ShaheerKhawaja · ShaheerKhawaja · Apr 15, 2026 · Apr 15, 2026
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -37,15 +37,13 @@ jobs:
 
       - name: Run tests (0 failures required)
         run: |
-          OUTPUT=$(bun test 2>&1) || true
-          echo "$OUTPUT"
-          FAIL_COUNT=$(echo "$OUTPUT" | grep -oE '[0-9]+ fail' | head -1 | grep -oE '[0-9]+' || echo "0")
-          PASS_COUNT=$(echo "$OUTPUT" | grep -oE '[0-9]+ pass' | head -1 | grep -oE '[0-9]+' || echo "0")
-          echo "Tests: $PASS_COUNT pass, $FAIL_COUNT fail"
-          if [ "${FAIL_COUNT:-0}" -gt 0 ]; then
+          # Use bun test's exit code directly — more reliable than parsing grep output.
+          # Previous grep-based approach matched "0 fail" in per-file summaries and missed overall failures.
+          if ! bun test; then
             echo "::error::Test failures detected. 0 failures required."
             exit 1
           fi
+          echo "All tests passed."
 
   lint:
     runs-on: ubuntu-latest

diff --git a/codex-overrides/refine.md b/codex-overrides/refine.md
@@ -17,6 +17,9 @@ Use this as the Codex-first refinement workflow. It should inspect flagged outpu
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/refine.md`
+
 1. load the flagged outputs or pending signals
 2. critique the weaknesses directly
 3. refine in focused passes

diff --git a/codex-overrides/retro.md b/codex-overrides/retro.md
@@ -17,6 +17,9 @@ Use this as the Codex-first retrospective workflow. It should look back across r
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/retro.md`
+
 1. inspect recent commits and artifacts
 2. summarize wins, misses, and repeated pain points
 3. connect those patterns to concrete improvements

diff --git a/codex-overrides/tdd.md b/codex-overrides/tdd.md
@@ -17,6 +17,9 @@ Use this as the Codex-first TDD workflow. It should enforce red-green-refactor a
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/tdd.md`
+
 1. write the failing test first
 2. confirm the failure
 3. implement the minimum change to pass

diff --git a/codex-overrides/writing-plans.md b/codex-overrides/writing-plans.md
@@ -17,6 +17,9 @@ Use this as the Codex-first execution-planning workflow. It should convert an ap
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/writing-plans.md`
+
 1. restate the approved scope
 2. break the work into tasks
 3. map dependencies and risk

diff --git a/codex-skills/productionos-refine/SKILL.md b/codex-skills/productionos-refine/SKILL.md
@@ -19,6 +19,9 @@ Use this as the Codex-first refinement workflow. It should inspect flagged outpu
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/refine.md`
+
 1. load the flagged outputs or pending signals
 2. critique the weaknesses directly
 3. refine in focused passes

diff --git a/codex-skills/productionos-retro/SKILL.md b/codex-skills/productionos-retro/SKILL.md
@@ -19,6 +19,9 @@ Use this as the Codex-first retrospective workflow. It should look back across r
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/retro.md`
+
 1. inspect recent commits and artifacts
 2. summarize wins, misses, and repeated pain points
 3. connect those patterns to concrete improvements

diff --git a/codex-skills/productionos-tdd/SKILL.md b/codex-skills/productionos-tdd/SKILL.md
@@ -19,6 +19,9 @@ Use this as the Codex-first TDD workflow. It should enforce red-green-refactor a
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/tdd.md`
+
 1. write the failing test first
 2. confirm the failure
 3. implement the minimum change to pass

diff --git a/codex-skills/productionos-writing-plans/SKILL.md b/codex-skills/productionos-writing-plans/SKILL.md
@@ -19,6 +19,9 @@ Use this as the Codex-first execution-planning workflow. It should convert an ap
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/writing-plans.md`
+
 1. restate the approved scope
 2. break the work into tasks
 3. map dependencies and risk

diff --git a/skills/refine/SKILL.md b/skills/refine/SKILL.md
@@ -17,6 +17,9 @@ Use this as the Codex-first refinement workflow. It should inspect flagged outpu
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/refine.md`
+
 1. load the flagged outputs or pending signals
 2. critique the weaknesses directly
 3. refine in focused passes

diff --git a/skills/retro/SKILL.md b/skills/retro/SKILL.md
@@ -17,6 +17,9 @@ Use this as the Codex-first retrospective workflow. It should look back across r
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/retro.md`
+
 1. inspect recent commits and artifacts
 2. summarize wins, misses, and repeated pain points
 3. connect those patterns to concrete improvements

diff --git a/skills/tdd/SKILL.md b/skills/tdd/SKILL.md
@@ -17,6 +17,9 @@ Use this as the Codex-first TDD workflow. It should enforce red-green-refactor a
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/tdd.md`
+
 1. write the failing test first
 2. confirm the failure
 3. implement the minimum change to pass

diff --git a/skills/writing-plans/SKILL.md b/skills/writing-plans/SKILL.md
@@ -17,6 +17,9 @@ Use this as the Codex-first execution-planning workflow. It should convert an ap
 
 ## Codex Workflow
 
+Source references:
+- `.claude/commands/writing-plans.md`
+
 1. restate the approved scope
 2. break the work into tasks
 3. map dependencies and risk