after`
+   - Inline: `Text before <cmt>comment text</cmt> text after`
+   - Inline: `Text before <comment>comment text</comment> text after`
    - Multi-line:
      ```markdown
      CMT:
      comment text
      ENDCMT
      ```
-3. Ignore `CMT:` and `ENDCMT` sequences inside fenced code blocks.
-4. Ignore `CMT:` and `ENDCMT` sequences inside HTML comments.
+     ```markdown
+     <cmt>
+     comment text
+     </cmt>
+     ```
+     ```markdown
+     <comment>
+     comment text
+     </comment>
+     ```
+3. Ignore comment markers inside fenced code blocks.
+4. Ignore comment markers inside HTML comments.
 5. Update `NEAREST_HEADING` whenever a Markdown heading is encountered outside fenced code and HTML comments.
 6. Preserve surrounding non-comment text when removing inline comment blocks from the working plan text.
 7. Assign raw comment IDs in document order as `CMT-1`, `CMT-2`, ... only for non-empty blocks.
@@ -217,7 +232,7 @@ Extraction rules:
 For each non-empty comment block, capture:
 
 - `id` (`CMT-N`)
-- `original_text` exactly as written between `CMT:` and `ENDCMT`
+- `original_text` exactly as written between the comment markers
 - `normalized_text` with surrounding whitespace trimmed
 - `start_line`, `start_column`
 - `end_line`, `end_column`
@@ -230,8 +245,8 @@ For each non-empty comment block, capture:
 
 These are fatal extraction errors:
 
-1. Nested `CMT:` while already inside a comment block
-2. `ENDCMT` encountered while not inside a comment block
+1. Nested comment start marker while already inside a comment block
+2. Comment end marker encountered while not inside a comment block or wrong end marker for the format
 3. End of file reached while still inside a comment block
 
 Every fatal parse error MUST report:
@@ -243,9 +258,9 @@ Every fatal parse error MUST report:
 
 Examples of acceptable messages:
 
-- `Comment parse error: nested CMT block at line 48, column 3 near "## Acceptance Criteria" (context: "CMT: split AC-2...")`
-- `Comment parse error: stray ENDCMT at line 109, column 1 near "## Task Breakdown" (context: "ENDCMT")`
-- `Comment parse error: missing ENDCMT for block opened at line 72, column 5 near "## Dependencies and Sequence"`
+- `Comment parse error: nested comment block at line 48, column 3 near "## Acceptance Criteria" (context: "<cmt>split AC-2...")`
+- `Comment parse error: stray comment end marker at line 109, column 1 near "## Task Breakdown" (context: "</comment>")`
+- `Comment parse error: missing end marker for block opened at line 72, column 5 near "## Dependencies and Sequence"`
 
 ### Outputs from Phase 2
 
@@ -403,7 +418,7 @@ Optional sections that MUST be preserved when present in the input:
 
 ### Refinement Rules
 
-1. Remove every resolved `CMT:` / `ENDCMT` tag and all enclosed comment text from the refined plan.
+1. Remove every resolved comment marker and all enclosed comment text from the refined plan.
 2. Do not add any new top-level schema section.
 3. Preserve `AC-X` / `AC-X.Y` formatting.
 4. Preserve task IDs unless a comment explicitly requests a structural change.
@@ -429,7 +444,7 @@ Rules:
 Before generating the QA document, verify:
 
 1. All required sections are still present
-2. No `CMT:` or `ENDCMT` markers remain
+2. No comment markers remain
 3. Every referenced `AC-*` exists
 4. Every task dependency references an existing task ID or `-`
 5. Every task row has exactly one valid routing tag: `coding` or `analyze`

diff --git a/commands/start-pr-loop.md b/commands/start-pr-loop.md
diff --git a/commands/start-rlcr-loop.md b/commands/start-rlcr-loop.md
@@ -1,6 +1,6 @@
 ---
 description: "Start iterative loop with Codex review"
-argument-hint: "[path/to/plan.md | --plan-file path/to/plan.md] [--max N] [--codex-model MODEL:EFFORT] [--codex-timeout SECONDS] [--track-plan-file] [--push-every-round] [--base-branch BRANCH] [--full-review-round N] [--skip-impl] [--claude-answer-codex] [--agent-teams] [--yolo] [--skip-quiz]"
+argument-hint: "[path/to/plan.md | --plan-file path/to/plan.md] [--max N] [--codex-model MODEL:EFFORT] [--codex-timeout SECONDS] [--track-plan-file] [--push-every-round] [--base-branch BRANCH] [--full-review-round N] [--skip-impl] [--claude-answer-codex] [--agent-teams] [--yolo] [--skip-quiz] [--privacy]"
 allowed-tools:
   - "Bash(${CLAUDE_PLUGIN_ROOT}/scripts/setup-rlcr-loop.sh:*)"
   - "Read"
@@ -127,6 +127,15 @@ This command starts an iterative development loop where:
 7. If code review finds issues (`[P0-9]` markers), you fix them and continue
 8. When no issues are found, the loop ends with a Finalize Phase
 
+## What Is a Round
+
+**One round = the agent believes the entire plan is finished.** A round boundary is when the agent writes a summary and attempts to exit, triggering Codex review. This is the fundamental semantic:
+
+- A round is NOT one task, one milestone, one stage, or one layer of the plan.
+- If the plan has multiple stages or milestones, they are all completed within a single round before writing the round summary.
+- Intermediate progress checks (e.g., verifying a stage before starting the next) should use manual `ask-codex` calls, not round boundaries.
+- Only write `round-N-summary.md` and attempt to exit when you believe ALL tasks in the plan are done.
+
 ## Goal Tracker System
 
 This loop uses a **Goal Tracker** to prevent goal drift across iterations:

diff --git a/config/codex-hooks.json b/config/codex-hooks.json
@@ -0,0 +1,17 @@
+{
+  "description": "Humanize Codex Hooks - Native Stop hooks for RLCR loops",
+  "hooks": {
+    "Stop": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "{{HUMANIZE_RUNTIME_ROOT}}/hooks/loop-codex-stop-hook.sh",
+            "timeout": 7200,
+            "statusMessage": "humanize RLCR stop hook"
+          }
+        ]
+      }
+    ]
+  }
+}
diff --git a/docs/bitlesson.md b/docs/bitlesson.md
@@ -18,6 +18,10 @@ Provider routing is automatic:
 
 If the configured provider binary is missing, the selector falls back to the default Codex model so the loop can still proceed.
 
+On Codex-only installs, Humanize writes `provider_mode: "codex-only"` into the user config.
+When that mode is present, the selector forces BitLesson selection onto the Codex/OpenAI path
+before provider resolution, even if an older default such as `haiku` would otherwise route to Claude.
+
 ## Workflow
 
 Each project keeps its BitLesson knowledge base at `.humanize/bitlesson.md`.

diff --git a/docs/install-for-claude.md b/docs/install-for-claude.md
@@ -68,7 +68,6 @@ Then use:
 
 ```bash
 humanize monitor rlcr   # Monitor RLCR loop
-humanize monitor pr     # Monitor PR loop
 ```
 
 ## Other Install Guides
-Original file line number
+Diff line change
@@ Expand Up / @@ -68,7 +68,6 @@ Then use: @@
     ```bash
     humanize monitor rlcr   # Monitor RLCR loop
-    humanize monitor pr     # Monitor PR loop
     ```
     ## Other Install Guides
@@ Expand Down @@