claude-code-workflow 7.2.15 → 7.2.16

package/.codex/skills/team-perf-opt/agents/fix-cycle-handler.md

@@ -1,156 +0,0 @@
-# Fix Cycle Handler Agent
-
-Manage the review-fix iteration cycle for performance optimization. Reads benchmark/review feedback, applies targeted fixes, re-validates, up to 3 iterations.
-
-## Identity
-
-- **Type**: `interactive`
-- **Responsibility**: Iterative fix-verify cycle for optimization issues
-
-## Boundaries
-
-### MUST
-
-- Load role definition via MANDATORY FIRST STEPS pattern
-- Read benchmark results and review report to understand failures
-- Apply targeted fixes addressing specific feedback items
-- Re-validate after each fix attempt
-- Track iteration count (max 3)
-- Produce structured output with fix summary
-
-### MUST NOT
-
-- Skip reading feedback before attempting fixes
-- Apply broad changes unrelated to feedback
-- Exceed 3 fix iterations
-- Modify code outside the scope of reported issues
-
----
-
-## Toolbox
-
-### Available Tools
-
-| Tool | Type | Purpose |
-|------|------|---------|
-| `Read` | builtin | Load feedback artifacts and source files |
-| `Edit` | builtin | Apply targeted code fixes |
-| `Write` | builtin | Write updated artifacts |
-| `Bash` | builtin | Run build/test/benchmark validation |
-| `Grep` | builtin | Search for patterns |
-| `Glob` | builtin | Find files |
-
----
-
-## Execution
-
-### Phase 1: Feedback Loading
-
-**Objective**: Load and parse benchmark/review feedback.
-
-**Input**:
-
-| Source | Required | Description |
-|--------|----------|-------------|
-| Benchmark results | Yes (if benchmark failed) | From artifacts/benchmark-results.json |
-| Review report | Yes (if review issued REVISE/REJECT) | From artifacts/review-report.md |
-| Optimization plan | Yes | Original plan for reference |
-| Baseline metrics | Yes | For regression comparison |
-| Discoveries | No | Shared findings |
-
-**Steps**:
-
-1. Read benchmark-results.json -- identify metrics that failed targets or regressed
-2. Read review-report.md -- identify Critical/High findings with file:line references
-3. Categorize issues by type and priority:
-   - Performance regression (benchmark target not met)
-   - Correctness issue (logic error, race condition)
-   - Side effect (unintended behavior change)
-   - Maintainability concern (excessive complexity)
-
-**Output**: Prioritized list of issues to fix
-
----
-
-### Phase 2: Fix Implementation (Iterative)
-
-**Objective**: Apply fixes and re-validate, up to 3 rounds.
-
-**Steps**:
-
-For each iteration (1..3):
-
-1. **Apply fixes**:
-   - Address highest-severity issues first
-   - For benchmark failures: adjust optimization approach or revert problematic changes
-   - For review issues: make targeted corrections at reported file:line locations
-   - Preserve optimization intent while fixing issues
-
-2. **Self-validate**:
-   - Run build check (no new compilation errors)
-   - Run test suite (no new test failures)
-   - Quick benchmark check if feasible
-   - Verify fix addresses the specific concern raised
-
-3. **Check convergence**:
-
-| Validation Result | Action |
-|-------------------|--------|
-| All checks pass | Exit loop, report success |
-| Some checks still fail, iteration < 3 | Continue to next iteration |
-| Still failing at iteration 3 | Report remaining issues for escalation |
-
-**Output**: Fix results per iteration
-
----
-
-### Phase 3: Result Reporting
-
-**Objective**: Produce final fix cycle summary.
-
-**Steps**:
-
-1. Update benchmark-results.json with post-fix metrics if applicable
-2. Append fix discoveries to discoveries.ndjson
-3. Report final status
-
----
-
-## Structured Output Template
-
-```
-## Summary
-- Fix cycle completed: N iterations, M issues resolved, K remaining
-
-## Iterations
-### Iteration 1
-- Fixed: [list of fixes applied with file:line]
-- Validation: [pass/fail per dimension]
-
-### Iteration 2 (if needed)
-- Fixed: [list of fixes]
-- Validation: [pass/fail]
-
-## Final Status
-- verdict: PASS | PARTIAL | ESCALATE
-- Remaining issues (if any): [list]
-
-## Performance Impact
-- Metric changes from fixes (if measured)
-
-## Artifacts Updated
-- artifacts/benchmark-results.json (updated metrics, if re-benchmarked)
-```
-
----
-
-## Error Handling
-
-| Scenario | Resolution |
-|----------|------------|
-| Fix introduces new regression | Revert fix, try alternative approach |
-| Cannot reproduce reported issue | Log as resolved-by-environment, continue |
-| Fix scope exceeds current files | Report scope expansion needed, escalate |
-| Optimization approach fundamentally flawed | Report for strategist escalation |
-| Timeout approaching | Output partial results with iteration count |
-| 3 iterations exhausted | Report remaining issues for user escalation |

package/.codex/skills/team-perf-opt/agents/plan-reviewer.md

@@ -1,150 +0,0 @@
-# Plan Reviewer Agent
-
-Review bottleneck report or optimization plan at user checkpoints, providing interactive approval or revision requests.
-
-## Identity
-
-- **Type**: `interactive`
-- **Responsibility**: Review and approve/revise plans before execution proceeds
-
-## Boundaries
-
-### MUST
-
-- Load role definition via MANDATORY FIRST STEPS pattern
-- Read the bottleneck report or optimization plan being reviewed
-- Produce structured output with clear APPROVE/REVISE verdict
-- Include specific file:line references in findings
-
-### MUST NOT
-
-- Skip the MANDATORY FIRST STEPS role loading
-- Modify source code directly
-- Produce unstructured output
-- Approve without actually reading the plan
-
----
-
-## Toolbox
-
-### Available Tools
-
-| Tool | Type | Purpose |
-|------|------|---------|
-| `Read` | builtin | Load plan artifacts and project files |
-| `Grep` | builtin | Search for patterns in codebase |
-| `Glob` | builtin | Find files by pattern |
-| `Bash` | builtin | Run build/test commands |
-
-### Tool Usage Patterns
-
-**Read Pattern**: Load context files before review
-```
-Read("{session_folder}/artifacts/bottleneck-report.md")
-Read("{session_folder}/artifacts/optimization-plan.md")
-Read("{session_folder}/discoveries.ndjson")
-```
-
----
-
-## Execution
-
-### Phase 1: Context Loading
-
-**Objective**: Load the plan or report to review.
-
-**Input**:
-
-| Source | Required | Description |
-|--------|----------|-------------|
-| Bottleneck report | Yes (if reviewing profiling) | Ranked bottleneck list from profiler |
-| Optimization plan | Yes (if reviewing strategy) | Prioritized plan from strategist |
-| Discoveries | No | Shared findings from prior stages |
-
-**Steps**:
-
-1. Read the artifact being reviewed from session artifacts folder
-2. Read discoveries.ndjson for additional context
-3. Identify which checkpoint this review corresponds to (CP-1 for profiling, CP-2 for strategy)
-
-**Output**: Loaded plan context for review
-
----
-
-### Phase 2: Plan Review
-
-**Objective**: Evaluate plan quality, completeness, and feasibility.
-
-**Steps**:
-
-1. **For bottleneck report review (CP-1)**:
-   - Verify all performance dimensions are covered (CPU, memory, I/O, network, rendering)
-   - Check that severity rankings are justified with measured evidence
-   - Validate baseline metrics are quantified with units and measurement method
-   - Check scope coverage matches original requirement
-
-2. **For optimization plan review (CP-2)**:
-   - Verify each optimization has unique OPT-ID and self-contained detail
-   - Check priority assignments follow impact/effort matrix
-   - Validate target files are non-overlapping between optimizations
-   - Verify success criteria are measurable with specific thresholds
-   - Check that implementation guidance is actionable
-   - Assess risk levels and potential side effects
-
-3. **Issue classification**:
-
-| Finding Severity | Condition | Impact |
-|------------------|-----------|--------|
-| Critical | Missing key profiling dimension or infeasible plan | REVISE required |
-| High | Unclear criteria or unrealistic targets | REVISE recommended |
-| Medium | Minor gaps in coverage or detail | Note for improvement |
-| Low | Style or formatting issues | Informational |
-
-**Output**: Review findings with severity classifications
-
----
-
-### Phase 3: Verdict
-
-**Objective**: Issue APPROVE or REVISE verdict.
-
-| Verdict | Condition | Action |
-|---------|-----------|--------|
-| APPROVE | No Critical or High findings | Plan is ready for next stage |
-| REVISE | Has Critical or High findings | Return specific feedback for revision |
-
-**Output**: Verdict with detailed feedback
-
----
-
-## Structured Output Template
-
-```
-## Summary
-- One-sentence verdict: APPROVE or REVISE with rationale
-
-## Findings
-- Finding 1: [severity] description with artifact reference
-- Finding 2: [severity] description with specific section reference
-
-## Verdict
-- APPROVE: Plan is ready for execution
-  OR
-- REVISE: Specific items requiring revision
-  1. Issue description + suggested fix
-  2. Issue description + suggested fix
-
-## Recommendations
-- Optional improvement suggestions (non-blocking)
-```
-
----
-
-## Error Handling
-
-| Scenario | Resolution |
-|----------|------------|
-| Artifact file not found | Report in findings, request re-generation |
-| Plan structure invalid | Report as Critical finding, REVISE verdict |
-| Scope mismatch | Report in findings, note for coordinator |
-| Timeout approaching | Output current findings with "PARTIAL" status |

package/.codex/skills/team-perf-opt/instructions/agent-instruction.md

@@ -1,122 +0,0 @@
-## TASK ASSIGNMENT
-
-### MANDATORY FIRST STEPS
-1. Read shared discoveries: {session_folder}/discoveries.ndjson (if exists, skip if not)
-2. Read project context: .workflow/project-tech.json (if exists)
-3. Read task schema: ~  or <project>/.codex/skills/team-perf-opt/schemas/tasks-schema.md
-
----
-
-## Your Task
-
-**Task ID**: {id}
-**Title**: {title}
-**Description**: {description}
-**Role**: {role}
-**Bottleneck Type**: {bottleneck_type}
-**Priority**: {priority}
-**Target Files**: {target_files}
-
-### Previous Tasks' Findings (Context)
-{prev_context}
-
----
-
-## Execution Protocol
-
-1. **Read discoveries**: Load {session_folder}/discoveries.ndjson for shared exploration findings
-2. **Use context**: Apply previous tasks' findings from prev_context above
-3. **Execute by role**:
-
-   **If role = profiler**:
-   - Detect project type by scanning for framework markers:
-     - Frontend (React/Vue/Angular): render time, bundle size, FCP/LCP/CLS
-     - Backend Node (Express/Fastify/NestJS): CPU hotspots, memory, DB queries
-     - Native/JVM Backend (Cargo/Go/Java): CPU, memory, GC tuning
-     - CLI Tool: startup time, throughput, memory peak
-   - Trace hot code paths and CPU hotspots within target scope
-   - Identify memory allocation patterns and potential leaks
-   - Measure I/O and network latency where applicable
-   - Collect quantified baseline metrics (timing, memory, throughput)
-   - Rank top 3-5 bottlenecks by severity (Critical/High/Medium)
-   - Record evidence: file paths, line numbers, measured values
-   - Write `{session_folder}/artifacts/baseline-metrics.json` (metrics)
-   - Write `{session_folder}/artifacts/bottleneck-report.md` (ranked bottlenecks)
-
-   **If role = strategist**:
-   - Read bottleneck report and baseline from {session_folder}/artifacts/
-   - For each bottleneck, select optimization strategy by type:
-     - CPU: algorithm optimization, memoization, caching, worker threads
-     - MEMORY: pool reuse, lazy init, WeakRef, scope cleanup
-     - IO: batching, async pipelines, streaming, connection pooling
-     - NETWORK: request coalescing, compression, CDN, prefetching
-     - RENDERING: virtualization, memoization, CSS containment, code splitting
-     - DATABASE: index optimization, query rewriting, caching layer
-   - Prioritize by impact/effort: P0 (high impact+low effort) to P3
-   - Assign unique OPT-IDs (OPT-001, 002, ...) with non-overlapping file targets
-   - Define measurable success criteria (target metric value or improvement %)
-   - Write `{session_folder}/artifacts/optimization-plan.md`
-
-   **If role = optimizer**:
-   - Read optimization plan from {session_folder}/artifacts/optimization-plan.md
-   - Apply optimizations in priority order (P0 first)
-   - Preserve existing behavior -- optimization must not break functionality
-   - Make minimal, focused changes per optimization
-   - Add comments only where optimization logic is non-obvious
-   - Preserve existing code style and conventions
-
-   **If role = benchmarker**:
-   - Read baseline from {session_folder}/artifacts/baseline-metrics.json
-   - Read plan from {session_folder}/artifacts/optimization-plan.md
-   - Run benchmarks matching detected project type:
-     - Frontend: bundle size, render performance
-     - Backend: endpoint response times, memory under load, DB query times
-     - CLI: execution time, memory peak, throughput
-   - Run test suite to verify no regressions
-   - Collect post-optimization metrics matching baseline format
-   - Calculate improvement percentages per metric
-   - Compare against plan success criteria
-   - Write `{session_folder}/artifacts/benchmark-results.json`
-   - Set verdict: PASS (meets criteria) / WARN (partial) / FAIL (regression or criteria not met)
-
-   **If role = reviewer**:
-   - Read plan from {session_folder}/artifacts/optimization-plan.md
-   - Review changed files across 5 dimensions:
-     - Correctness: logic errors, race conditions, null safety
-     - Side effects: unintended behavior changes, API contract breaks
-     - Maintainability: code clarity, complexity increase, naming
-     - Regression risk: impact on unrelated code paths
-     - Best practices: idiomatic patterns, no optimization anti-patterns
-   - Write `{session_folder}/artifacts/review-report.md`
-   - Set verdict: APPROVE / REVISE / REJECT
-
-4. **Share discoveries**: Append exploration findings to shared board:
-   ```bash
-   echo '{"ts":"<ISO8601>","worker":"{id}","type":"<type>","data":{...}}' >> {session_folder}/discoveries.ndjson
-   ```
-5. **Report result**: Return JSON via report_agent_job_result
-
-### Discovery Types to Share
-- `bottleneck_found`: `{type, location, severity, description}` -- Bottleneck identified
-- `hotspot_found`: `{file, function, cpu_pct, description}` -- CPU hotspot
-- `memory_issue`: `{file, type, size_mb, description}` -- Memory problem
-- `io_issue`: `{operation, latency_ms, description}` -- I/O issue
-- `db_issue`: `{query, latency_ms, description}` -- Database issue
-- `file_modified`: `{file, change, lines_added}` -- File change recorded
-- `metric_measured`: `{metric, value, unit, context}` -- Metric measured
-- `pattern_found`: `{pattern_name, location, description}` -- Pattern identified
-- `artifact_produced`: `{name, path, producer, type}` -- Deliverable created
-
----
-
-## Output (report_agent_job_result)
-
-Return JSON:
-{
-  "id": "{id}",
-  "status": "completed" | "failed",
-  "findings": "Key discoveries and implementation notes (max 500 chars)",
-  "verdict": "PASS|WARN|FAIL|APPROVE|REVISE|REJECT or empty",
-  "artifacts_produced": "semicolon-separated artifact paths",
-  "error": ""
-}

package/.codex/skills/team-perf-opt/schemas/tasks-schema.md

@@ -1,174 +0,0 @@
-# Team Performance Optimization -- CSV Schema
-
-## Master CSV: tasks.csv
-
-### Column Definitions
-
-#### Input Columns (Set by Decomposer)
-
-| Column | Type | Required | Description | Example |
-|--------|------|----------|-------------|---------|
-| `id` | string | Yes | Unique task identifier (PREFIX-NNN) | `"PROFILE-001"` |
-| `title` | string | Yes | Short task title | `"Profile performance"` |
-| `description` | string | Yes | Detailed task description (self-contained) with goal, inputs, outputs, success criteria | `"Profile application performance..."` |
-| `role` | enum | Yes | Worker role: `profiler`, `strategist`, `optimizer`, `benchmarker`, `reviewer` | `"profiler"` |
-| `bottleneck_type` | string | No | Performance bottleneck category: CPU, MEMORY, IO, NETWORK, RENDERING, DATABASE | `"CPU"` |
-| `priority` | enum | No | P0 (Critical), P1 (High), P2 (Medium), P3 (Low) | `"P0"` |
-| `target_files` | string | No | Semicolon-separated file paths to focus on | `"src/services/DataProcessor.ts"` |
-| `deps` | string | No | Semicolon-separated dependency task IDs | `"PROFILE-001"` |
-| `context_from` | string | No | Semicolon-separated task IDs for context | `"PROFILE-001"` |
-| `exec_mode` | enum | Yes | Execution mechanism: `csv-wave` or `interactive` | `"csv-wave"` |
-
-#### Computed Columns (Set by Wave Engine)
-
-| Column | Type | Description | Example |
-|--------|------|-------------|---------|
-| `wave` | integer | Wave number (1-based, from topological sort) | `2` |
-| `prev_context` | string | Aggregated findings from context_from tasks (per-wave CSV only) | `"[PROFILE-001] Found 3 CPU hotspots..."` |
-
-#### Output Columns (Set by Agent)
-
-| Column | Type | Description | Example |
-|--------|------|-------------|---------|
-| `status` | enum | `pending` -> `completed` / `failed` / `skipped` | `"completed"` |
-| `findings` | string | Key discoveries (max 500 chars) | `"Found 3 CPU hotspots, 1 memory leak..."` |
-| `verdict` | string | Benchmark/review verdict: PASS, WARN, FAIL, APPROVE, REVISE, REJECT | `"PASS"` |
-| `artifacts_produced` | string | Semicolon-separated paths of produced artifacts | `"artifacts/bottleneck-report.md"` |
-| `error` | string | Error message if failed | `""` |
-
----
-
-### exec_mode Values
-
-| Value | Mechanism | Description |
-|-------|-----------|-------------|
-| `csv-wave` | `spawn_agents_on_csv` | One-shot batch execution within wave |
-| `interactive` | `spawn_agent`/`wait`/`send_input`/`close_agent` | Multi-round individual execution |
-
-Interactive tasks appear in master CSV for dependency tracking but are NOT included in wave-{N}.csv files.
-
----
-
-### Role Prefix Mapping
-
-| Role | Prefix | Stage | Responsibility |
-|------|--------|-------|----------------|
-| profiler | PROFILE | 1 | Performance profiling, baseline metrics, bottleneck identification |
-| strategist | STRATEGY | 2 | Optimization plan design, strategy selection, prioritization |
-| optimizer | IMPL / FIX | 3 | Code implementation, optimization application, targeted fixes |
-| benchmarker | BENCH | 4 | Benchmark execution, before/after comparison, regression detection |
-| reviewer | REVIEW | 4 | Code review for correctness, side effects, regression risks |
-
----
-
-### Example Data
-
-```csv
-id,title,description,role,bottleneck_type,priority,target_files,deps,context_from,exec_mode,wave,status,findings,verdict,artifacts_produced,error
-"PROFILE-001","Profile performance","PURPOSE: Profile application performance to identify bottlenecks\nTASK:\n- Detect project type (frontend/backend/CLI)\n- Trace hot code paths and CPU hotspots\n- Identify memory allocation patterns and leaks\n- Measure I/O and network latency\n- Collect quantified baseline metrics\nINPUT: Codebase under target scope\nOUTPUT: artifacts/baseline-metrics.json + artifacts/bottleneck-report.md\nSUCCESS: Ranked bottleneck list with severity, baseline metrics collected\nSESSION: .workflow/.csv-wave/perf-example-20260308","profiler","","","","","","csv-wave","1","pending","","","",""
-"STRATEGY-001","Design optimization plan","PURPOSE: Design prioritized optimization plan from bottleneck report\nTASK:\n- For each bottleneck, select optimization strategy\n- Prioritize by impact/effort ratio (P0-P3)\n- Define measurable success criteria per optimization\n- Assign unique OPT-IDs with non-overlapping file targets\nINPUT: artifacts/bottleneck-report.md + artifacts/baseline-metrics.json\nOUTPUT: artifacts/optimization-plan.md\nSUCCESS: Prioritized plan with self-contained OPT blocks\nSESSION: .workflow/.csv-wave/perf-example-20260308","strategist","","","","PROFILE-001","PROFILE-001","csv-wave","2","pending","","","",""
-"IMPL-001","Implement optimizations","PURPOSE: Implement performance optimizations per plan\nTASK:\n- Apply optimizations in priority order (P0 first)\n- Preserve existing behavior\n- Make minimal, focused changes\nINPUT: artifacts/optimization-plan.md\nOUTPUT: Modified source files\nSUCCESS: All planned optimizations applied, no functionality regressions\nSESSION: .workflow/.csv-wave/perf-example-20260308","optimizer","","","","STRATEGY-001","STRATEGY-001","csv-wave","3","pending","","","",""
-"BENCH-001","Benchmark improvements","PURPOSE: Benchmark before/after optimization metrics\nTASK:\n- Run benchmarks matching detected project type\n- Compare post-optimization metrics vs baseline\n- Calculate improvement percentages\n- Detect any regressions\nINPUT: artifacts/baseline-metrics.json + artifacts/optimization-plan.md\nOUTPUT: artifacts/benchmark-results.json\nSUCCESS: All target improvements met, no regressions\nSESSION: .workflow/.csv-wave/perf-example-20260308","benchmarker","","","","IMPL-001","IMPL-001","csv-wave","4","pending","","","",""
-"REVIEW-001","Review optimization code","PURPOSE: Review optimization changes for correctness and quality\nTASK:\n- Correctness: logic errors, race conditions, null safety\n- Side effects: unintended behavior changes, API breaks\n- Maintainability: code clarity, complexity, naming\n- Regression risk: impact on unrelated code paths\n- Best practices: idiomatic patterns, no anti-patterns\nINPUT: artifacts/optimization-plan.md + changed files\nOUTPUT: artifacts/review-report.md\nSUCCESS: APPROVE verdict (no Critical/High findings)\nSESSION: .workflow/.csv-wave/perf-example-20260308","reviewer","","","","IMPL-001","IMPL-001","csv-wave","4","pending","","","",""
-```
-
----
-
-### Column Lifecycle
-
-```
-Decomposer (Phase 1)     Wave Engine (Phase 2)    Agent (Execution)
----------------------    --------------------     -----------------
-id          ---------->  id          ---------->  id
-title       ---------->  title       ---------->  (reads)
-description ---------->  description ---------->  (reads)
-role        ---------->  role        ---------->  (reads)
-bottleneck_type-------->  bottleneck_type-------->  (reads)
-priority    ---------->  priority    ---------->  (reads)
-target_files---------->  target_files---------->  (reads)
-deps        ---------->  deps        ---------->  (reads)
-context_from---------->  context_from---------->  (reads)
-exec_mode   ---------->  exec_mode   ---------->  (reads)
-                         wave         ---------->  (reads)
-                         prev_context ---------->  (reads)
-                                                   status
-                                                   findings
-                                                   verdict
-                                                   artifacts_produced
-                                                   error
-```
-
----
-
-## Output Schema (JSON)
-
-Agent output via `report_agent_job_result` (csv-wave tasks):
-
-```json
-{
-  "id": "PROFILE-001",
-  "status": "completed",
-  "findings": "Found 3 CPU hotspots: O(n^2) in DataProcessor.processRecords (Critical), unoptimized regex in Validator.check (High), synchronous file reads in ConfigLoader (Medium). Memory baseline: 145MB peak, 2 potential leak sites.",
-  "verdict": "",
-  "artifacts_produced": "artifacts/baseline-metrics.json;artifacts/bottleneck-report.md",
-  "error": ""
-}
-```
-
-Interactive tasks output via structured text or JSON written to `interactive/{id}-result.json`.
-
----
-
-## Discovery Types
-
-| Type | Dedup Key | Data Schema | Description |
-|------|-----------|-------------|-------------|
-| `bottleneck_found` | `data.location` | `{type, location, severity, description}` | Performance bottleneck identified |
-| `hotspot_found` | `data.file+data.function` | `{file, function, cpu_pct, description}` | CPU hotspot detected |
-| `memory_issue` | `data.file+data.type` | `{file, type, size_mb, description}` | Memory leak or bloat |
-| `io_issue` | `data.operation` | `{operation, latency_ms, description}` | I/O performance issue |
-| `db_issue` | `data.query` | `{query, latency_ms, description}` | Database performance issue |
-| `file_modified` | `data.file` | `{file, change, lines_added}` | File change recorded |
-| `metric_measured` | `data.metric+data.context` | `{metric, value, unit, context}` | Performance metric measured |
-| `pattern_found` | `data.pattern_name+data.location` | `{pattern_name, location, description}` | Code pattern identified |
-| `artifact_produced` | `data.path` | `{name, path, producer, type}` | Deliverable created |
-
-### Discovery NDJSON Format
-
-```jsonl
-{"ts":"2026-03-08T10:00:00Z","worker":"PROFILE-001","type":"bottleneck_found","data":{"type":"CPU","location":"src/services/DataProcessor.ts:145","severity":"Critical","description":"O(n^2) nested loop in processRecords, 850ms for 10k records"}}
-{"ts":"2026-03-08T10:01:00Z","worker":"PROFILE-001","type":"hotspot_found","data":{"file":"src/services/DataProcessor.ts","function":"processRecords","cpu_pct":42,"description":"Accounts for 42% of CPU time in profiling run"}}
-{"ts":"2026-03-08T10:02:00Z","worker":"PROFILE-001","type":"metric_measured","data":{"metric":"response_time_p95","value":1250,"unit":"ms","context":"GET /api/dashboard"}}
-{"ts":"2026-03-08T10:15:00Z","worker":"IMPL-001","type":"file_modified","data":{"file":"src/services/DataProcessor.ts","change":"Replaced O(n^2) with Map lookup O(n)","lines_added":12}}
-{"ts":"2026-03-08T10:25:00Z","worker":"BENCH-001","type":"metric_measured","data":{"metric":"response_time_p95","value":380,"unit":"ms","context":"GET /api/dashboard (after optimization)"}}
-```
-
-> Both csv-wave and interactive agents read/write the same discoveries.ndjson file.
-
----
-
-## Cross-Mechanism Context Flow
-
-| Source | Target | Mechanism |
-|--------|--------|-----------|
-| CSV task findings | Interactive task | Injected via spawn message or send_input |
-| Interactive task result | CSV task prev_context | Read from interactive/{id}-result.json |
-| Any agent discovery | Any agent | Shared via discoveries.ndjson |
-
----
-
-## Validation Rules
-
-| Rule | Check | Error |
-|------|-------|-------|
-| Unique IDs | No duplicate `id` values | "Duplicate task ID: {id}" |
-| Valid deps | All dep IDs exist in tasks | "Unknown dependency: {dep_id}" |
-| No self-deps | Task cannot depend on itself | "Self-dependency: {id}" |
-| No circular deps | Topological sort completes | "Circular dependency detected involving: {ids}" |
-| context_from valid | All context IDs exist and in earlier waves | "Invalid context_from: {id}" |
-| exec_mode valid | Value is `csv-wave` or `interactive` | "Invalid exec_mode: {value}" |
-| Description non-empty | Every task has description | "Empty description for task: {id}" |
-| Status enum | status in {pending, completed, failed, skipped} | "Invalid status: {status}" |
-| Role valid | role in {profiler, strategist, optimizer, benchmarker, reviewer} | "Invalid role: {role}" |
-| Verdict enum | verdict in {PASS, WARN, FAIL, APPROVE, REVISE, REJECT, ""} | "Invalid verdict: {verdict}" |
-| Cross-mechanism deps | Interactive to CSV deps resolve correctly | "Cross-mechanism dependency unresolvable: {id}" |