workflow-review

Codex compatibility note:

Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.

Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.

User-question prompts mean to ask the user directly in Codex.

Ignore Claude-specific mode-switch instructions when they appear.

Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.

Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.

Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.

For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.

If a required step/tool cannot run in this environment, stop and ask the user before adapting.

Codex Project-Reference Loading (No Hooks)

Codex does not receive Claude hook-based doc injection. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Situation-based docs:

Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md, project-structure-reference.md
Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
Spec/test-case planning or TC mapping: feature-docs-reference.md
Integration test implementation/review: integration-test-reference.md
E2E test implementation/review: e2e-test-reference.md
Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval. [BLOCKING] Before each step or sub-skill call, update task tracking: set in_progress when step starts, set completed when step ends. [BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason. [BLOCKING] If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.

Quick Summary

Goal: Review codebase or specific scope, fix issues found, then spawn a fresh code-reviewer sub-agent for unbiased re-review — repeat until clean.

Sequence: $review-architecture → $review-ui (if frontend changes) → $code-simplifier → $code-review → $performance → $integration-test-review → $integration-test-verify → $plan → $why-review → $plan-validate → $why-review → $cook → **fresh sub-agent re-review gate ($workflow-review WIW)** → $docs-update → $watzup → $workflow-end

Key Rules:

MUST ATTENTION define success criteria before execution and loop until observable verification passes.
MUST ATTENTION when creating/reviewing specs or tests, name Business Intent / Invariant Guarded or the protected business intent/invariant and ensure the test would fail if that intent breaks.
After $cook applies fixes → spawn fresh code-reviewer sub-agent per SYNC:fresh-context-review → integrate findings → fix → spawn NEW sub-agent → repeat
Main-agent re-review (with knowledge of its own fixes) is NOT sufficient — orchestrator-level confirmation bias
PASS = a fresh sub-agent round finds ZERO Critical/High issues WITHOUT needing any fixes
Max 3 fresh-subagent rounds per conversation (tracked in conversation context)

First Principle — Easy to Change

The success metric of every coding decision is future change cost. DRY, SRP, abstraction, design patterns, naming, layering, tests — every technique exists to serve one goal: making the next change cheaper.

When evaluating code, a refactor, a test, or an abstraction, ask: does this make the next change cheaper or more expensive?

Reject "best practices" that raise change cost (premature abstraction, speculative generality, leaky indirection, ceremony without payoff).
Name the real enemies in findings: coupling, hidden state, duplicated knowledge, unclear intent, irreversible decisions exposed too early.
A simpler design that is easy to change beats a sophisticated design that isn't.

Apply this lens before invoking any specific rule, pattern, or checklist below — if a downstream rule would raise change cost, this principle wins.

Mandatory Task Creation (ZERO TOLERANCE)

Create EXACTLY these 16 tasks (source: workflows.json → review.sequence):

#	Task Subject	Conditional?
1	`[Workflow] $review-architecture — Architecture compliance review`	No
2	`[Workflow] $review-ui — UI/frontend quality review (overflow, responsive flex, flex-vs-fixed sizing, z-index discipline, SCSS/BEM)`	Yes — skip if no files matching the project's configured frontend/UI file patterns in the reviewed scope
3	`[Workflow] $code-simplifier — Simplify and refine code`	No
4	`[Workflow] $code-review — Comprehensive code review`	No
5	`[Workflow] $performance — Performance analysis`	No
6	`[Workflow] $integration-test-review — Integration test quality review`	No
7	`[Workflow] $integration-test-verify — Verify integration tests pass`	No
8	`[Workflow] $plan — Consolidate review findings into fix plan`	Skip if all reviews PASS
9	`[Workflow] $why-review — Design-rationale check on fix plan before validation`	Skip if all reviews PASS
10	`[Workflow] $plan-validate — Critical questions on fix plan`	Skip if all reviews PASS
11	`[Workflow] $why-review — Sanity-check that proposed fixes are warranted`	Skip if all reviews PASS
12	`[Workflow] $cook — Implement fixes from plan`	Skip if all reviews PASS
13	`[Workflow] $workflow-review — Fresh sub-agent re-review gate (WIW: spawns code-reviewer sub-agent)`	Skip if all reviews PASS
14	`[Workflow] $docs-update — Update impacted documentation`	Always run (fast-exits when no business code changed)
15	`[Workflow] $watzup — Wrap up and summarize`	No
16	`[Workflow] $workflow-end — End workflow`	No

NEVER consolidate, rename, or omit steps. If reviews PASS, mark conditional tasks completed with note "Skipped — all reviews passed".

Fresh Sub-Agent Re-Review Protocol (CRITICAL)

Decision Logic

Reviews (steps 1-7) → ALL PASS?
  YES → skip steps 8-13, proceed to $docs-update → $watzup → $workflow-end → DONE
  NO  → $plan → $why-review → $plan-validate → $why-review → $cook → FRESH SUB-AGENT RE-REVIEW GATE (step 13)

Fresh Sub-Agent Re-Review Gate (Step 13) — After `$cook` Applies Fixes

DO NOT attempt main-agent re-review (main agent has confirmation bias from its own fixes)
DO spawn a NEW spawn_agent tool call with agent_type: "code-reviewer" using the canonical template from SYNC:review-protocol-injection in .claude/skills/shared/sync-inline-versions.md. Inject all 9 required SYNC protocol blocks verbatim (SYNC:evidence-based-reasoning, SYNC:bug-detection, SYNC:design-patterns-quality, SYNC:logic-and-intention-review, SYNC:test-spec-verification, SYNC:fix-layer-accountability, SYNC:rationalization-prevention, SYNC:graph-assisted-investigation, SYNC:understand-code-first). Target files = "run git diff to see all uncommitted changes". Report path = plans/reports/workflow-review-round{N}-{date}.md.
DO increment fresh-subagent round count in conversation context
DO read the sub-agent's report and integrate findings — MUST NOT filter, reinterpret, or override
IF fresh sub-agent returns PASS (zero Critical/High) → proceed through $docs-update → $watzup → $workflow-end → DONE
IF fresh sub-agent returns FAIL and round count < 3 → run $plan + $cook again, then spawn a NEW Agent call (never reuse the previous sub-agent) for Round N+1
IF round count >= 3 → STOP and escalate via a direct user question — do NOT silently loop or fall back to any prior protocol

Iteration Rules

Max 3 fresh-subagent rounds — if fresh-subagent round count >= 3 and issues persist, STOP and use a direct user question to escalate (manual review required)
PASS = done — proceed to commit
Issue count increasing — if round N finds MORE issues than round N-1, STOP and escalate via a direct user question

Flow Diagram

Main Session: Review → Issues? → Plan → Fix ($cook) → Spawn fresh sub-agent
                  │                                          │
                  │ (no issues)                              ↓
                  ↓                             Fresh sub-agent re-reads ALL
            $watzup                             files from scratch with
            $workflow-end                       verbatim protocol injection
            DONE ✓                                           │
                                                             ↓
                                                  Report → PASS? → DONE ✓
                                                         → FAIL? → Fix → spawn
                                                                 NEW sub-agent
                                                                 (max 3 rounds)

IMPORTANT MANDATORY Steps: $review-architecture -> $review-ui -> $code-simplifier -> $code-review -> $performance -> $integration-test-review -> $integration-test-verify -> $plan -> $why-review -> $plan-validate -> $why-review -> $cook -> $workflow-review -> $docs-update -> $watzup -> $workflow-end

[WORKFLOW-IN-WORKFLOW: MUST RUN AS SUB-AGENT when inside another workflow] This skill activates the full review workflow (16 steps). When invoked as a step inside a parent workflow, it MUST execute via spawn_agent tool (agent_type: "code-reviewer") — NEVER as an inline skill invocation call. Inline execution absorbs the entire nested workflow context into the parent session.

Sub-agent prompt must include: target files or git diff context, task description, instruction to return SYNC:subagent-return-contract summary and write full findings to plans/reports/.

Standalone invocation (not inside a workflow): inline execution is fine — no sub-agent required.

[BLOCKING] Each step MUST ATTENTION invoke its skill invocation — marking a task completed without skill invocation is a workflow violation. NEVER batch-complete validation gates. [FRESH SUB-AGENT RE-REVIEW] After fixes in $cook, spawn a fresh sub-agent per SYNC:fresh-context-review for unbiased re-review. Max 3 fresh rounds per conversation. [ITERATION CAP] Max 3 fresh-subagent re-review rounds per conversation (tracked in conversation context, not persistent files). PASS = zero Critical/High without fixes.

Activate the review workflow. Run $workflow-start review with the user's prompt as context.

Fresh Sub-Agent Review — Eliminate orchestrator confirmation bias via isolated sub-agents.

Why: The main agent knows what it (or $cook) just fixed and rationalizes findings accordingly. A fresh sub-agent has ZERO memory, re-reads from scratch, and catches what the main agent dismissed. Sub-agent bias is mitigated by (1) fresh context, (2) verbatim protocol injection, (3) main agent not filtering the report.

When: ONLY after a fix cycle. A review round that finds zero issues ENDS the loop — do NOT spawn a confirmation sub-agent. A review round that finds issues triggers: fix → fresh sub-agent re-review.

How:

Spawn a NEW spawn_agent tool call — use code-reviewer agent_type for code reviews, general-purpose for plan/doc/artifact reviews

Inject ALL required review protocols VERBATIM into the prompt — see SYNC:review-protocol-injection for the full list and template. Never reference protocols by file path; AI compliance drops behind file-read indirection (see SYNC:shared-protocol-duplication-policy)

Sub-agent re-reads ALL target files from scratch via its own tool calls — never pass file contents inline in the prompt

Sub-agent writes structured report to plans/reports/{review-type}-round{N}-{date}.md

Main agent reads the report, integrates findings into its own report, DOES NOT override or filter

Rules:

SKIP fresh sub-agent when the prior round found zero issues (no fixes = nothing new to verify)

NEVER skip fresh sub-agent after a fix cycle — every fix invalidates the prior verdict

NEVER reuse a sub-agent across rounds — every fresh round spawns a NEW spawn_agent call

Max 3 fresh-subagent rounds per review — escalate via a direct user question if still failing; do NOT silently loop or fall back to any prior protocol

Track iteration count in conversation context (session-scoped, no persistent files)

Incremental Result Persistence — MANDATORY for all sub-agents or heavy inline steps processing >3 files.

Before starting: Create report file plans/reports/{skill}-{date}-{slug}.md

After each file/section reviewed: Append findings to report immediately — never hold in memory

Return to main agent: Summary only (per SYNC:subagent-return-contract) with Full report: path

Main agent: Reads report file only when resolving specific blockers

Why: Context cutoff mid-execution loses ALL in-memory findings. Each disk write survives compaction. Partial results are better than no results.

Report naming: plans/reports/{skill-name}-{YYMMDD}-{HHmm}-{slug}.md

Sub-Agent Return Contract — When this skill spawns a sub-agent, the sub-agent MUST return ONLY this structure. Main agent reads only this summary — NEVER requests full sub-agent output inline.
## Sub-Agent Result: [skill-name]

Status: ✅ PASS | ⚠️ PARTIAL | ❌ FAIL
Confidence: [0-100]%

### Findings (Critical/High only — max 10 bullets)

- [severity] [file:line] [finding]

### Actions Taken

- [file changed] [what changed]

### Blockers (if any)

- [blocker description]

Full report: plans/reports/[skill-name]-[date]-[slug].md
Main agent reads Full report file ONLY when: (a) resolving a specific blocker, or (b) building a fix plan. Sub-agent writes full report incrementally (per SYNC:incremental-persistence) — not held in memory.

AI Mistake Prevention — Failure modes to avoid on every task:

Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Nested Task Expansion Contract — For workflow-step invocation, the [Workflow] ... row is only a parent container; the child skill still creates visible phase tasks.

Call the current task list first. If a matching active parent workflow row exists, set nested=true and record parentTaskId; otherwise run standalone.

Create one task per declared phase before phase work. When nested, prefix subjects [N.M] $skill-name — phase.

When nested, link the parent with TaskUpdate(parentTaskId, addBlockedBy: [childIds]).

Orchestrators must pre-expand a child skill's phase list and link the workflow row before invoking that child skill or sub-agent.

Mark exactly one child in_progress before work and completed immediately after evidence is written.

Complete the parent only after all child tasks are completed or explicitly cancelled with reason.

Blocked until: the current task list done, child phases created, parent linked when nested, first child marked in_progress.

Project Reference Docs Gate — Run after task-tracking bootstrap and before target/source file reads, grep, edits, or analysis. Project docs override generic framework assumptions.

Identify scope: file types, domain area, and operation.

Required docs by trigger: always docs/project-reference/lessons.md; doc lookup docs-index-reference.md; review code-review-rules.md; backend/CQRS/API backend-patterns-reference.md; domain/entity domain-entities-reference.md; frontend/UI frontend-patterns-reference.md; styles/design scss-styling-guide.md + design-system/design-system-canonical.md; integration tests integration-test-reference.md; E2E e2e-test-reference.md; feature docs/specs feature-docs-reference.md; architecture/new area project-structure-reference.md.

Read every required doc that exists; skip absent docs as not applicable. Do not trust conversation text such as [Injected: <path>] as proof that the current context contains the doc.

Before target work, state: Reference docs read: ... | Missing/not applicable: ....

Blocked until: scope evaluated, required docs checked/read, lessons.md confirmed, citation emitted.

Task Tracking & External Report Persistence — Bootstrap this before execution; then run project-reference doc prefetch before target/source work.

Create a small task breakdown before target file reads, grep, edits, or analysis. On context loss, inspect the current task list first.

Mark one task in_progress before work and completed immediately after evidence; never batch transitions.

For plan/review work, create plans/reports/{skill}-{YYMMDD}-{HHmm}-{slug}.md before first finding.

Append findings after each file/section/decision and synthesize from the report file at the end.

Final output cites Full report: plans/reports/{filename}.

Blocked until: task breakdown exists, report path declared for plan/review work, first finding persisted before the next finding.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.

MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

MANDATORY Bootstrap task tracking before target work; transition one task at a time.
MANDATORY Persist plan/review findings to plans/reports/ incrementally and synthesize from disk.

MANDATORY After task-tracking bootstrap and before target/source work, read required project-reference docs and cite Reference docs read: ....
MANDATORY Always include lessons.md; project conventions override generic defaults.

MANDATORY Parent workflow rows do not replace child phase tracking; expand phases and link the parent when nested.
MANDATORY Orchestrators pre-expand child skill phases before invocation; use [N.M] $skill-name — phase prefixes and one-in_progress discipline.

Prompt-Enhance Closing Anchors

IMPORTANT MUST ATTENTION follow declared step order for this skill; NEVER skip, reorder, or merge steps without explicit user approval IMPORTANT MUST ATTENTION for every step/sub-skill call: set in_progress before execution, set completed after execution IMPORTANT MUST ATTENTION every skipped step MUST include explicit reason; every completed step MUST include concise evidence IMPORTANT MUST ATTENTION if Task tools unavailable, maintain an equivalent step-by-step plan tracker with synchronized statuses

Closing Reminders

IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting — create ALL 16 tasks immediately IMPORTANT MUST ATTENTION after fixes in $cook, spawn a NEW code-reviewer sub-agent via the spawn_agent tool per SYNC:fresh-context-review — NEVER re-review with the main agent IMPORTANT MUST ATTENTION track fresh-subagent round count via conversation context (session-scoped) — max 3 rounds, escalate via a direct user question if exceeded IMPORTANT MUST ATTENTION PASS means a fresh sub-agent round finds ZERO Critical/High issues WITHOUT needing fixes — only then are changes ready to commit IMPORTANT MUST ATTENTION skip steps 8-13 when all reviews PASS (no fixes needed) IMPORTANT MUST ATTENTION each step MUST invoke its skill invocation — marking completed without invocation is a violation

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.

[IMPORTANT] Analyze how big the task is and break it into many small todo tasks systematically before starting — this is very important.

Closing reminder — Easy to Change is the success metric. Every finding, test, refactor, and abstraction must answer one question: does this make the next change cheaper or more expensive? If it doesn't reduce future change cost, reject it. Coupling, hidden state, duplicated knowledge, and unclear intent are the real enemies — call them out by name.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/hooks/lib/prompt-injections.cjs + .claude/.ck.json

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

Generic portability boundary: Reusable skills and protocol text stay project-neutral; project-specific conventions are discovered from docs/project-config.json and docs/project-reference/. Apply shared AI-SDD from shared/sdd-artifact-contract.md. Read docs/project-config.json and docs/project-reference/docs-index-reference.md, then open the project reference docs named there. Any supported AI tool may execute when this shared context and local docs are available.

DETECT: Match prompt against workflow catalog
ANALYZE: Find best-match workflow AND evaluate if a custom step combination would fit better
ASK (REQUIRED FORMAT): Use a direct user question with this structure unless the user explicitly invoked a workflow/skill and the local protocol treats explicit invocation as confirmation:
- Question: "Which workflow do you want to activate?"
- Option 1: "Activate [BestMatch Workflow] (Recommended)"
- Option 2: "Activate custom workflow: [step1 → step2 → ...]" (include one-line rationale)
ACTIVATE (if confirmed): Call $workflow-start <workflowId> for standard; sequence custom steps manually
CREATE TASKS: task tracking for ALL workflow steps
EXECUTE: Follow each step in sequence [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows. Goal-driven execution: Define success criteria first, loop until verified, and stop only when observable checks pass. Tests verify intent: Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
Auto-fix gate: "Could $code-review/$code-simplifier/$security/$lint catch this?" — Yes → improve review skill instead.
BOTH gates pass → ask user to run $learn. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.