$csv-wave-pipeline "Implement user authentication with OAuth, JWT, and 2FA"
$csv-wave-pipeline -c 4 "Refactor payment module with Stripe and PayPal"
$csv-wave-pipeline -y "Build notification system with email and SMS"
$csv-wave-pipeline --continue "auth-20260228"

• -y, --yes

  : Skip all confirmations (auto mode)

• -c, --concurrency N

  : Max concurrent agents within each wave (default: 4)

• --continue

  : Resume existing session

.workflow/.csv-wave/{session-id}/

tasks.csv

results.csv

discoveries.ndjson

context.md

1. Decompose Requirement
   javascript

   // Use ccw cli to decompose requirement into subtasks
   Bash({
     command: `ccw cli -p "PURPOSE: Decompose requirement into 3-10 atomic tasks for batch agent execution. Each task must include implementation description, test cases, and acceptance criteria.

• description: what to implement (specific enough for an agent to execute independently)
• test: what tests to write and how to verify (e.g. 'Unit test: X returns Y; Edge test: handles Z')
• acceptance_criteria: measurable conditions that define done (e.g. 'API returns 200; token expires after 1h')
• scope: target file/directory glob (e.g. 'src/auth/**') — tasks in same wave MUST have non-overlapping scopes
• hints: implementation tips + reference files, format '<tips> || <ref_file1>;<ref_file2>' (e.g. 'Use strategy pattern || src/base/Strategy.ts;docs/design.md')
• execution_directives: commands to run for verification or tool constraints (e.g. 'Run npm test --bail; Ensure tsc passes')
• deps: task IDs that must complete first
• context_from: task IDs whose findings are needed CONSTRAINTS: 3-10 tasks | Each task is atomic | No circular deps | test and acceptance_criteria must be concrete and verifiable | Same-wave tasks must have non-overlapping scopes

2. **Compute Waves** (Topological Sort → Depth Grouping)

```javascript
function computeWaves(tasks) {
  // Build adjacency: task.deps → predecessors
  const taskMap = new Map(tasks.map(t => [t.id, t]))
  const inDegree = new Map(tasks.map(t => [t.id, 0]))
  const adjList = new Map(tasks.map(t => [t.id, []]))

  for (const task of tasks) {
    for (const dep of task.deps) {
      if (taskMap.has(dep)) {
        adjList.get(dep).push(task.id)
        inDegree.set(task.id, inDegree.get(task.id) + 1)
      }
    }
  }

  // BFS-based topological sort with depth tracking
  const queue = []  // [taskId, depth]
  const waveAssignment = new Map()

  for (const [id, deg] of inDegree) {
    if (deg === 0) {
      queue.push([id, 1])
      waveAssignment.set(id, 1)
    }
  }

  let maxWave = 1
  let idx = 0
  while (idx < queue.length) {
    const [current, depth] = queue[idx++]
    for (const next of adjList.get(current)) {
      const newDeg = inDegree.get(next) - 1
      inDegree.set(next, newDeg)
      const nextDepth = Math.max(waveAssignment.get(next) || 0, depth + 1)
      waveAssignment.set(next, nextDepth)
      if (newDeg === 0) {
        queue.push([next, nextDepth])
        maxWave = Math.max(maxWave, nextDepth)
      }
    }
  }

  // Detect cycles: any task without wave assignment
  for (const task of tasks) {
    if (!waveAssignment.has(task.id)) {
      throw new Error(`Circular dependency detected involving task ${task.id}`)
    }
  }

  return { waveAssignment, maxWave }
}

const { waveAssignment, maxWave } = computeWaves(decomposedTasks)

1. Generate tasks.csv
   javascript

   const header = 'id,title,description,test,acceptance_criteria,scope,hints,execution_directives,deps,context_from,wave,status,findings,files_modified,tests_passed,acceptance_met,error'
   const rows = decomposedTasks.map(task => {
     const wave = waveAssignment.get(task.id)
     return [
       task.id,
       csvEscape(task.title),
       csvEscape(task.description),
       csvEscape(task.test),
       csvEscape(task.acceptance_criteria),
       csvEscape(task.scope),
       csvEscape(task.hints),
       csvEscape(task.execution_directives),
       task.deps.join(';'),
       task.context_from.join(';'),
       wave,
       'pending',  // status
       '',         // findings
       '',         // files_modified
       '',         // tests_passed
       '',         // acceptance_met
       ''          // error
     ].map(cell => `"${String(cell).replace(/"/g, '""')}"`).join(',')
   })
   
   Write(`${sessionFolder}/tasks.csv`, [header, ...rows].join('\n'))

2. User Validation (skip if AUTO_YES)
   javascript

   if (!AUTO_YES) {
     // Display task breakdown with wave assignment
     console.log(`\n## Task Breakdown (${decomposedTasks.length} tasks, ${maxWave} waves)\n`)
     for (let w = 1; w <= maxWave; w++) {
       const waveTasks = decomposedTasks.filter(t => waveAssignment.get(t.id) === w)
       console.log(`### Wave ${w} (${waveTasks.length} tasks, concurrent)`)
       waveTasks.forEach(t => console.log(`  - [${t.id}] ${t.title}`))
     }
   
     const answer = AskUserQuestion({
       questions: [{
         question: "Approve task breakdown?",
         header: "Validation",
         multiSelect: false,
         options: [
           { label: "Approve", description: "Proceed with wave execution" },
           { label: "Modify", description: `Edit ${sessionFolder}/tasks.csv manually, then --continue` },
           { label: "Cancel", description: "Abort" }
         ]
       }]
     })  // BLOCKS
   
     if (answer.Validation === "Modify") {
       console.log(`Edit: ${sessionFolder}/tasks.csv\nResume: $csv-wave-pipeline --continue`)
       return
     } else if (answer.Validation === "Cancel") {
       return
     }
   }

• tasks.csv created with valid schema and wave assignments
• No circular dependencies
• User approved (or AUTO_YES)

spawn_agents_on_csv

1. Wave Loop
   javascript

   const failedIds = new Set()
   const skippedIds = new Set()
   
   for (let wave = 1; wave <= maxWave; wave++) {
     console.log(`\n## Wave ${wave}/${maxWave}\n`)
   
     // 1. Read current master CSV
     const masterCsv = parseCsv(Read(`${sessionFolder}/tasks.csv`))
   
     // 2. Filter tasks for this wave
     const waveTasks = masterCsv.filter(row => parseInt(row.wave) === wave)
   
     // 3. Skip tasks whose deps failed
     const executableTasks = []
     for (const task of waveTasks) {
       const deps = task.deps.split(';').filter(Boolean)
       if (deps.some(d => failedIds.has(d) || skippedIds.has(d))) {
         skippedIds.add(task.id)
         // Update master CSV: mark as skipped
         updateMasterCsvRow(sessionFolder, task.id, {
           status: 'skipped',
           error: 'Dependency failed or skipped'
         })
         console.log(`  [${task.id}] ${task.title} → SKIPPED (dependency failed)`)
         continue
       }
       executableTasks.push(task)
     }
   
     if (executableTasks.length === 0) {
       console.log(`  No executable tasks in wave ${wave}`)
       continue
     }
   
     // 4. Build prev_context for each task
     for (const task of executableTasks) {
       const contextIds = task.context_from.split(';').filter(Boolean)
       const prevFindings = contextIds
         .map(id => {
           const prevRow = masterCsv.find(r => r.id === id)
           if (prevRow && prevRow.status === 'completed' && prevRow.findings) {
             return `[Task ${id}: ${prevRow.title}] ${prevRow.findings}`
           }
           return null
         })
         .filter(Boolean)
         .join('\n')
       task.prev_context = prevFindings || 'No previous context available'
     }
   
     // 5. Write wave CSV
     const waveHeader = 'id,title,description,test,acceptance_criteria,scope,hints,execution_directives,deps,context_from,wave,prev_context'
     const waveRows = executableTasks.map(t =>
       [t.id, t.title, t.description, t.test, t.acceptance_criteria, t.scope, t.hints, t.execution_directives, t.deps, t.context_from, t.wave, t.prev_context]
         .map(cell => `"${String(cell).replace(/"/g, '""')}"`)
         .join(',')
     )
     Write(`${sessionFolder}/wave-${wave}.csv`, [waveHeader, ...waveRows].join('\n'))
   
     // 6. Execute wave
     console.log(`  Executing ${executableTasks.length} tasks (concurrency: ${maxConcurrency})...`)
   
     const waveResult = spawn_agents_on_csv({
       csv_path: `${sessionFolder}/wave-${wave}.csv`,
       id_column: "id",
       instruction: buildInstructionTemplate(sessionFolder, wave),
       max_concurrency: maxConcurrency,
       max_runtime_seconds: 600,
       output_csv_path: `${sessionFolder}/wave-${wave}-results.csv`,
       output_schema: {
         type: "object",
         properties: {
           id: { type: "string" },
           status: { type: "string", enum: ["completed", "failed"] },
           findings: { type: "string" },
           files_modified: { type: "array", items: { type: "string" } },
           tests_passed: { type: "boolean" },
           acceptance_met: { type: "string" },
           error: { type: "string" }
         },
         required: ["id", "status", "findings", "tests_passed"]
       }
     })
     // ↑ Blocks until all agents in this wave complete
   
     // 7. Merge results into master CSV
     const waveResults = parseCsv(Read(`${sessionFolder}/wave-${wave}-results.csv`))
     for (const result of waveResults) {
       updateMasterCsvRow(sessionFolder, result.id, {
         status: result.status,
         findings: result.findings || '',
         files_modified: (result.files_modified || []).join(';'),
         tests_passed: String(result.tests_passed ?? ''),
         acceptance_met: result.acceptance_met || '',
         error: result.error || ''
       })
   
       if (result.status === 'failed') {
         failedIds.add(result.id)
         console.log(`  [${result.id}] ${result.title} → FAILED: ${result.error}`)
       } else {
         console.log(`  [${result.id}] ${result.title} → COMPLETED`)
       }
     }
   
     // 8. Cleanup temporary wave CSV
     Bash(`rm -f "${sessionFolder}/wave-${wave}.csv"`)
   
     console.log(`  Wave ${wave} done: ${waveResults.filter(r => r.status === 'completed').length} completed, ${waveResults.filter(r => r.status === 'failed').length} failed`)
   }

2. Instruction Template Builder
   javascript

   function buildInstructionTemplate(sessionFolder, wave) {
     return `

1. Read shared discoveries: ${sessionFolder}/discoveries.ndjson (if exists, skip if not)
2. Read project context: .workflow/project-tech.json (if exists)

Format: `<tips> || <ref_file1>;<ref_file2>`. Read ALL reference files (after ||) before starting implementation. Apply tips (before ||) as implementation guidance.

Commands to run for verification, tool restrictions, or environment requirements. Follow these constraints during and after implementation.

1. Read references: Parse {hints} — read all files listed after `||` to understand existing patterns
2. Read discoveries: Load ${sessionFolder}/discoveries.ndjson for shared exploration findings
3. Use context: Apply previous tasks' findings from prev_context above
4. Stay in scope: ONLY create/modify files within {scope} — do NOT touch files outside this boundary
5. Apply hints: Follow implementation tips from {hints} (before `||`)
6. Execute: Implement the task as described
7. Write tests: Implement the test cases defined above
8. Run directives: Execute commands from {execution_directives} to verify your work
9. Verify acceptance: Ensure all acceptance criteria are met before reporting completion
10. Share discoveries: Append exploration findings to shared board: ```bash echo '{"ts":"<ISO8601>","worker":"{id}","type":"<type>","data":{...}}' >> ${sessionFolder}/discoveries.ndjson ```
11. Report result: Return JSON via report_agent_job_result

• `code_pattern`: {name, file, description} — reusable patterns found
• `integration_point`: {file, description, exports[]} — module connection points
• `convention`: {naming, imports, formatting} — code style conventions
• `blocker`: {issue, severity, impact} — blocking issues encountered

• All test cases pass
• All acceptance criteria are met Otherwise set status to "failed" with details in error field. ` }

  undefined

1. Master CSV Update Helper
   javascript

   function updateMasterCsvRow(sessionFolder, taskId, updates) {
     const csvPath = `${sessionFolder}/tasks.csv`
     const content = Read(csvPath)
     const lines = content.split('\n')
     const header = lines[0].split(',')
   
     for (let i = 1; i < lines.length; i++) {
       const cells = parseCsvLine(lines[i])
       if (cells[0] === taskId || cells[0] === `"${taskId}"`) {
         // Update specified columns
         for (const [col, val] of Object.entries(updates)) {
           const colIdx = header.indexOf(col)
           if (colIdx >= 0) {
             cells[colIdx] = `"${String(val).replace(/"/g, '""')}"`
           }
         }
         lines[i] = cells.join(',')
         break
       }
     }
   
     Write(csvPath, lines.join('\n'))
   }

• All waves executed in order
• Each wave's results merged into master CSV before next wave starts
• Dependent tasks skipped when predecessor failed
• discoveries.ndjson accumulated across all waves

1. Export results.csv
   javascript

   const masterCsv = Read(`${sessionFolder}/tasks.csv`)
   // results.csv = master CSV (already has all results populated)
   Write(`${sessionFolder}/results.csv`, masterCsv)

2. Generate context.md
   javascript

   const tasks = parseCsv(masterCsv)
   const completed = tasks.filter(t => t.status === 'completed')
   const failed = tasks.filter(t => t.status === 'failed')
   const skipped = tasks.filter(t => t.status === 'skipped')
   
   const contextContent = `# CSV Batch Execution Report

• Session: ${sessionId}
• Waves: ${maxWave}
• Completed: ${completed.length}/${tasks.length}
• Failed: ${failed.length}
• Skipped: ${skipped.length}

4. **Offer Next Steps** (skip if AUTO_YES)

```javascript
if (!AUTO_YES && failed.length > 0) {
  const answer = AskUserQuestion({
    questions: [{
      question: `${failed.length} tasks failed. Next action?`,
      header: "Next Step",
      multiSelect: false,
      options: [
        { label: "Retry Failed", description: `Re-execute ${failed.length} failed tasks with updated context` },
        { label: "View Report", description: "Display context.md" },
        { label: "Done", description: "Complete session" }
      ]
    }]
  })  // BLOCKS

  if (answer['Next Step'] === "Retry Failed") {
    // Reset failed tasks to pending, re-run Phase 2 for their waves
    for (const task of failed) {
      updateMasterCsvRow(sessionFolder, task.id, { status: 'pending', error: '' })
    }
    // Also reset skipped tasks whose deps are now retrying
    for (const task of skipped) {
      updateMasterCsvRow(sessionFolder, task.id, { status: 'pending', error: '' })
    }
    // Re-execute Phase 2 (loop will skip already-completed tasks)
    // → goto Phase 2
  } else if (answer['Next Step'] === "View Report") {
    console.log(Read(`${sessionFolder}/context.md`))
  }
}

• results.csv exported
• context.md generated
• Summary displayed to user

discoveries.ndjson

• Created by the first agent to write a discovery
• Carries over across waves — never cleared
• Agents append via

  echo '...' >> discoveries.ndjson

{"ts":"2026-02-28T10:00:00+08:00","worker":"1","type":"code_pattern","data":{"name":"repository-pattern","file":"src/repos/Base.ts","description":"Abstract CRUD repository"}}
{"ts":"2026-02-28T10:01:00+08:00","worker":"2","type":"integration_point","data":{"file":"src/auth/index.ts","description":"Auth module entry","exports":["authenticate","authorize"]}}

code_pattern

data.name

integration_point

data.file

convention

blocker

data.issue

tech_stack

test_command

1. Read board before own exploration → skip covered areas
2. Write discoveries immediately via

   echo >>

   → don't batch
3. Deduplicate — check existing entries; skip if same type + dedup key exists
4. Append-only — never modify or delete existing lines