[RALPH + ULTRAWORK - ITERATION {{ITERATION}}/{{MAX}}]

Your previous attempt did not output the completion promise. Continue working on the task.

<Use_When>

• Task requires guaranteed completion with verification (not just "do your best")
• User says "ralph", "don't stop", "must complete", "finish this", or "keep going until done"
• Work may span multiple iterations and needs persistence across retries
• Task benefits from structured PRD-driven execution with reviewer sign-off </Use_When>

<Do_Not_Use_When>

• User wants a full autonomous pipeline from idea to code -- use autopilot instead
• User wants to explore or plan before committing -- use plan skill instead
• User wants a quick one-shot fix -- delegate directly to an executor agent
• User wants manual control over completion -- use ultrawork directly </Do_Not_Use_When>

<Why_This_Exists> Complex tasks often fail silently: partial implementations get declared "done", tests get skipped, edge cases get forgotten. Ralph prevents this by:

1. Structuring work into discrete user stories with testable acceptance criteria (prd.json)
2. Iterating story-by-story until each one passes
3. Tracking progress and learnings across iterations (progress.txt)
4. Requiring fresh reviewer verification against specific acceptance criteria before completion </Why_This_Exists>

<PRD_Mode> By default, ralph operates in PRD mode. A scaffold prd.json is auto-generated when ralph starts if none exists.

Opt-out: If {{PROMPT}} contains --no-prd, skip PRD generation and work in legacy mode (no story tracking, generic verification). Use this for trivial quick fixes.

Reviewer selection: Pass --critic=architect, --critic=critic, or --critic=codex in the Ralph prompt to choose the completion reviewer for that run. architect remains the default. </PRD_Mode>

<Execution_Policy>

• Fire independent agent calls simultaneously -- never wait sequentially for independent work
• Use run_in_background: true for long operations (installs, builds, test suites)
• Always pass the model parameter explicitly when delegating to agents
• Read docs/shared/agent-tiers.md before first delegation to select correct agent tiers
• Deliver the full implementation: no scope reduction, no partial completion, no deleting tests to make them pass </Execution_Policy>

2. Pick next story: Read prd.json and select the highest-priority story with passes: false. This is your current focus.

3. Implement the current story:

   • Delegate to specialist agents at appropriate tiers:
     • Simple lookups: LOW tier (Haiku) -- "What does this function return?"
     • Standard work: MEDIUM tier (Sonnet) -- "Add error handling to this module"
     • Complex analysis: HIGH tier (Opus) -- "Debug this race condition"
   • If during implementation you discover sub-tasks, add them as new stories to prd.json
   • Run long operations in background: Builds, installs, test suites use run_in_background: true

4. Verify the current story's acceptance criteria: a. For EACH acceptance criterion in the story, verify it is met with fresh evidence b. Run relevant checks (test, build, lint, typecheck) and read the output c. If any criterion is NOT met, continue working -- do NOT mark the story as complete

5. Mark story complete: a. When ALL acceptance criteria are verified, set passes: true for this story in prd.json b. Record progress in progress.txt: what was implemented, files changed, learnings for future iterations c. Add any discovered codebase patterns to progress.txt

6. Check PRD completion: a. Read prd.json -- are ALL stories marked passes: true? b. If NOT all complete, loop back to Step 2 (pick next story) c. If ALL complete, proceed to Step 7 (architect verification)

7. Reviewer verification (tiered, against acceptance criteria):

   • <5 files, <100 lines with full tests: STANDARD tier minimum (architect-medium / Sonnet)
   • Standard changes: STANDARD tier (architect-medium / Sonnet)

   • 20 files or security/architectural changes: THOROUGH tier (architect / Opus)

   • If --critic=critic, use the Claude critic agent for the approval pass
   • If --critic=codex, run omc ask codex --agent-prompt critic "..." for the approval pass
   • Ralph floor: always at least STANDARD, even for small changes
   • The selected reviewer verifies against the SPECIFIC acceptance criteria from prd.json, not vague "is it done?"

8. On approval: Run /oh-my-claudecode:cancel to cleanly exit and clean up all state files

9. On rejection: Fix the issues raised, re-verify with the same reviewer, then loop back to check if the story needs to be marked incomplete

   </Steps>

<Tool_Usage>

• Use Task(subagent_type="oh-my-claudecode:architect", ...) for architect verification cross-checks when changes are security-sensitive, architectural, or involve complex multi-system integration
• Use Task(subagent_type="oh-my-claudecode:critic", ...) when --critic=critic
• Use omc ask codex --agent-prompt critic "..." when --critic=codex
• Skip architect consultation for simple feature additions, well-tested changes, or time-critical verification
• Proceed with architect agent verification alone -- never block on unavailable tools
• Use state_write / state_read for ralph mode state persistence between iterations </Tool_Usage>

After refinement: acceptanceCriteria: [ "detectNoPrdFlag('ralph --no-prd fix') returns true", "detectNoPrdFlag('ralph fix this') returns false", "stripNoPrdFlag removes --no-prd and trims whitespace", "TypeScript compiles with no errors (npm run build)" ]

Why good: Generic criteria replaced with specific, testable criteria.
</Good>

<Good>
Correct parallel delegation:

Task(subagent_type="oh-my-claudecode:executor", model="haiku", prompt="Add type export for UserConfig") Task(subagent_type="oh-my-claudecode:executor", model="sonnet", prompt="Implement the caching layer for API responses") Task(subagent_type="oh-my-claudecode:executor", model="opus", prompt="Refactor auth module to support OAuth2 flow")

Why good: Three independent tasks fired simultaneously at appropriate tiers.
</Good>

<Good>
Story-by-story verification:

1. Story US-001: "Add flag detection helpers"
   • Criterion: "detectNoPrdFlag returns true for --no-prd" → Run test → PASS
   • Criterion: "TypeScript compiles" → Run build → PASS
   • Mark US-001 passes: true
2. Story US-002: "Wire PRD into bridge.ts"
   • Continue to next story...

Why good: Each story verified against its own acceptance criteria before marking complete.
</Good>

<Bad>
Claiming completion without PRD verification:
"All the changes look good, the implementation should work correctly. Task complete."
Why bad: Uses "should" and "look good" -- no fresh evidence, no story-by-story verification, no architect review.
</Bad>

<Bad>
Sequential execution of independent tasks:

Task(executor, "Add type export") → wait → Task(executor, "Implement caching") → wait → Task(executor, "Refactor auth")

Why bad: These are independent tasks that should run in parallel, not sequentially.
</Bad>

<Bad>
Keeping generic acceptance criteria:
"prd.json created with criteria: Implementation is complete, Code compiles. Moving on to coding."
Why bad: Did not refine scaffold criteria into task-specific ones. This is PRD theater.
</Bad>
</Examples>

<Escalation_And_Stop_Conditions>
- Stop and report when a fundamental blocker requires user input (missing credentials, unclear requirements, external service down)
- Stop when the user says "stop", "cancel", or "abort" -- run `/oh-my-claudecode:cancel`
- Continue working when the hook system sends "The boulder never stops" -- this means the iteration continues
- If the selected reviewer rejects verification, fix the issues and re-verify (do not stop)
- If the same issue recurs across 3+ iterations, report it as a potential fundamental problem
</Escalation_And_Stop_Conditions>

<Final_Checklist>
- [ ] All prd.json stories have `passes: true` (no incomplete stories)
- [ ] prd.json acceptance criteria are task-specific (not generic boilerplate)
- [ ] All requirements from the original task are met (no scope reduction)
- [ ] Zero pending or in_progress TODO items
- [ ] Fresh test run output shows all tests pass
- [ ] Fresh build output shows success
- [ ] lsp_diagnostics shows 0 errors on affected files
- [ ] progress.txt records implementation details and learnings
- [ ] Selected reviewer verification passed against specific acceptance criteria
- [ ] `/oh-my-claudecode:cancel` run for clean state cleanup
</Final_Checklist>

<Advanced>
## Background Execution Rules

**Run in background** (`run_in_background: true`):
- Package installation (npm install, pip install, cargo build)
- Build processes (make, project build commands)
- Test suites
- Docker operations (docker build, docker pull)

**Run blocking** (foreground):
- Quick status checks (git status, ls, pwd)
- File reads and edits
- Simple commands
</Advanced>

Original task:
{{PROMPT}}