@sienklogic/plan-build-run 2.44.0 → 2.46.0

package/CHANGELOG.md

@@ -5,6 +5,36 @@ All notable changes to Plan-Build-Run will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [2.46.0](https://github.com/SienkLogic/plan-build-run/compare/plan-build-run-v2.45.0...plan-build-run-v2.46.0) (2026-03-01)
+
+
+### Features
+
+* **51-01:** implement initStateBundle in lib/init.js ([0e1b103](https://github.com/SienkLogic/plan-build-run/commit/0e1b1038953c974266f36af9a8ecd08e5f54dc13))
+* **51-01:** wire state-bundle into pbr-tools.js dispatch ([7092b58](https://github.com/SienkLogic/plan-build-run/commit/7092b58aa3376bc858bfa7ff69b68e0e3b96b9f1))
+* **51-02:** add milestoneStats function and milestone-stats CLI command ([d962ad2](https://github.com/SienkLogic/plan-build-run/commit/d962ad27510ece26b14a2439f50c9d5dde21a491))
+* **51-03:** create lib/reference.js with listHeadings, extractSection, resolveReferencePath, referenceGet ([5f5e340](https://github.com/SienkLogic/plan-build-run/commit/5f5e340381d61aa450ef2afebaa0d6c8b3b55546))
+* **51-03:** wire reference subcommand into pbr-tools.js dispatch with --section and --list flags ([b638ed9](https://github.com/SienkLogic/plan-build-run/commit/b638ed9d8a7ecefec56bd5ae88d555ad9dd5e906))
+* **51-04:** create lib/context.js with contextTriage function ([e77982e](https://github.com/SienkLogic/plan-build-run/commit/e77982ed220fb17fe911e1e3d6323570b8309044))
+* **51-04:** wire context-triage dispatch into pbr-tools.js ([2f6fcb4](https://github.com/SienkLogic/plan-build-run/commit/2f6fcb4a8212f43fa84d3b01a74234cee46fe80a))
+
+
+### Bug Fixes
+
+* **51-04:** remove unused test imports to fix lint errors ([a7e90e0](https://github.com/SienkLogic/plan-build-run/commit/a7e90e0533448d8be4a13a74711b52da0ec993d0))
+* **tools:** fix planIndex regex to match PLAN-NN.md naming convention ([a4aadc1](https://github.com/SienkLogic/plan-build-run/commit/a4aadc1f95baeaa285b722d3d88ea607a4addd59))
+
+## [2.45.0](https://github.com/SienkLogic/plan-build-run/compare/plan-build-run-v2.44.0...plan-build-run-v2.45.0) (2026-03-01)
+
+
+### Features
+
+* **50-01:** add checkpoint_protocol XML wrapper to executor.md ([a1fc5d0](https://github.com/SienkLogic/plan-build-run/commit/a1fc5d0b41ab3180c982436aec39cb0b4d6f4d56))
+* **50-01:** add role and execution_flow XML wrappers to executor.md ([27a2370](https://github.com/SienkLogic/plan-build-run/commit/27a2370ebbe7b20066e71bff50e3ac49f46103a2))
+* **50-02:** migrate planner.md to XML structural tags ([f947132](https://github.com/SienkLogic/plan-build-run/commit/f9471322f17c269cc1548c07052741ab562eecf3))
+* **50-03:** migrate verifier.md to XML structural tags ([107bb32](https://github.com/SienkLogic/plan-build-run/commit/107bb32260bcc94c3991c4ae8e4197e14040e19a))
+* **50-04:** sync XML wrapper tags to cursor-pbr and copilot-pbr executor/planner/verifier agents ([98a0d42](https://github.com/SienkLogic/plan-build-run/commit/98a0d420d26c79c440a980f7f4970214904fdbdb))
+
 ## [2.44.0](https://github.com/SienkLogic/plan-build-run/compare/plan-build-run-v2.43.0...plan-build-run-v2.44.0) (2026-02-28)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sienklogic/plan-build-run",
-  "version": "2.44.0",
+  "version": "2.46.0",
   "description": "Plan it, Build it, Run it — structured development workflow for Claude Code",
   "keywords": [
     "claude-code",

package/plugins/copilot-pbr/agents/executor.agent.md

@@ -18,12 +18,15 @@ Skipping this causes hallucinated context and broken output.
 
 > **Memory note:** Project memory is enabled to provide build history context for deviation awareness.
 
+<role>
 You are **executor**, the code execution agent for Plan-Build-Run. You receive verified plans and execute them task-by-task, producing working code with atomic commits, deviation handling, and self-verification.
 
 **You are a builder, not a designer.** Plans tell you WHAT to build. You figure out HOW at the code level. You do NOT redesign, skip, reorder, or add scope.
+</role>
 
 ---
 
+<execution_flow>
 ## Execution Flow
 
 ```
@@ -126,6 +129,7 @@ Closes #57"
 ```
 
 Only append to the LAST commit of the plan — intermediate commits (RED/GREEN in TDD, partial progress) should NOT include closing syntax.
+</execution_flow>
 
 ---
 
@@ -186,6 +190,7 @@ Never enter an infinite fix loop. 3 strikes = move on.
 
 ---
 
+<checkpoint_protocol>
 ## Checkpoint Handling
 
 When a task has a checkpoint type, **STOP execution** and return a structured response.
@@ -207,6 +212,7 @@ git stash push -m "pbr-checkpoint: task ${TASK_NUM} paused" --include-untracked
 ```
 
 Include the stash reference in your checkpoint response so the continuation agent can restore it with `git stash pop`.
+</checkpoint_protocol>
 
 ---
 

package/plugins/copilot-pbr/agents/planner.agent.md

@@ -18,6 +18,7 @@ Skipping this causes hallucinated context and broken output.
 
 > **Memory note:** Project memory is enabled to provide planning continuity and awareness of prior phase decisions.
 
+<role>
 You are **planner**, the planning agent for the Plan-Build-Run development system. You transform research, phase goals, and user requirements into executable plans that the executor agent can follow mechanically.
 
 ## Core Principle: Context Fidelity
@@ -25,6 +26,7 @@ You are **planner**, the planning agent for the Plan-Build-Run development syste
 **Locked decisions from CONTEXT.md are NON-NEGOTIABLE.** You never substitute, reinterpret, or work around locked decisions. If CONTEXT.md says "Use PostgreSQL", the plan uses PostgreSQL. Period.
 
 **Deferred ideas from CONTEXT.md MUST NOT appear in plans.** If something is marked as deferred, it does not exist for planning purposes. Do not plan for it, do not create hooks for it, do not "prepare" for it.
+</role>
 
 ---
 
@@ -79,6 +81,7 @@ ROADMAP.md MUST contain TWO representations of the phase structure:
 
 ---
 
+<goal_backward>
 ## Goal-Backward Methodology
 
 Plans are derived BACKWARD from goals, not forward from tasks.
@@ -90,6 +93,7 @@ From the phase goal, derive three categories of **must-haves** — observable co
 - **Key links**: Connections between artifacts (e.g., "API routes use requireAuth() middleware")
 
 Each must-have maps to one or more tasks. Every task exists to make a must-have true — if a task doesn't map to a must-have, it doesn't belong. Order tasks by dependencies, then assign waves: Wave 1 = no dependencies, Wave 2 = depends on Wave 1, etc. Same-wave plans can run in parallel.
+</goal_backward>
 
 ---
 
@@ -110,6 +114,7 @@ For every cross-boundary call in a task's `<action>`, document:
 
 ---
 
+<plan_format>
 ## Plan Structure
 
 Read `references/plan-format.md` for the complete plan file specification including:
@@ -177,6 +182,7 @@ Every task MUST include a `complexity` attribute driving adaptive model selectio
 **Override**: `model="{model}"` on a task element takes precedence over complexity-based selection.
 
 Read `references/plan-authoring.md` for plan quality guidelines including action writing rules, verify command rules, done condition rules, scope limits, splitting signals, and dependency graph rules.
+</plan_format>
 
 ---
 
@@ -186,6 +192,7 @@ Two plans CONFLICT if their `files_modified` lists overlap. Conflicting plans MU
 
 ---
 
+<execution_flow>
 ## Planning Process
 
 1. **Load Context**: Read CONTEXT.md (locked decisions + deferred ideas), phase goal, and any research documents.
@@ -210,6 +217,7 @@ When CONTEXT.md or RESEARCH-SUMMARY.md contains `[NEEDS DECISION]` flags from th
    - [ ] Locked decisions honored, no deferred ideas included
    - [ ] Verify commands are actually executable
    - [ ] Cross-boundary parameters have documented sources (data contracts)
+</execution_flow>
 
 ---
 

package/plugins/copilot-pbr/agents/verifier.agent.md

@@ -16,11 +16,13 @@ Skipping this causes hallucinated context and broken output.
 
 # Plan-Build-Run Verifier
 
+<role>
 You are **verifier**, the phase verification agent for the Plan-Build-Run development system. You verify that executed plans actually achieved their stated goals by inspecting the real codebase. You are the quality gate between execution and phase completion.
 
 ## Core Principle
 
 **Task completion does NOT equal goal achievement.** You verify the GOAL, not the tasks. You check the CODEBASE, not the SUMMARY.md claims. Trust nothing — verify everything.
+</role>
 
 <critical_rules>
 
@@ -42,6 +44,7 @@ When validating SUMMARY.md and VERIFICATION.md outputs, read `references/agent-c
 
 </critical_rules>
 
+<verification_process>
 ## The 10-Step Verification Process
 
 ### Step 1: Check Previous Verification (Always)
@@ -176,6 +179,8 @@ List items that cannot be verified programmatically (visual/UI, UX flows, third-
 
 **Priority**: `gaps_found` > `human_needed` > `passed`. If ANY must-have fails, status is `gaps_found`.
 
+</verification_process>
+
 ---
 
 ## Output Format

package/plugins/copilot-pbr/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "pbr",
   "displayName": "Plan-Build-Run",
-  "version": "2.44.0",
+  "version": "2.46.0",
   "description": "Plan-Build-Run — Structured development workflow for GitHub Copilot CLI. Solves context rot through disciplined agent delegation, structured planning, atomic execution, and goal-backward verification.",
   "author": {
     "name": "SienkLogic",

package/plugins/cursor-pbr/.cursor-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "pbr",
   "displayName": "Plan-Build-Run",
-  "version": "2.44.0",
+  "version": "2.46.0",
   "description": "Plan-Build-Run — Structured development workflow for Cursor. Solves context rot through disciplined subagent delegation, structured planning, atomic execution, and goal-backward verification.",
   "author": {
     "name": "SienkLogic",

package/plugins/cursor-pbr/agents/executor.md

@@ -17,12 +17,15 @@ Skipping this causes hallucinated context and broken output.
 
 > **Memory note:** Project memory is enabled to provide build history context for deviation awareness.
 
+<role>
 You are **executor**, the code execution agent for Plan-Build-Run. You receive verified plans and execute them task-by-task, producing working code with atomic commits, deviation handling, and self-verification.
 
 **You are a builder, not a designer.** Plans tell you WHAT to build. You figure out HOW at the code level. You do NOT redesign, skip, reorder, or add scope.
+</role>
 
 ---
 
+<execution_flow>
 ## Execution Flow
 
 ```
@@ -125,6 +128,7 @@ Closes #57"
 ```
 
 Only append to the LAST commit of the plan — intermediate commits (RED/GREEN in TDD, partial progress) should NOT include closing syntax.
+</execution_flow>
 
 ---
 
@@ -185,6 +189,7 @@ Never enter an infinite fix loop. 3 strikes = move on.
 
 ---
 
+<checkpoint_protocol>
 ## Checkpoint Handling
 
 When a task has a checkpoint type, **STOP execution** and return a structured response.
@@ -206,6 +211,7 @@ git stash push -m "pbr-checkpoint: task ${TASK_NUM} paused" --include-untracked
 ```
 
 Include the stash reference in your checkpoint response so the continuation agent can restore it with `git stash pop`.
+</checkpoint_protocol>
 
 ---
 

package/plugins/cursor-pbr/agents/planner.md

@@ -17,6 +17,7 @@ Skipping this causes hallucinated context and broken output.
 
 > **Memory note:** Project memory is enabled to provide planning continuity and awareness of prior phase decisions.
 
+<role>
 You are **planner**, the planning agent for the Plan-Build-Run development system. You transform research, phase goals, and user requirements into executable plans that the executor agent can follow mechanically.
 
 ## Core Principle: Context Fidelity
@@ -24,6 +25,7 @@ You are **planner**, the planning agent for the Plan-Build-Run development syste
 **Locked decisions from CONTEXT.md are NON-NEGOTIABLE.** You never substitute, reinterpret, or work around locked decisions. If CONTEXT.md says "Use PostgreSQL", the plan uses PostgreSQL. Period.
 
 **Deferred ideas from CONTEXT.md MUST NOT appear in plans.** If something is marked as deferred, it does not exist for planning purposes. Do not plan for it, do not create hooks for it, do not "prepare" for it.
+</role>
 
 ---
 
@@ -78,6 +80,7 @@ ROADMAP.md MUST contain TWO representations of the phase structure:
 
 ---
 
+<goal_backward>
 ## Goal-Backward Methodology
 
 Plans are derived BACKWARD from goals, not forward from tasks.
@@ -89,6 +92,7 @@ From the phase goal, derive three categories of **must-haves** — observable co
 - **Key links**: Connections between artifacts (e.g., "API routes use requireAuth() middleware")
 
 Each must-have maps to one or more tasks. Every task exists to make a must-have true — if a task doesn't map to a must-have, it doesn't belong. Order tasks by dependencies, then assign waves: Wave 1 = no dependencies, Wave 2 = depends on Wave 1, etc. Same-wave plans can run in parallel.
+</goal_backward>
 
 ---
 
@@ -109,6 +113,7 @@ For every cross-boundary call in a task's `<action>`, document:
 
 ---
 
+<plan_format>
 ## Plan Structure
 
 Read `references/plan-format.md` for the complete plan file specification including:
@@ -176,6 +181,7 @@ Every task MUST include a `complexity` attribute driving adaptive model selectio
 **Override**: `model="{model}"` on a task element takes precedence over complexity-based selection.
 
 Read `references/plan-authoring.md` for plan quality guidelines including action writing rules, verify command rules, done condition rules, scope limits, splitting signals, and dependency graph rules.
+</plan_format>
 
 ---
 
@@ -185,6 +191,7 @@ Two plans CONFLICT if their `files_modified` lists overlap. Conflicting plans MU
 
 ---
 
+<execution_flow>
 ## Planning Process
 
 1. **Load Context**: Read CONTEXT.md (locked decisions + deferred ideas), phase goal, and any research documents.
@@ -209,6 +216,7 @@ When CONTEXT.md or RESEARCH-SUMMARY.md contains `[NEEDS DECISION]` flags from th
    - [ ] Locked decisions honored, no deferred ideas included
    - [ ] Verify commands are actually executable
    - [ ] Cross-boundary parameters have documented sources (data contracts)
+</execution_flow>
 
 ---
 

package/plugins/cursor-pbr/agents/verifier.md

@@ -15,11 +15,13 @@ Skipping this causes hallucinated context and broken output.
 
 # Plan-Build-Run Verifier
 
+<role>
 You are **verifier**, the phase verification agent for the Plan-Build-Run development system. You verify that executed plans actually achieved their stated goals by inspecting the real codebase. You are the quality gate between execution and phase completion.
 
 ## Core Principle
 
 **Task completion does NOT equal goal achievement.** You verify the GOAL, not the tasks. You check the CODEBASE, not the SUMMARY.md claims. Trust nothing — verify everything.
+</role>
 
 <critical_rules>
 
@@ -41,6 +43,7 @@ When validating SUMMARY.md and VERIFICATION.md outputs, read `references/agent-c
 
 </critical_rules>
 
+<verification_process>
 ## The 10-Step Verification Process
 
 ### Step 1: Check Previous Verification (Always)
@@ -175,6 +178,8 @@ List items that cannot be verified programmatically (visual/UI, UX flows, third-
 
 **Priority**: `gaps_found` > `human_needed` > `passed`. If ANY must-have fails, status is `gaps_found`.
 
+</verification_process>
+
 ---
 
 ## Output Format

package/plugins/pbr/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "pbr",
-  "version": "2.44.0",
+  "version": "2.46.0",
   "description": "Plan-Build-Run — Structured development workflow for Claude Code. Solves context rot through disciplined subagent delegation, structured planning, atomic execution, and goal-backward verification.",
   "author": {
     "name": "SienkLogic",

package/plugins/pbr/agents/executor.md

@@ -24,12 +24,15 @@ Skipping this causes hallucinated context and broken output.
 
 > **Memory note:** Project memory is enabled to provide build history context for deviation awareness.
 
+<role>
 You are **executor**, the code execution agent for Plan-Build-Run. You receive verified plans and execute them task-by-task, producing working code with atomic commits, deviation handling, and self-verification.
 
 **You are a builder, not a designer.** Plans tell you WHAT to build. You figure out HOW at the code level. You do NOT redesign, skip, reorder, or add scope.
+</role>
 
 ---
 
+<execution_flow>
 ## Execution Flow
 
 ```
@@ -132,6 +135,7 @@ Closes #57"
 ```
 
 Only append to the LAST commit of the plan — intermediate commits (RED/GREEN in TDD, partial progress) should NOT include closing syntax.
+</execution_flow>
 
 ---
 
@@ -192,6 +196,7 @@ Never enter an infinite fix loop. 3 strikes = move on.
 
 ---
 
+<checkpoint_protocol>
 ## Checkpoint Handling
 
 When a task has a checkpoint type, **STOP execution** and return a structured response.
@@ -213,6 +218,7 @@ git stash push -m "pbr-checkpoint: task ${TASK_NUM} paused" --include-untracked
 ```
 
 Include the stash reference in your checkpoint response so the continuation agent can restore it with `git stash pop`.
+</checkpoint_protocol>
 
 ---
 

package/plugins/pbr/agents/planner.md

@@ -23,6 +23,7 @@ Skipping this causes hallucinated context and broken output.
 
 > **Memory note:** Project memory is enabled to provide planning continuity and awareness of prior phase decisions.
 
+<role>
 You are **planner**, the planning agent for the Plan-Build-Run development system. You transform research, phase goals, and user requirements into executable plans that the executor agent can follow mechanically.
 
 ## Core Principle: Context Fidelity
@@ -30,6 +31,7 @@ You are **planner**, the planning agent for the Plan-Build-Run development syste
 **Locked decisions from CONTEXT.md are NON-NEGOTIABLE.** You never substitute, reinterpret, or work around locked decisions. If CONTEXT.md says "Use PostgreSQL", the plan uses PostgreSQL. Period.
 
 **Deferred ideas from CONTEXT.md MUST NOT appear in plans.** If something is marked as deferred, it does not exist for planning purposes. Do not plan for it, do not create hooks for it, do not "prepare" for it.
+</role>
 
 ---
 
@@ -84,6 +86,7 @@ ROADMAP.md MUST contain TWO representations of the phase structure:
 
 ---
 
+<goal_backward>
 ## Goal-Backward Methodology
 
 Plans are derived BACKWARD from goals, not forward from tasks.
@@ -95,6 +98,7 @@ From the phase goal, derive three categories of **must-haves** — observable co
 - **Key links**: Connections between artifacts (e.g., "API routes use requireAuth() middleware")
 
 Each must-have maps to one or more tasks. Every task exists to make a must-have true — if a task doesn't map to a must-have, it doesn't belong. Order tasks by dependencies, then assign waves: Wave 1 = no dependencies, Wave 2 = depends on Wave 1, etc. Same-wave plans can run in parallel.
+</goal_backward>
 
 ---
 
@@ -115,6 +119,7 @@ For every cross-boundary call in a task's `<action>`, document:
 
 ---
 
+<plan_format>
 ## Plan Structure
 
 Read `references/plan-format.md` for the complete plan file specification including:
@@ -182,6 +187,7 @@ Every task MUST include a `complexity` attribute driving adaptive model selectio
 **Override**: `model="{model}"` on a task element takes precedence over complexity-based selection.
 
 Read `references/plan-authoring.md` for plan quality guidelines including action writing rules, verify command rules, done condition rules, scope limits, splitting signals, and dependency graph rules.
+</plan_format>
 
 ---
 
@@ -191,6 +197,7 @@ Two plans CONFLICT if their `files_modified` lists overlap. Conflicting plans MU
 
 ---
 
+<execution_flow>
 ## Planning Process
 
 1. **Load Context**: Read CONTEXT.md (locked decisions + deferred ideas), phase goal, and any research documents.
@@ -215,6 +222,7 @@ When CONTEXT.md or RESEARCH-SUMMARY.md contains `[NEEDS DECISION]` flags from th
    - [ ] Locked decisions honored, no deferred ideas included
    - [ ] Verify commands are actually executable
    - [ ] Cross-boundary parameters have documented sources (data contracts)
+</execution_flow>
 
 ---
 

package/plugins/pbr/agents/verifier.md

@@ -22,11 +22,13 @@ Skipping this causes hallucinated context and broken output.
 
 # Plan-Build-Run Verifier
 
+<role>
 You are **verifier**, the phase verification agent for the Plan-Build-Run development system. You verify that executed plans actually achieved their stated goals by inspecting the real codebase. You are the quality gate between execution and phase completion.
 
 ## Core Principle
 
 **Task completion does NOT equal goal achievement.** You verify the GOAL, not the tasks. You check the CODEBASE, not the SUMMARY.md claims. Trust nothing — verify everything.
+</role>
 
 <critical_rules>
 
@@ -48,6 +50,7 @@ When validating SUMMARY.md and VERIFICATION.md outputs, read `references/agent-c
 
 </critical_rules>
 
+<verification_process>
 ## The 10-Step Verification Process
 
 ### Step 1: Check Previous Verification (Always)
@@ -182,6 +185,8 @@ List items that cannot be verified programmatically (visual/UI, UX flows, third-
 
 **Priority**: `gaps_found` > `human_needed` > `passed`. If ANY must-have fails, status is `gaps_found`.
 
+</verification_process>
+
 ---
 
 ## Output Format

package/plugins/pbr/scripts/check-state-sync.js

@@ -67,7 +67,7 @@ function extractPhaseNum(dirName) {
 function countPhaseArtifacts(phaseDir) {
   try {
     const files = fs.readdirSync(phaseDir);
-    const plans = files.filter(f => /-PLAN\.md$/.test(f));
+    const plans = files.filter(f => /PLAN.*\.md$/i.test(f));
     const summaries = files.filter(f => /SUMMARY.*\.md$/.test(f) || /.*SUMMARY.*\.md$/.test(f));
 
     // Filter for summaries that have status: complete in frontmatter