prizmkit 1.1.1 → 1.1.4

package/bundled/dev-pipeline/templates/agent-prompts/critic-code-challenge.md

@@ -0,0 +1,13 @@
+"Read {{CRITIC_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
+**MODE: Code Challenge**
+1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` — Implementation Log section shows what Dev changed.
+2. Read `.prizm-docs/root.prizm` and relevant module docs for RULES/PATTERNS.
+3. Read the actual source files changed (from Implementation Log).
+4. Read comparable existing source files in the same module for style comparison.
+5. Read test files created/modified (from Implementation Log) — evaluate test quality:
+   - Coverage adequacy: Do tests cover all code paths modified? Target: {{COVERAGE_TARGET}}%
+   - Test brittleness: Do tests pass consistently (not flaky)? Check Implementation Log for test re-runs
+   - Edge case handling: Are boundary conditions tested? Are error paths tested?
+6. Challenge code integration quality: style fit, robustness, existing code cohesion, hidden impact.
+7. Challenge test quality: coverage, brittleness, edge case handling.
+Write `.prizmkit/specs/{{FEATURE_SLUG}}/challenge-report.md` (overwrite) with findings (or 'No significant challenges')."

package/bundled/dev-pipeline/templates/agent-prompts/critic-plan-challenge.md

@@ -0,0 +1,7 @@
+"Read {{CRITIC_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
+**MODE: Plan Challenge**
+1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has project context, Section 4 has file manifest.
+2. Read `.prizm-docs/root.prizm` and relevant L1/L2 docs for affected modules.
+3. Read existing source files in the modules this plan touches.
+4. Challenge plan.md against the project's existing architecture, patterns, and style.
+Write `.prizmkit/specs/{{FEATURE_SLUG}}/challenge-report.md` with findings (or 'No significant challenges')."

package/bundled/dev-pipeline/templates/agent-prompts/dev-fix.md

@@ -0,0 +1,7 @@
+"Read {{DEV_SUBAGENT_PATH}}. Fix NEEDS_FIXES issues for feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}).
+1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` — '## Review Notes' section contains structured Fix Instructions with exact steps.
+2. Follow Fix Instructions in order (respect Depends On / Blocks dependencies). Each FIX-N has: Root Cause, Fix Strategy, Code Guidance, and Verification criteria.
+3. After each fix, run the Verification command listed in that FIX-N to confirm it works.
+4. Run `{{TEST_CMD}}` to verify no regressions.
+5. Append fix summary to '## Implementation Log' in context-snapshot.md.
+6. Do NOT execute any git commands."

package/bundled/dev-pipeline/templates/agent-prompts/dev-implement.md

@@ -0,0 +1,27 @@
+"Read {{DEV_SUBAGENT_PATH}}. Implement feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}).
+**IMPORTANT**: Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has Prizm Context (TRAPS/RULES), Section 4 has File Manifest with paths and interfaces.
+⚠️ DO NOT re-read source files already listed in Section 4 File Manifest unless you need implementation detail beyond the interface summary.
+1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` for full context.
+2. Run `/prizmkit-implement` to execute the tasks in plan.md. Run tests with: `{{TEST_CMD}}`. Known baseline failures (pre-existing, not your fault): `{{BASELINE_FAILURES}}`.
+3. If plan.md has more than 5 tasks: run `/compact` after completing every 3 tasks to manage context budget. If `/compact` is unavailable, continue without it.
+4. After implement completes, verify the '## Implementation Log' section was written to context-snapshot.md.
+
+## Acceptance Criteria Verification
+
+Update the AC Verification Checklist in context-snapshot.md by marking each item [x] as you verify it:
+- As you complete each task, verify the corresponding acceptance criteria
+- Check the AC Checklist at the end of implementation
+- All [ ] must become [x] — if any AC remains unverified, the feature is incomplete
+- Document any AC that cannot be verified due to test failures
+
+## Test Failure Recovery (Max 2 Fix Rounds)
+
+If tests fail during implementation:
+- **Round 1**: Analyze failure (code bug vs. brittle test vs. environment), apply fix, re-run tests
+- **Round 2 (if still failing)**: Try alternate fix approach, re-run tests
+- **After Round 2**: Document failure in Implementation Log with root cause, category, and fix attempted
+- **Do NOT block completion** if unable to resolve — only NEW REGRESSIONS (not in baseline) require fixing
+- **If any AC cannot be verified** due to test failure: the feature is incomplete, add to failure notes
+
+4. Do NOT execute any git commands (no git add/commit/reset/push).
+Do NOT exit until all tasks are [x], the '## Implementation Log' section is written, and AC Verification Checklist is 100% complete in context-snapshot.md."

package/bundled/dev-pipeline/templates/agent-prompts/dev-resume.md

@@ -0,0 +1,5 @@
+"Read {{DEV_SUBAGENT_PATH}}. You are resuming implementation of feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}).
+1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` — Section 4 has File Manifest, 'Implementation Log' (if present) shows what was already done.
+2. Run `git diff HEAD` to see actual code changes already made.
+3. Run `/prizmkit-implement` to complete the remaining `[ ]` tasks. Run tests with: `{{TEST_CMD}}`.
+4. Do NOT execute any git commands."

package/bundled/dev-pipeline/templates/agent-prompts/reviewer-analyze.md

@@ -0,0 +1,5 @@
+"Read {{REVIEWER_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
+1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has project context, Section 4 has file manifest.
+2. Run prizmkit-analyze: cross-check `spec.md` and `plan.md` (including Tasks section) for consistency.
+3. Before flagging CRITICAL or HIGH issues, read the relevant source files listed in the File Manifest to verify.
+Report: CRITICAL, HIGH, MEDIUM issues found (or 'No issues found')."

package/bundled/dev-pipeline/templates/agent-prompts/reviewer-review.md

@@ -0,0 +1,12 @@
+"Read {{REVIEWER_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
+**IMPORTANT**: Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST.
+1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md`:
+   - Section 3: Prizm Context (RULES, PATTERNS to check against)
+   - Section 4: File Manifest (original file structure)
+   - '## Implementation Log': what Dev changed, key decisions, discoveries
+   - '## Acceptance Criteria Verification Checklist': verify all items are [x]
+2. **AC Verification Gate**: Check that AC Verification Checklist shows ALL criteria marked [x]. If any [ ] remains, return verdict NEEDS_FIXES with message "AC Verification incomplete: [list unmet criteria]"
+3. Run prizmkit-code-review (both phases): Phase 1 diagnostic review (spec compliance, code quality, correctness), then Phase 2 fix strategy formulation for any findings. Read ONLY files listed in Implementation Log for diagnosis; MAY read additional files for impact analysis.
+4. Run the full test suite using `{{TEST_CMD}}` — **ONLY if the Implementation Log does not already confirm all tests passing**. If Implementation Log states tests passed, trust it and skip the re-run. When running tests: `{{TEST_CMD}} 2>&1 | tee /tmp/review-test-out.txt | tail -20`, then grep `/tmp/review-test-out.txt` for details — do NOT re-run the suite multiple times. Write and execute integration tests covering all user stories from spec.md.
+5. Write structured '## Review Notes' to context-snapshot.md with Fix Instructions (Root Cause, Impact, Fix Strategy, Code Guidance, Verification for each finding) and Re-Review Expectations.
+Report verdict: PASS, PASS_WITH_WARNINGS, or NEEDS_FIXES."

package/bundled/dev-pipeline/templates/bootstrap-tier1.md

@@ -25,7 +25,7 @@ You are the **session orchestrator**. Implement Feature {{FEATURE_ID}}: "{{FEATU
 
 ### Project Brief
 
-> Distilled summary of the project's key requirements and design decisions, captured during planning. When your feature implementation touches any of these key points, ensure alignment.
+> Product ideas checklist from planning. Lines marked [x] are already implemented. When your feature touches any [ ] item, ensure alignment. After implementation, mark relevant items [x] and append the key file/directory paths.
 
 {{PROJECT_BRIEF}}
 
@@ -152,6 +152,8 @@ $TEST_CMD 2>&1 | tee /tmp/test-baseline.txt | tail -20
 - Runs tests using `TEST_CMD` after each task
 - Writes '## Implementation Log' to `context-snapshot.md`
 
+**3b-compact.** Context management — if plan.md has more than 5 tasks, run `/compact` after completing every 3 tasks during implementation. This prevents context window exhaustion in long sessions. If `/compact` is not available (non-Claude CLI), skip this step.
+
 **3c.** After implement completes, verify:
 1. All tasks in plan.md are `[x]`
 2. Run the full test suite to ensure nothing is broken
@@ -160,6 +162,32 @@ $TEST_CMD 2>&1 | tee /tmp/test-baseline.txt | tail -20
 
 **CP-2**: All acceptance criteria met, all tests pass.
 
+### Test Failure Recovery Protocol
+
+When tests fail during Phase 3:
+
+1. **Analyze failure output**:
+   - Identify root cause (code bug vs. test brittleness vs. environment issue)
+   - Check if baseline already recorded this failure
+
+2. **Categorize and fix** (max 2 rounds):
+   - **Pre-existing baseline failure**: Expected, record as acceptable
+   - **New regression**: Fix the code and re-run tests
+   - **Brittle test**: Fix the test or environment
+   - **Environment issue**: Fix setup and re-run
+
+3. **Recovery limit**:
+   - Max 2 fix attempts per failing test
+   - After 2 rounds, if still failing: document in Implementation Log with root cause
+   - **Do NOT block commit** if unable to resolve
+
+4. **Failure documentation**:
+   - Test name, root cause, category, fix attempted, final status
+   - If any AC cannot be verified due to test failure: feature is incomplete
+
+**Context-Aware Optimization**: If Implementation Log already confirms "all tests passing," skip full suite re-run.
+
+
 {{IF_BROWSER_INTERACTION}}
 ### Phase 3.5: Browser Verification (playwright-cli) — MANDATORY
 
@@ -172,8 +200,9 @@ You MUST execute this phase. Do NOT skip it. Do NOT mark it as completed without
 4. If the page requires authentication, use playwright-cli to register a test user and log in first
 
 **Verification**:
-5. Use `playwright-cli` to open `{{BROWSER_URL}}`, then verify:
+5. Use `playwright-cli snapshot` on `{{BROWSER_URL}}` to discover actual element refs, then verify these goals:
    {{BROWSER_VERIFY_STEPS}}
+   Decide the concrete playwright-cli actions (click, fill, assert, etc.) yourself based on the snapshot output and your knowledge of the implemented code. The goals above describe WHAT to verify — you determine HOW.
 6. Take a final screenshot for evidence
 
 **Cleanup (REQUIRED — you started it, you stop it)**:
@@ -258,6 +287,8 @@ git status --short
 ```
 Working tree MUST be clean after this step. If any feature-related files remain, stage them into the SAME commit via `git add <file> && git commit --amend --no-edit`, do NOT create a separate commit.
 
+**Exception**: `session-summary.md` in the artifact directory is a local cross-session artifact generated by `/prizmkit-committer` — it is NOT committed to git. Ignore it in the clean-tree check.
+
 ## Critical Paths
 
 | Resource | Path |

package/bundled/dev-pipeline/templates/bootstrap-tier2.md

@@ -25,7 +25,7 @@ You are the **session orchestrator**. Implement Feature {{FEATURE_ID}}: "{{FEATU
 
 ### Project Brief
 
-> Distilled summary of the project's key requirements and design decisions, captured during planning. When your feature implementation touches any of these key points, ensure alignment.
+> Product ideas checklist from planning. Lines marked [x] are already implemented. When your feature touches any [ ] item, ensure alignment. After implementation, mark relevant items [x] and append the key file/directory paths.
 
 {{PROJECT_BRIEF}}
 
@@ -162,7 +162,7 @@ Before proceeding past CP-1, verify:
 
 ### Phase 3: Analyze — Reviewer Subagent
 
-Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false).
+Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", mode="plan", run_in_background=false).
 
 Prompt:
 > "Read {{REVIEWER_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
@@ -185,7 +185,7 @@ ls {{CRITIC_SUBAGENT_PATH}} 2>/dev/null && echo "CRITIC:READY" || echo "CRITIC:M
 ```
 If CRITIC:MISSING — skip Phase 3.5 entirely and proceed to Phase 4. Log: "Critic agent not installed — skipping Plan Challenge."
 
-Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", run_in_background=false).
+Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", mode="plan", run_in_background=false).
 
 Prompt:
 > "Read {{CRITIC_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
@@ -214,9 +214,10 @@ Prompt:
 > **IMPORTANT**: Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has Prizm Context (TRAPS/RULES), Section 4 has File Manifest with paths and interfaces.
 > ⚠️ DO NOT re-read source files already listed in Section 4 File Manifest unless you need implementation detail beyond the interface summary.
 > 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` for full context.
-> 2. Run `/prizmkit-implement` to execute the tasks in plan.md. Use `TEST_CMD=<TEST_CMD>` for testing. Baseline failures: `BASELINE_FAILURES=<BASELINE_FAILURES>`.
-> 3. After implement completes, verify the '## Implementation Log' section was written to context-snapshot.md.
-> 4. Do NOT execute any git commands (no git add/commit/reset/push).
+> 2. Run `/prizmkit-implement` to execute the tasks in plan.md. Run tests with: `{{TEST_CMD}}`. Known baseline failures (pre-existing, not your fault): `{{BASELINE_FAILURES}}`.
+> 3. If plan.md has more than 5 tasks: run `/compact` after completing every 3 tasks to manage context budget. If `/compact` is unavailable, continue without it.
+> 4. After implement completes, verify the '## Implementation Log' section was written to context-snapshot.md.
+> 5. Do NOT execute any git commands (no git add/commit/reset/push).
 > Do NOT exit until all tasks are [x] and the '## Implementation Log' section is written in context-snapshot.md."
 
 Wait for Dev to return. All tasks must be `[x]`, tests pass.
@@ -237,7 +238,7 @@ ls {{CRITIC_SUBAGENT_PATH}} 2>/dev/null && echo "CRITIC:READY" || echo "CRITIC:M
 ```
 If CRITIC:MISSING — skip Phase 4.5 entirely and proceed to Phase 5. Log: "Critic agent not installed — skipping Code Challenge."
 
-Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", run_in_background=false).
+Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", mode="plan", run_in_background=false).
 
 Prompt:
 > "Read {{CRITIC_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
@@ -267,7 +268,7 @@ Prompt:
 >    - Section 4: File Manifest (original file structure)
 >    - '## Implementation Log': what Dev changed, key decisions, discoveries
 > 2. Run prizmkit-code-review (both phases): Phase 1 diagnostic review (spec compliance, code quality, correctness), then Phase 2 fix strategy formulation for any findings. Read ONLY files listed in Implementation Log for diagnosis; MAY read additional files for impact analysis.
-> 3. Run the full test suite — **ONLY if the Implementation Log does not already confirm all tests passing**. If the log states tests passed, trust it and skip the re-run. When running: `$TEST_CMD 2>&1 | tee /tmp/review-test-out.txt | tail -20`, then grep the file for details — do NOT re-run the suite multiple times. Write and execute integration tests covering all user stories.
+> 3. Run the full test suite using `{{TEST_CMD}}` — **ONLY if the Implementation Log does not already confirm all tests passing**. If the log states tests passed, trust it and skip the re-run. When running: `{{TEST_CMD}} 2>&1 | tee /tmp/review-test-out.txt | tail -20`, then grep the file for details — do NOT re-run the suite multiple times. Write and execute integration tests covering all user stories.
 > 4. Write structured '## Review Notes' to context-snapshot.md with Fix Instructions (Root Cause, Impact, Fix Strategy, Code Guidance, Verification for each finding) and Re-Review Expectations.
 > Report verdict: PASS, PASS_WITH_WARNINGS, or NEEDS_FIXES."
 
@@ -296,8 +297,9 @@ You MUST execute this phase. Do NOT skip it. Do NOT mark it as completed without
 4. If the page requires authentication, use playwright-cli to register a test user and log in first
 
 **Verification**:
-5. Use `playwright-cli` to open `{{BROWSER_URL}}`, then verify:
+5. Use `playwright-cli snapshot` on `{{BROWSER_URL}}` to discover actual element refs, then verify these goals:
    {{BROWSER_VERIFY_STEPS}}
+   Decide the concrete playwright-cli actions (click, fill, assert, etc.) yourself based on the snapshot output and your knowledge of the implemented code. The goals above describe WHAT to verify — you determine HOW.
 6. Take a final screenshot for evidence
 
 **Cleanup (REQUIRED — you started it, you stop it)**:
@@ -382,6 +384,8 @@ git status --short
 ```
 Working tree MUST be clean after this step. If any feature-related files remain, stage them into the SAME commit via `git add <file> && git commit --amend --no-edit`, do NOT create a separate commit.
 
+**Exception**: `session-summary.md` in the artifact directory is a local cross-session artifact generated by `/prizmkit-committer` — it is NOT committed to git. Ignore it in the clean-tree check.
+
 ## Critical Paths
 
 | Resource | Path |

package/bundled/dev-pipeline/templates/bootstrap-tier3.md

@@ -25,7 +25,7 @@ You are the **session orchestrator**. Implement Feature {{FEATURE_ID}}: "{{FEATU
 
 ### Project Brief
 
-> Distilled summary of the project's key requirements and design decisions, captured during planning. When your feature implementation touches any of these key points, ensure alignment.
+> Product ideas checklist from planning. Lines marked [x] are already implemented. When your feature touches any [ ] item, ensure alignment. After implementation, mark relevant items [x] and append the key file/directory paths.
 
 {{PROJECT_BRIEF}}
 
@@ -199,7 +199,7 @@ Before proceeding past CP-1, verify:
 
 ### Phase 3: Analyze — Reviewer Agent
 
-Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false).
+Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", mode="plan", run_in_background=false).
 
 Prompt:
 > "Read {{REVIEWER_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
@@ -226,7 +226,7 @@ If CRITIC:MISSING — skip Phase 3.5 entirely and proceed to Phase 4. Log: "Crit
 
 **If {{CRITIC_COUNT}} = 1 → Single Critic** (skip to CP-2.5 after this):
 
-Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", run_in_background=false).
+Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", mode="plan", run_in_background=false).
 
 Prompt:
 > "Read {{CRITIC_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
@@ -239,7 +239,7 @@ Prompt:
 
 **If {{CRITIC_COUNT}} = 3 → Multi-Critic Voting** (skip Single Critic above):
 
-Spawn 3 Critic agents sequentially (each with run_in_background=false), each with a different focus lens:
+Spawn 3 Critic agents sequentially (each with mode="plan", run_in_background=false), each with a different focus lens:
 
 Critic-A prompt (append to base prompt above):
 > "**Focus Lens: Architecture & Scalability.** Prioritize: architectural pattern fit, scalability implications, over-engineering risks, component boundary design.
@@ -279,9 +279,10 @@ Prompt:
 > **IMPORTANT**: Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has Prizm Context (TRAPS/RULES), Section 4 has File Manifest with paths and interfaces.
 > ⚠️ DO NOT re-read source files already listed in Section 4 File Manifest unless you need implementation detail beyond the interface summary.
 > 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` for full context.
-> 2. Run `/prizmkit-implement` to execute the tasks in plan.md. Use `TEST_CMD=<TEST_CMD>` for testing. Baseline failures: `BASELINE_FAILURES=<BASELINE_FAILURES>`.
-> 3. After implement completes, verify the '## Implementation Log' section was written to context-snapshot.md.
-> 4. Do NOT execute any git commands (no git add/commit/reset/push).
+> 2. Run `/prizmkit-implement` to execute the tasks in plan.md. Run tests with: `{{TEST_CMD}}`. Known baseline failures (pre-existing, not your fault): `{{BASELINE_FAILURES}}`.
+> 3. If plan.md has more than 5 tasks: run `/compact` after completing every 3 tasks to manage context budget. If `/compact` is unavailable, continue without it.
+> 4. After implement completes, verify the '## Implementation Log' section was written to context-snapshot.md.
+> 5. Do NOT execute any git commands (no git add/commit/reset/push).
 > Do NOT exit until all tasks are [x] and the '## Implementation Log' section is written in context-snapshot.md."
 
 **Gate Check — Implementation Log**:
@@ -297,7 +298,7 @@ Wait for Dev to return. **If Dev times out before all tasks are `[x]`**:
    > "Read {{DEV_SUBAGENT_PATH}}. You are resuming implementation of feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}).
    > 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` — Section 4 has File Manifest, 'Implementation Log' (if present) shows what was already done.
    > 2. Run `git diff HEAD` to see actual code changes already made.
-   > 3. Run `/prizmkit-implement` to complete the remaining `[ ]` tasks. Use `TEST_CMD=<TEST_CMD>` for testing.
+   > 3. Run `/prizmkit-implement` to complete the remaining `[ ]` tasks. Run tests with: `{{TEST_CMD}}`.
    > 4. Do NOT execute any git commands."
 3. Max 2 recovery retries. After 2 failures, orchestrator implements remaining tasks directly.
 
@@ -312,7 +313,7 @@ ls {{CRITIC_SUBAGENT_PATH}} 2>/dev/null && echo "CRITIC:READY" || echo "CRITIC:M
 ```
 If CRITIC:MISSING — skip Phase 4.5 entirely and proceed to Phase 5. Log: "Critic agent not installed — skipping Code Challenge."
 
-Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", run_in_background=false).
+Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", mode="plan", run_in_background=false).
 
 Prompt:
 > "Read {{CRITIC_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
@@ -342,7 +343,7 @@ Prompt:
 >    - Section 4: File Manifest (original file structure)
 >    - '## Implementation Log': what Dev changed, key decisions, discoveries
 > 2. Run prizmkit-code-review (both phases): Phase 1 diagnostic review (spec compliance, code quality, correctness), then Phase 2 fix strategy formulation for any findings. Read ONLY files listed in Implementation Log for diagnosis; MAY read additional files for impact analysis.
-> 3. Run the full test suite using `TEST_CMD=<TEST_CMD>` — **ONLY if the Implementation Log does not already confirm all tests passing**. If Implementation Log states tests passed, trust it and skip the re-run. When running tests: `$TEST_CMD 2>&1 | tee /tmp/review-test-out.txt | tail -20`, then grep `/tmp/review-test-out.txt` for details — do NOT re-run the suite multiple times. Write and execute integration tests covering all user stories from spec.md.
+> 3. Run the full test suite using `{{TEST_CMD}}` — **ONLY if the Implementation Log does not already confirm all tests passing**. If Implementation Log states tests passed, trust it and skip the re-run. When running tests: `{{TEST_CMD}} 2>&1 | tee /tmp/review-test-out.txt | tail -20`, then grep `/tmp/review-test-out.txt` for details — do NOT re-run the suite multiple times. Write and execute integration tests covering all user stories from spec.md.
 > 4. Write structured '## Review Notes' to context-snapshot.md with Fix Instructions (Root Cause, Impact, Fix Strategy, Code Guidance, Verification for each finding) and Re-Review Expectations.
 > Report verdict: PASS, PASS_WITH_WARNINGS, or NEEDS_FIXES."
 
@@ -360,7 +361,7 @@ If GATE:MISSING — send message to Reviewer (re-spawn if needed): "Write the '#
   > 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` — '## Review Notes' section contains structured Fix Instructions with exact steps.
   > 2. Follow Fix Instructions in order (respect Depends On / Blocks dependencies). Each FIX-N has: Root Cause, Fix Strategy, Code Guidance, and Verification criteria.
   > 3. After each fix, run the Verification command listed in that FIX-N to confirm it works.
-  > 4. Use `TEST_CMD=<TEST_CMD>` to verify no regressions.
+  > 4. Run `{{TEST_CMD}}` to verify no regressions.
   > 5. Append fix summary to '## Implementation Log' in context-snapshot.md.
   > 6. Do NOT execute any git commands."
   Then re-run Review (max 3 rounds).
@@ -379,8 +380,9 @@ You MUST execute this phase. Do NOT skip it. Do NOT mark it as completed without
 4. If the page requires authentication, use playwright-cli to register a test user and log in first
 
 **Verification**:
-5. Use `playwright-cli` to open `{{BROWSER_URL}}`, then verify:
+5. Use `playwright-cli snapshot` on `{{BROWSER_URL}}` to discover actual element refs, then verify these goals:
    {{BROWSER_VERIFY_STEPS}}
+   Decide the concrete playwright-cli actions (click, fill, assert, etc.) yourself based on the snapshot output and your knowledge of the implemented code. The goals above describe WHAT to verify — you determine HOW.
 6. Take a final screenshot for evidence
 
 **Cleanup (REQUIRED — you started it, you stop it)**:
@@ -475,6 +477,8 @@ git status --short
 ```
 Working tree MUST be clean after this step. If any feature-related files remain, stage them into the SAME commit via `git add <file> && git commit --amend --no-edit`, do NOT create a separate commit.
 
+**Exception**: `session-summary.md` in the artifact directory is a local cross-session artifact generated by `/prizmkit-committer` — it is NOT committed to git. Ignore it in the clean-tree check.
+
 ## Critical Paths
 
 | Resource | Path |

package/bundled/dev-pipeline/templates/bugfix-bootstrap-prompt.md

@@ -67,6 +67,19 @@ You are the **bug fix session orchestrator**. Fix Bug {{BUG_ID}}: "{{BUG_TITLE}}
 
 **IMPORTANT**: Only 2 artifact files per bug, NEVER more. This is a fixed convention.
 
+## Workflow Checkpoint System
+
+A checkpoint file tracks your progress through this workflow:
+
+**Path**: `{{CHECKPOINT_PATH}}`
+
+**Rules**:
+1. **Before each step**: Read `workflow-checkpoint.json`, verify the previous step has `status: "completed"` or `status: "skipped"`. If not, complete it first.
+2. **Starting a step**: Update the current step to `status: "in_progress"`.
+3. **After each step completes**: Update the step to `status: "completed"`. Verify JSON is valid after writing.
+4. **On failure**: Set the step to `status: "failed"` and halt.
+5. **On resume**: Steps already `"completed"` are skipped. Start from the first `"pending"` or `"in_progress"` step.
+
 ## Execution Instructions
 
 **YOU are the orchestrator. Execute each phase by spawning the appropriate team agent with run_in_background=false.**
@@ -92,7 +105,7 @@ Reference `{{TEAM_CONFIG_PATH}}` for agent definitions:
 
 - Spawn Dev agent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false)
   Prompt: "Read {{DEV_SUBAGENT_PATH}}. For bug {{BUG_ID}} ('{{BUG_TITLE}}'):
-  1. Run `/prizmkit-tool-error-triage` with the bug description and error source
+  1. Triage the bug: classify error type (Runtime/Network/Auth/Data/Logic/Config/External), check `.prizm-docs/` TRAPS for known patterns, trace call chain to identify root cause
   2. Check `.prizm-docs/` TRAPS sections for matching known issues
   3. Classify: category, subcategory, root cause (confirmed or suspected), affected files
   4. Assess impact: which modules are affected, what is the blast radius
@@ -109,6 +122,7 @@ Reference `{{TEAM_CONFIG_PATH}}` for agent definitions:
   "
 - **Wait for Dev to return**
 - **CP-BF-1**: `.prizmkit/bugfix/{{BUG_ID}}/fix-plan.md` exists
+- **Checkpoint update**: set step `bug-diagnosis` to `"completed"` in `{{CHECKPOINT_PATH}}`
 
 **DECISION GATE — Fast Path Check**:
 - If severity is LOW or MEDIUM, AND root cause is obvious (high confidence), AND fix is < 10 lines:
@@ -130,8 +144,7 @@ Reference `{{TEAM_CONFIG_PATH}}` for agent definitions:
 - Spawn Dev agent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false)
   Prompt: "Read {{DEV_SUBAGENT_PATH}}. For bug {{BUG_ID}}:
   1. Read the fix plan from `.prizmkit/bugfix/{{BUG_ID}}/fix-plan.md`
-  2. Run `/prizmkit-tool-bug-reproducer` with the bug description and triage results
-  3. Generate a minimal reproduction test that FAILS with current code
+  2. Generate a minimal reproduction test (API: curl sequence; UI: step-by-step; Logic: unit test; Data: seed+query) that FAILS with current code
   4. Execute the reproduction test to confirm it fails
   5. If reproduction fails, refine and retry (max 2 rounds)
   6. Report: reproduction test path, red/green status, investigation pointers
@@ -142,6 +155,7 @@ Reference `{{TEAM_CONFIG_PATH}}` for agent definitions:
   - Write session-status.json with status="partial", errors=["reproduction_failed"]
   - Set bug status to `needs_info` and STOP
 - **CP-BF-2**: Reproduction test exists and FAILS
+- **Checkpoint update**: set step `bug-reproduce` to `"completed"` in `{{CHECKPOINT_PATH}}`
 
 ---
 
@@ -159,11 +173,13 @@ Reference `{{TEAM_CONFIG_PATH}}` for agent definitions:
      - Do NOT refactor — fix the bug only
   4. Run the reproduction test → MUST PASS
   5. Run the module's test suite → MUST PASS (no regression)
-  6. If fix fails after 3 rounds, report detailed analysis
+  6. If the fix involves multiple files or steps: run `/compact` after completing the core fix and before running the full test suite, to free context budget. If `/compact` is unavailable, continue without it.
+  7. If fix fails after 3 rounds, report detailed analysis
   "
 - **Wait for Dev to return**
 - If fix fails after 3 rounds: escalate to user, write status="failed"
 - **CP-BF-3**: Reproduction test passes, module tests pass
+- **Checkpoint update**: set step `bug-fix` to `"completed"` in `{{CHECKPOINT_PATH}}`
 
 ---
 
@@ -186,6 +202,7 @@ Reference `{{TEAM_CONFIG_PATH}}` for agent definitions:
 - **Wait for Reviewer to return**
 - If NEEDS_FIXES: return to Phase 3 for refinement following Fix Instructions (max 2 review rounds)
 - **CP-BF-4**: Code review passes, all tests green
+- **Checkpoint update**: set step `prizmkit-code-review` to `"completed"` in `{{CHECKPOINT_PATH}}`
 
 {{IF_VERIFICATION_MANUAL_OR_HYBRID}}
 **MANUAL VERIFICATION GATE**:
@@ -223,6 +240,7 @@ Reference `{{TEAM_CONFIG_PATH}}` for agent definitions:
   - Acceptance Criteria Verification (checklist with pass/fail for each criterion)
 
 - **CP-BF-5**: Commit recorded, fix-report.md written, TRAPS updated (if applicable)
+- **Checkpoint update**: set steps `prizmkit-committer` and `bug-report` to `"completed"` in `{{CHECKPOINT_PATH}}`
 
 ### Step 3: Report Session Status
 

package/bundled/dev-pipeline/templates/feature-list-schema.json

@@ -126,7 +126,7 @@
               },
               "verify_steps": {
                 "type": "array",
-                "description": "Ordered playwright-cli commands to execute for verification",
+                "description": "Verification goals describing WHAT to verify (not HOW). Pipeline AI decides concrete playwright-cli actions at runtime based on actual code and snapshot.",
                 "items": {
                   "type": "string"
                 }

package/bundled/dev-pipeline/templates/refactor-list-schema.json

@@ -0,0 +1,159 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "Dev-Pipeline Refactor List",
+  "description": "Schema for refactor-list.json — standardized input for the Refactor Pipeline",
+  "type": "object",
+  "required": ["$schema", "project_name", "refactors"],
+  "properties": {
+    "$schema": {
+      "type": "string",
+      "const": "dev-pipeline-refactor-list-v1"
+    },
+    "project_name": {
+      "type": "string",
+      "minLength": 1
+    },
+    "project_description": {
+      "type": "string"
+    },
+    "created_at": {
+      "type": "string",
+      "format": "date-time"
+    },
+    "created_by": {
+      "type": "string"
+    },
+    "refactors": {
+      "type": "array",
+      "minItems": 1,
+      "items": {
+        "type": "object",
+        "required": [
+          "id", "title", "description", "scope", "type",
+          "priority", "complexity", "behavior_preservation",
+          "acceptance_criteria", "dependencies", "status"
+        ],
+        "properties": {
+          "id": {
+            "type": "string",
+            "pattern": "^R-\\d{3}$",
+            "description": "Refactor ID, format R-001, R-002..."
+          },
+          "title": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Refactor title — brief description of the change"
+          },
+          "description": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Detailed description: what is being refactored and why"
+          },
+          "scope": {
+            "type": "object",
+            "description": "Files and modules affected by this refactor",
+            "properties": {
+              "files": {
+                "type": "array",
+                "items": { "type": "string" },
+                "description": "File paths affected by this refactor"
+              },
+              "modules": {
+                "type": "array",
+                "items": { "type": "string" },
+                "description": "Module names affected by this refactor"
+              }
+            }
+          },
+          "type": {
+            "type": "string",
+            "enum": ["extract", "rename", "restructure", "simplify", "decouple", "migrate"],
+            "description": "extract=extract-function/module; rename=rename-symbols; restructure=move/reorganize; simplify=reduce-complexity; decouple=remove-dependencies; migrate=tech-migration"
+          },
+          "priority": {
+            "type": "string",
+            "enum": ["critical", "high", "medium", "low"],
+            "description": "Refactor priority. Pipeline processes critical before high before medium before low; within same level, array order determines sequence."
+          },
+          "complexity": {
+            "type": "string",
+            "enum": ["low", "medium", "high"],
+            "description": "Estimated complexity of the refactor"
+          },
+          "behavior_preservation": {
+            "type": "object",
+            "required": ["strategy"],
+            "description": "Strategy for ensuring no behavior changes",
+            "properties": {
+              "strategy": {
+                "type": "string",
+                "enum": ["test-gate", "snapshot", "manual"],
+                "description": "test-gate=existing-tests-must-pass; snapshot=before/after-snapshot-comparison; manual=human-verification"
+              },
+              "existing_tests": {
+                "type": "boolean",
+                "description": "Whether existing tests cover the refactored code"
+              },
+              "new_tests_needed": {
+                "type": "array",
+                "items": { "type": "string" },
+                "description": "New tests that should be written before refactoring"
+              }
+            }
+          },
+          "acceptance_criteria": {
+            "type": "array",
+            "minItems": 1,
+            "items": { "type": "string" },
+            "description": "Conditions that must be met for the refactor to be considered complete"
+          },
+          "dependencies": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "pattern": "^R-\\d{3}$"
+            },
+            "description": "IDs of refactors that must be completed before this one"
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "pending",
+              "in_progress",
+              "completed",
+              "failed",
+              "skipped"
+            ],
+            "description": "Refactor status"
+          },
+          "model": {
+            "type": "string",
+            "description": "AI model ID for this refactor. Overrides $MODEL env var."
+          },
+          "estimated_lines": {
+            "type": "integer",
+            "description": "Estimated number of lines affected by this refactor"
+          }
+        }
+      }
+    },
+    "global_context": {
+      "type": "object",
+      "description": "Global context for all refactors in this batch",
+      "properties": {
+        "tech_stack": { "type": "string" },
+        "language": { "type": "string" },
+        "runtime": { "type": "string" },
+        "frontend_framework": { "type": "string" },
+        "frontend_styling": { "type": "string" },
+        "backend_framework": { "type": "string" },
+        "database": { "type": "string" },
+        "orm": { "type": "string" },
+        "testing_strategy": { "type": "string" },
+        "bundler": { "type": "string" },
+        "project_type": { "type": "string" },
+        "ci_pipeline": { "type": "string" }
+      }
+    }
+  }
+}

package/bundled/dev-pipeline/templates/sections/ac-verification-checklist.md

@@ -0,0 +1,13 @@
+## Acceptance Criteria Verification Checklist
+
+This checklist is auto-generated from feature.acceptance_criteria. The Dev agent must verify each criterion and mark as complete:
+
+{{AC_CHECKLIST}}
+
+**Verification Gates**:
+1. All [x] items confirmed by Dev agent during implementation
+2. Reviewer agent verifies checklist is 100% complete before clearing PASS verdict
+3. Any unmet AC ([ ] remaining) marks feature as incomplete
+
+---
+