prizmkit 1.1.1 → 1.1.4

package/bundled/dev-pipeline/templates/sections/checkpoint-system.md

@@ -0,0 +1,36 @@
+## Workflow Checkpoint System
+
+A checkpoint file tracks your progress through this workflow:
+
+**Path**: `{{CHECKPOINT_PATH}}`
+
+### Rules
+
+1. **Before each skill**: Read `workflow-checkpoint.json`, verify the previous step has `status: "completed"` or `status: "skipped"`. If it is still `"pending"` or `"in_progress"`, you MUST complete it first before moving on.
+
+2. **Starting a skill**: Update the current step to `status: "in_progress"`.
+
+3. **After each skill completes**: Update the current step to `status: "completed"`. Then immediately re-read the file to verify the JSON is valid. If the read fails, re-write the file with correct JSON.
+
+4. **On failure**: Set the step to `status: "failed"` and continue to the next step if possible, or halt and write failure-log.md.
+
+5. **On session exit**: The checkpoint file reflects your actual progress. Do NOT manually set future steps to "completed".
+
+### Checkpoint Update Pattern
+
+After completing each skill:
+
+1. Read `{{CHECKPOINT_PATH}}`
+2. Update the current step `"status": "completed"`
+3. Update the next step `"status": "in_progress"`
+4. Write the updated JSON back to `{{CHECKPOINT_PATH}}`
+5. Verify: `python3 -c "import json; json.load(open('{{CHECKPOINT_PATH}}'))"` — if this fails, re-write
+
+### Resume Behavior
+
+**Checkpoint is the primary source of truth for resume.** On retry sessions:
+
+1. Read `workflow-checkpoint.json` — steps already `"completed"` or `"skipped"` are skipped
+2. Start from the first `"pending"` or `"in_progress"` step
+3. If `failure-log.md` exists, read it for diagnostic context (why the previous session failed, what approach to try differently) — but do NOT use it to determine which step to resume from
+4. If `workflow-checkpoint.json` is missing or corrupted, fall back to `failure-log.md` + the resume phase as the legacy mechanism

package/bundled/dev-pipeline/templates/sections/failure-log-check.md

@@ -1,4 +1,4 @@
-**Check for previous failure log:**
+**Check for previous failure log** (diagnostic context only — do NOT use to determine resume point):
 ```bash
 cat .prizmkit/specs/{{FEATURE_SLUG}}/failure-log.md 2>/dev/null || echo "NO_PREVIOUS_FAILURE"
 ```
@@ -6,3 +6,4 @@ If failure-log.md exists:
 - Read ROOT_CAUSE and SUGGESTION — adjust your approach accordingly
 - Read DISCOVERED_TRAPS — if any are genuine, inject into .prizm-docs/ during the commit phase retrospective
 - Do NOT delete failure-log.md until this session completes all phases and commits successfully
+- **Note**: The resume point is determined by `workflow-checkpoint.json`, not by failure-log.md

package/bundled/dev-pipeline/templates/sections/feature-context.md

@@ -9,7 +9,7 @@
 
 ### 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}}
 

package/bundled/dev-pipeline/templates/sections/phase-analyze-agent.md

@@ -1,15 +1,19 @@
 ### Analyze — Reviewer Subagent
 
-Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false).
+**Spawn Agent**:
+| Parameter | Value |
+|-----------|-------|
+| subagent_type | prizm-dev-team-reviewer |
+| mode | plan |
+| run_in_background | false |
 
-Prompt:
-> "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 `plan.md` (including Tasks section) against feature description and acceptance criteria 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')."
+**Prompt**:
+> {{AGENT_PROMPT_REVIEWER_ANALYZE}}
 
 Wait for Reviewer to return.
 - If CRITICAL issues found: fix them yourself — read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` for full project context. Fix ONLY the listed CRITICAL issues in plan.md. Then re-run analyze (max 1 round).
 
 **CP-2**: No CRITICAL issues.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `prizmkit-analyze` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-analyze-full.md

@@ -1,15 +1,19 @@
 ### Analyze — Reviewer Agent
 
-Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false).
+**Spawn Agent**:
+| Parameter | Value |
+|-----------|-------|
+| subagent_type | prizm-dev-team-reviewer |
+| mode | plan |
+| run_in_background | false |
 
-Prompt:
-> "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')."
+**Prompt**:
+> {{AGENT_PROMPT_REVIEWER_ANALYZE}}
 
 Wait for Reviewer to return.
 - If CRITICAL issues found: fix them yourself — read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` for full project context. Fix ONLY the listed CRITICAL issues in spec.md/plan.md. Then re-run analyze (max 1 round).
 
 **CP-2**: No CRITICAL issues.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `prizmkit-analyze` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-browser-verification.md

@@ -9,8 +9,9 @@ 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)**:
@@ -29,3 +30,6 @@ You MUST execute this phase. Do NOT skip it. Do NOT mark it as completed without
    ```
 
 If verification fails, log the failure details but continue to commit. Failures do NOT block the commit, but you MUST attempt verification and MUST clean up the dev server.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `browser-verification` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-commit-full.md

@@ -34,3 +34,6 @@ This single commit includes: feature code + tests + .prizm-docs/ updates. Do NOT
 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.
+
+
+**Checkpoint update**: After `/prizmkit-retrospective` completes, update `workflow-checkpoint.json` — set step `prizmkit-retrospective` to `"completed"`. After `/prizmkit-committer` completes, set step `prizmkit-committer` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-commit.md

@@ -24,3 +24,6 @@ This single commit includes: feature code + tests + .prizm-docs/ updates. Do NOT
 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.
+
+
+**Checkpoint update**: After `/prizmkit-retrospective` completes, update `workflow-checkpoint.json` — set step `prizmkit-retrospective` to `"completed"`. After `/prizmkit-committer` completes, set step `prizmkit-committer` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-context-snapshot-agent-suffix.md

@@ -12,3 +12,6 @@
 
      ### Known TRAPS (from .prizm-docs/)
      - <trap entries extracted from L1/L2 docs>
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `context-snapshot` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-context-snapshot-lite-suffix.md

@@ -1,3 +1,6 @@
    - **Section 3 — Prizm Context**: content of root.prizm and relevant L1/L2 docs
    - **Section 4 — Existing Source Files**: **full verbatim content** of each related file in fenced code blocks (with `### path/to/file` heading and line count). Include ALL files needed for implementation and review — downstream phases read this section instead of re-reading individual source files
    - **Section 5 — Existing Tests**: full content of related test files as code block
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `context-snapshot` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-critic-code.md

@@ -6,19 +6,20 @@ ls {{CRITIC_SUBAGENT_PATH}} 2>/dev/null && echo "CRITIC:READY" || echo "CRITIC:M
 ```
 If CRITIC:MISSING — skip this phase entirely and proceed. Log: "Critic agent not installed — skipping Code Challenge."
 
-Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", run_in_background=false).
+**Spawn Agent**:
+| Parameter | Value |
+|-----------|-------|
+| subagent_type | prizm-dev-team-critic |
+| mode | plan |
+| run_in_background | false |
 
-Prompt:
-> "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. Challenge code integration quality: style fit, robustness, existing code cohesion, hidden impact.
-> Write `.prizmkit/specs/{{FEATURE_SLUG}}/challenge-report.md` (overwrite) with findings (or 'No significant challenges')."
+**Prompt**:
+> {{AGENT_PROMPT_CRITIC_CODE_CHALLENGE}}
 
 Wait for Critic to return.
 - Read challenge-report.md. For items marked CRITICAL/HIGH: spawn Dev to fix, then proceed to Review.
 
 **CP-3.5**: Code challenges reviewed and resolved.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `critic-code-review` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-critic-plan-full.md

@@ -10,20 +10,19 @@ If CRITIC:MISSING — skip this phase entirely and proceed. Log: "Critic agent n
 
 **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 Agent**:
+| Parameter | Value |
+|-----------|-------|
+| subagent_type | prizm-dev-team-critic |
+| mode | plan |
+| run_in_background | false |
 
-Prompt:
-> "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')."
+**Prompt**:
+> {{AGENT_PROMPT_CRITIC_PLAN_CHALLENGE}}
 
 **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.
@@ -43,3 +42,6 @@ After all critics return, read all 3 reports:
 - Max 1 plan revision round.
 
 **CP-2.5**: Plan challenges reviewed and resolved.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `critic-plan-review` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-critic-plan.md

@@ -6,19 +6,21 @@ ls {{CRITIC_SUBAGENT_PATH}} 2>/dev/null && echo "CRITIC:READY" || echo "CRITIC:M
 ```
 If CRITIC:MISSING — skip this phase entirely and proceed. Log: "Critic agent not installed — skipping Plan Challenge."
 
-Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", run_in_background=false).
+**Spawn Agent**:
+| Parameter | Value |
+|-----------|-------|
+| subagent_type | prizm-dev-team-critic |
+| mode | plan |
+| run_in_background | false |
 
-Prompt:
-> "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')."
+**Prompt**:
+> {{AGENT_PROMPT_CRITIC_PLAN_CHALLENGE}}
 
 Wait for Critic to return.
 - Read challenge-report.md. For items marked CRITICAL/HIGH: decide whether to adjust plan.md or document why the plan stands.
 - Max 1 plan revision round.
 
 **CP-2.5**: Plan challenges reviewed and resolved.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `critic-plan-review` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-deploy-verification.md

@@ -34,3 +34,6 @@ Deploy verification does NOT block the commit, but you MUST attempt it.
 4. Record smoke test results in `## Deploy Verification` section
 
 If the project cannot be started locally (e.g., requires external services, databases, credentials), skip the smoke test and note why.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `deploy-verification` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-implement-agent.md

@@ -2,17 +2,14 @@
 
 **Build artifacts rule** (passed to Dev): After any build/compile command (`go build`, `npm run build`, `tsc`, etc.), ensure the output binary or build directory is in `.gitignore`. Never commit compiled binaries, build output, or generated artifacts.
 
-Spawn Dev subagent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false).
+**Spawn Agent**:
+| Parameter | Value |
+|-----------|-------|
+| subagent_type | prizm-dev-team-dev |
+| run_in_background | false |
 
-Prompt:
-> "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. 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).
-> Do NOT exit until all tasks are [x] and the '## Implementation Log' section is written in context-snapshot.md."
+**Prompt**:
+> {{AGENT_PROMPT_DEV_IMPLEMENT}}
 
 Wait for Dev to return. All tasks must be `[x]`, tests pass.
 
@@ -22,3 +19,6 @@ After Dev agent returns, verify the Implementation Log was written:
 grep -q "## Implementation Log" .prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md && echo "GATE:PASS" || echo "GATE:MISSING"
 ```
 If GATE:MISSING — send message to Dev (re-spawn if needed): "Write the '## Implementation Log' section to context-snapshot.md before I can proceed to review. Include: files changed/created, key decisions, deviations from plan, notable discoveries."
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `prizmkit-implement` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-implement-full.md

@@ -9,17 +9,14 @@ grep -c '^\- \[ \]' .prizmkit/specs/{{FEATURE_SLUG}}/plan.md 2>/dev/null || true
 - If result is `0` (all tasks already `[x]`) → **SKIP this phase**, go directly to Review. Do NOT spawn Dev.
 - If result is non-zero → spawn Dev agent below.
 
-Spawn Dev agent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false).
-
-Prompt:
-> "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. 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).
-> Do NOT exit until all tasks are [x] and the '## Implementation Log' section is written in context-snapshot.md."
+**Spawn Agent**:
+| Parameter | Value |
+|-----------|-------|
+| subagent_type | prizm-dev-team-dev |
+| run_in_background | false |
+
+**Prompt**:
+> {{AGENT_PROMPT_DEV_IMPLEMENT}}
 
 **Gate Check — Implementation Log**:
 After Dev agent returns, verify the Implementation Log was written:
@@ -31,11 +28,10 @@ If GATE:MISSING — send message to Dev (re-spawn if needed): "Write the '## Imp
 Wait for Dev to return. **If Dev times out before all tasks are `[x]`**:
 1. Check progress: `grep -c '^\- \[ \]' .prizmkit/specs/{{FEATURE_SLUG}}/plan.md`
 2. If any tasks remain: re-spawn Dev with this recovery prompt:
-   > "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.
-   > 4. Do NOT execute any git commands."
+   > {{AGENT_PROMPT_DEV_RESUME}}
 3. Max 2 recovery retries. After 2 failures, orchestrator implements remaining tasks directly.
 
 All tasks `[x]`, tests pass.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `prizmkit-implement` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-implement-lite.md

@@ -30,3 +30,6 @@ $TEST_CMD 2>&1 | tee /tmp/test-baseline.txt | tail -20
 4. If any criterion is not met, fix it now (max 2 fix rounds)
 
 **CP-2**: All acceptance criteria met, all tests pass.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `prizmkit-implement` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-plan-agent.md

@@ -15,3 +15,6 @@ Before proceeding past CP-1, verify:
 4. If a DB design decision genuinely cannot be resolved from existing code alone, document the assumption made and flag it in the Implementation Log for user review.
 
 **CP-1**: plan.md exists with Tasks section.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `prizmkit-plan` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-plan-lite.md

@@ -14,3 +14,6 @@ Before proceeding past CP-1:
 3. Resolve all uncertain DB design decisions before writing Tasks — document choices in plan.md
 
 **CP-1**: plan.md exists with Tasks section.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `prizmkit-plan` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-review-agent.md

@@ -1,18 +1,13 @@
 ### Review + Test — Reviewer Subagent
 
-Spawn Reviewer subagent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false).
-
-Prompt:
-> "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
-> 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.
-> 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."
+**Spawn Agent**:
+| Parameter | Value |
+|-----------|-------|
+| subagent_type | prizm-dev-team-reviewer |
+| run_in_background | false |
+
+**Prompt**:
+> {{AGENT_PROMPT_REVIEWER_REVIEW}}
 
 Wait for Reviewer to return.
 
@@ -26,3 +21,6 @@ If GATE:MISSING — send message to Reviewer (re-spawn if needed): "Write the '#
 - If NEEDS_FIXES: spawn Dev to fix (Dev reads Fix Instructions in snapshot), re-run Review (max 3 rounds)
 
 **CP-3**: Tests pass, verdict is not NEEDS_FIXES.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `prizmkit-code-review` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-review-full.md

@@ -1,18 +1,13 @@
 ### Review + Test — Reviewer Agent
 
-Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false).
-
-Prompt:
-> "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
-> 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.
-> 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."
+**Spawn Agent**:
+| Parameter | Value |
+|-----------|-------|
+| subagent_type | prizm-dev-team-reviewer |
+| run_in_background | false |
+
+**Prompt**:
+> {{AGENT_PROMPT_REVIEWER_REVIEW}}
 
 Wait for Reviewer to return.
 
@@ -24,13 +19,10 @@ grep -q "## Review Notes" .prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md &
 If GATE:MISSING — send message to Reviewer (re-spawn if needed): "Write the '## Review Notes' section to context-snapshot.md with structured Fix Instructions. Include: verdict, findings with Root Cause/Impact/Fix Strategy/Code Guidance/Verification, and Re-Review Expectations."
 
 - If NEEDS_FIXES: spawn Dev to fix with this prompt:
-  > "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. Use `TEST_CMD=<TEST_CMD>` to verify no regressions.
-  > 5. Append fix summary to '## Implementation Log' in context-snapshot.md.
-  > 6. Do NOT execute any git commands."
+  > {{AGENT_PROMPT_DEV_FIX}}
   Then re-run Review (max 3 rounds).
 
 **CP-3**: Integration tests pass, verdict is not NEEDS_FIXES.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `prizmkit-code-review` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase-specify-plan-full.md

@@ -80,3 +80,6 @@ Before proceeding past CP-1, verify:
 4. If a DB design decision genuinely cannot be resolved from existing code alone, document the assumption made and flag it in the Implementation Log for user review.
 
 **CP-1**: Both spec.md and plan.md exist.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `context-snapshot-and-plan` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase0-init.md

@@ -2,3 +2,6 @@
 - Run `/prizmkit-init` (invoke the prizmkit-init skill)
 - Run `python3 {{INIT_SCRIPT_PATH}} --project-root {{PROJECT_ROOT}} --feature-id {{FEATURE_ID}} --feature-slug {{FEATURE_SLUG}}`
 - **CP-0**: Verify `.prizm-docs/root.prizm`, `.prizmkit/config.json` exist
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `prizmkit-init` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/phase0-test-baseline.md

@@ -10,3 +10,6 @@ $TEST_CMD 2>&1 | tee /tmp/test-baseline.txt | tail -20
 Save the list of **pre-existing failing tests** (if any) as `BASELINE_FAILURES`. These are known failures that existed before this session — Dev must NOT be blamed for them, but must list them in COMPLETION_SIGNAL.
 
 > **Test Output Rule**: Always capture test output to a temp file (`tee /tmp/test-out.txt`). Then grep the file instead of re-running the suite.
+
+
+**Checkpoint update**: Update `workflow-checkpoint.json` — set step `test-baseline` to `"completed"`.

package/bundled/dev-pipeline/templates/sections/resume-header.md

@@ -1,2 +1,5 @@
 ### Resume from Phase {{RESUME_PHASE}}
-Check `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` — if it exists, skip context building and use it directly.
+
+**Primary**: Read `{{CHECKPOINT_PATH}}` — find the first step with `"pending"` or `"in_progress"` status and resume from there. Steps already `"completed"` or `"skipped"` must NOT be re-executed.
+
+**Fallback**: If `workflow-checkpoint.json` is missing or corrupted, check `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` — if it exists, skip context building and use it directly.

package/bundled/dev-pipeline/templates/sections/test-failure-recovery.md

@@ -0,0 +1,75 @@
+## Test Failure Recovery Protocol
+
+When tests fail during implementation (Phase 3 / Phase 4):
+
+### Immediate Action — Recovery Attempt (Max 2 Rounds)
+
+1. **Analyze failure output**:
+   - Read the test failure message carefully
+   - Identify: root cause (code bug vs. test brittleness vs. environment issue)
+   - Check if baseline already recorded this failure (in BASELINE_FAILURES)
+
+2. **Categorize failure**:
+   - **Pre-existing baseline failure** (expected): Record as acceptable, do NOT fix
+   - **New regression**: Code introduced a bug, fix the code
+   - **Brittle test**: Test passes/fails inconsistently, fix the test or environment
+   - **Environment issue**: Missing dependency, wrong config, fix setup
+
+3. **Fix and re-run** (first round):
+   - Apply fix (code or test, not environment)
+   - Re-run `$TEST_CMD` to verify
+   - If now passing → continue to next task
+   - If still failing → **proceed to Round 2**
+
+4. **Second fix attempt** (second round only):
+   - Re-analyze the failure with fresh perspective
+   - Try alternate fix approach
+   - Re-run `$TEST_CMD`
+   - If still failing after Round 2 → **escalate** (see below)
+
+### Escalation Paths
+
+**Tier 1 (Single Agent)**:
+- After max 2 fix rounds with tests still failing
+- Document failure in Implementation Log with root cause analysis
+- Attempt one manual fix by re-reading related source code
+- If unable to resolve: record PARTIAL status with known failure list
+- **Do NOT block commit**; tests can fail during development (recovery may be deferred to next session)
+
+**Tier 2/3 (Dev + Reviewer)**:
+- After Dev completes max 2 fix rounds with tests still failing
+- Dev appends failure details to Implementation Log
+- Reviewer agent runs full test suite in Phase 5
+- If Reviewer confirms NEW regressions (not in baseline): mark verdict as `NEEDS_FIXES`
+- If Reviewer confirms only baseline failures remain: proceed with `PASS_WITH_WARNINGS`
+
+### Context-Aware Test Re-run (Performance Optimization)
+
+**Skip redundant re-runs**:
+- If Implementation Log section in context-snapshot.md already confirms "all tests passing"
+- → Skip Phase 5 test suite re-run (Reviewer will verify baseline log instead)
+- This avoids rebuilding/re-running tests when already verified
+
+**When to re-run**:
+- If Implementation Log is missing or incomplete
+- If any new code was added after the last test run
+- If Reviewer suspects brittleness or environment drift
+
+### Failure Capture Rules
+
+If tests remain broken after recovery:
+
+```
+## Test Failures Encountered
+
+- **Test**: [test name/path]
+  - Root Cause: [explanation]
+  - Category: [pre-existing baseline | new regression | brittle test | environment]
+  - Fix Attempted: [describe what was tried]
+  - Status: [still failing | requires next session | known limitation]
+
+- **Impact on Feature**: [can AC be verified despite failure | blocks AC verification]
+```
+
+**Rule**: If any AC cannot be verified due to test failure, the feature is incomplete. Document in failure-log.md for next session.
+

package/bundled/rules/prizm/prizm-commit-workflow.md

@@ -8,3 +8,4 @@ Before any git commit in this project:
 3. Bug fixes use `fix()` prefix, not `feat()`
 4. Bug fixes run retrospective with structural sync only (Job 1)
 5. Use `/prizmkit-committer` command for the pure commit workflow
+6. After commit, `/prizmkit-committer` generates `session-summary.md` (lightweight cross-session handoff, not committed to git)