bigpowers 2.68.6 → 2.70.0

package/.pi/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bigpowers",
-  "version": "2.68.6",
+  "version": "2.70.0",
   "description": "75 skills — 73 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers",
   "keywords": [
     "pi-package"

package/.pi/prompts/enforce-first.md

@@ -14,19 +14,11 @@ This skill is typically invoked internally by `develop-tdd` during the test-writ
 ## Modes
 
 - Default: full F.I.R.S.T audit (all 5 criteria)
-- --quick: Check F (Fast), I (Independent), and S (Self-Validating) only. Used by build-epic step 6 as a mechanical gate after audit-code. Skips R (Repeatable) and T (Timely) which require contextual judgment.
+- --quick: Check Fast, Independent, and Self-Validating criteria only (per CONVENTIONS.md §Tests). Used by build-epic step 6 as a mechanical gate after audit-code. Skips Repeatable and Timely which require contextual judgment.
 
 ## The F.I.R.S.T Rubric
 
-The canonical F.I.R.S.T definition lives in CONVENTIONS.md §Tests. This skill operationalizes each criterion:
-
-- **F (Fast):** No real I/O; suite target < 30s
-- **I (Independent):** No shared state; any order, same result
-- **R (Repeatable):** No machine deps; passes identically on CI and locally
-- **S (Self-Validating):** Assertions, not console.log; descriptive failures
-- **T (Timely):** Written with code; regression tests for every fix
-
-For the full rubric with checklists and fix patterns, see CONVENTIONS.md §Tests.
+See CONVENTIONS.md §Tests for the canonical F.I.R.S.T rubric definition, checklists, and fix patterns.
 
 ## Applying the rubric
 

package/.pi/prompts/investigate-bug.md

@@ -120,5 +120,7 @@ After writing the bug file, print a one-line summary of the root cause and sugge
 
 ## References
 
+<!-- story: e35s10 -->
+
 - [Feathers' Seams & Characterization Tests](../../docs/references/feathers.md) — seam types, characterization tests, and the legacy code change algorithm
 - [Fowler's Code Smells](../../docs/references/fowler.md) — identifying structural problems by smell before investigating

package/.pi/prompts/plan-refactor.md

@@ -78,6 +78,8 @@ After writing `specs/REFACTOR_LATEST.md`, suggest running `kickoff-branch` next
 
 ## References
 
+<!-- story: e35s10 -->
+
 - [Fowler's Refactoring Catalog](../../docs/references/fowler.md) — canonical refactoring vocabulary and code-smell taxonomy
 - [Beck's Tidy First?](../../docs/references/kent-beck.md) — structural change before behavioral change
 

package/.pi/skills/enforce-first/SKILL.md

@@ -16,19 +16,11 @@ This skill is typically invoked internally by `develop-tdd` during the test-writ
 ## Modes
 
 - Default: full F.I.R.S.T audit (all 5 criteria)
-- --quick: Check F (Fast), I (Independent), and S (Self-Validating) only. Used by build-epic step 6 as a mechanical gate after audit-code. Skips R (Repeatable) and T (Timely) which require contextual judgment.
+- --quick: Check Fast, Independent, and Self-Validating criteria only (per CONVENTIONS.md §Tests). Used by build-epic step 6 as a mechanical gate after audit-code. Skips Repeatable and Timely which require contextual judgment.
 
 ## The F.I.R.S.T Rubric
 
-The canonical F.I.R.S.T definition lives in CONVENTIONS.md §Tests. This skill operationalizes each criterion:
-
-- **F (Fast):** No real I/O; suite target < 30s
-- **I (Independent):** No shared state; any order, same result
-- **R (Repeatable):** No machine deps; passes identically on CI and locally
-- **S (Self-Validating):** Assertions, not console.log; descriptive failures
-- **T (Timely):** Written with code; regression tests for every fix
-
-For the full rubric with checklists and fix patterns, see CONVENTIONS.md §Tests.
+See CONVENTIONS.md §Tests for the canonical F.I.R.S.T rubric definition, checklists, and fix patterns.
 
 ## Applying the rubric
 

package/.pi/skills/investigate-bug/SKILL.md

@@ -122,5 +122,7 @@ After writing the bug file, print a one-line summary of the root cause and sugge
 
 ## References
 
+<!-- story: e35s10 -->
+
 - [Feathers' Seams & Characterization Tests](../../docs/references/feathers.md) — seam types, characterization tests, and the legacy code change algorithm
 - [Fowler's Code Smells](../../docs/references/fowler.md) — identifying structural problems by smell before investigating

package/.pi/skills/plan-refactor/SKILL.md

@@ -80,6 +80,8 @@ After writing `specs/REFACTOR_LATEST.md`, suggest running `kickoff-branch` next
 
 ## References
 
+<!-- story: e35s10 -->
+
 - [Fowler's Refactoring Catalog](../../docs/references/fowler.md) — canonical refactoring vocabulary and code-smell taxonomy
 - [Beck's Tidy First?](../../docs/references/kent-beck.md) — structural change before behavioral change
 

package/CHANGELOG.md

@@ -1,3 +1,17 @@
+# [2.70.0](https://github.com/danielvm-git/bigpowers/compare/v2.69.0...v2.70.0) (2026-07-06)
+
+
+### Features
+
+* **specs:** add e50 Codex CLI reach epic and update tech stack ([5df68a2](https://github.com/danielvm-git/bigpowers/commit/5df68a278af02212a008b363a604c6935a15e21a))
+
+# [2.69.0](https://github.com/danielvm-git/bigpowers/compare/v2.68.6...v2.69.0) (2026-07-06)
+
+
+### Features
+
+* **specs:** add e50 Codex CLI reach epic from issue [#52](https://github.com/danielvm-git/bigpowers/issues/52) ([029efdf](https://github.com/danielvm-git/bigpowers/commit/029efdfdae944e1f1e5cf805cf77e5c2d8a86588))
+
 ## [2.68.6](https://github.com/danielvm-git/bigpowers/compare/v2.68.5...v2.68.6) (2026-07-06)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bigpowers",
-  "version": "2.68.6",
+  "version": "2.70.0",
   "description": "73 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers",
   "main": "index.js",
   "scripts": {

package/skills/enforce-first/SKILL.md

@@ -16,19 +16,11 @@ This skill is typically invoked internally by `develop-tdd` during the test-writ
 ## Modes
 
 - Default: full F.I.R.S.T audit (all 5 criteria)
-- --quick: Check F (Fast), I (Independent), and S (Self-Validating) only. Used by build-epic step 6 as a mechanical gate after audit-code. Skips R (Repeatable) and T (Timely) which require contextual judgment.
+- --quick: Check Fast, Independent, and Self-Validating criteria only (per CONVENTIONS.md §Tests). Used by build-epic step 6 as a mechanical gate after audit-code. Skips Repeatable and Timely which require contextual judgment.
 
 ## The F.I.R.S.T Rubric
 
-The canonical F.I.R.S.T definition lives in CONVENTIONS.md §Tests. This skill operationalizes each criterion:
-
-- **F (Fast):** No real I/O; suite target < 30s
-- **I (Independent):** No shared state; any order, same result
-- **R (Repeatable):** No machine deps; passes identically on CI and locally
-- **S (Self-Validating):** Assertions, not console.log; descriptive failures
-- **T (Timely):** Written with code; regression tests for every fix
-
-For the full rubric with checklists and fix patterns, see CONVENTIONS.md §Tests.
+See CONVENTIONS.md §Tests for the canonical F.I.R.S.T rubric definition, checklists, and fix patterns.
 
 ## Applying the rubric
 

package/skills/investigate-bug/SKILL.md

@@ -122,6 +122,8 @@ After writing the bug file, print a one-line summary of the root cause and sugge
 
 ## References
 
+<!-- story: e35s10 -->
+
 - [Feathers' Seams & Characterization Tests](../../docs/references/feathers.md) — seam types, characterization tests, and the legacy code change algorithm
 - [Fowler's Code Smells](../../docs/references/fowler.md) — identifying structural problems by smell before investigating
 

package/skills/plan-refactor/SKILL.md

@@ -80,6 +80,8 @@ After writing `specs/REFACTOR_LATEST.md`, suggest running `kickoff-branch` next
 
 ## References
 
+<!-- story: e35s10 -->
+
 - [Fowler's Refactoring Catalog](../../docs/references/fowler.md) — canonical refactoring vocabulary and code-smell taxonomy
 - [Beck's Tidy First?](../../docs/references/kent-beck.md) — structural change before behavioral change
 

package/skills-lock.json

@@ -103,7 +103,7 @@
     },
     "enforce-first": {
       "description": "Apply the F.I.R.S.T test quality rubric (per CONVENTIONS.md §Tests) to a test suite or individual tests. Use when develop-tdd is writing tests, when test quality needs to be checked, or when user mentions F.I.R.S.T or \"test quality\".",
-      "sha256": "20f717d0496ca20f",
+      "sha256": "64cde2c5f741c77f",
       "path": "skills/enforce-firstSKILL.md"
     },
     "evolve-skill": {
@@ -158,7 +158,7 @@
     },
     "investigate-bug": {
       "description": "Investigate a bug or issue by exploring the codebase to find root cause, then write a TDD-based fix plan to specs/bugs/BUG-*.md. Use when user reports a bug, wants to investigate a problem, mentions \"triage\", or wants to plan a fix.",
-      "sha256": "548aaef63bc914c8",
+      "sha256": "b842fd329d1f7741",
       "path": "skills/investigate-bugSKILL.md"
     },
     "kickoff-branch": {
@@ -198,7 +198,7 @@
     },
     "plan-refactor": {
       "description": "Create a detailed refactor plan with tiny commits via user interview, then save it as specs/REFACTOR_LATEST.md. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.",
-      "sha256": "53769bafec01a9e6",
+      "sha256": "c418c850806e2f16",
       "path": "skills/plan-refactorSKILL.md"
     },
     "plan-release": {