maestro-flow-one 0.2.23 → 0.2.25

package/maestro-flow/agents/workflow-collab-planner.md

@@ -42,9 +42,10 @@ You are a collaborative planner that works within a pre-allocated task ID range.
   "type": "feature",
   "priority": "medium",
   "effort": "medium",
-  "action": "Implement",
+  "action": "<concrete action with exact values: function signatures, config keys, import paths>",
   "scope": "<module path>",
   "focus_paths": [],
+  "read_first": ["src/module/existing.ts", "src/types/shared.ts"],
   "depends_on": [],
   "parallel_group": null,
   "convergence": {
@@ -116,6 +117,8 @@ You are a collaborative planner that works within a pre-allocated task ID range.
 - Task files must use `convergence.criteria` (array of testable strings), not `done_when`
 - files must use `[{path, action, target, change}]` format, not `["path"]`
 - Each task must have convergence.criteria with min 2 testable conditions
+- Each task must have `read_first[]` — files the executor MUST read before implementation
+- `action` must contain concrete values (function signatures, config keys, import paths), not just a verb
 - Task definitions follow the same schema as workflow-planner output
 - If you discover scope that belongs to another planner's range, note it in plan-note.md
 - Do not modify other planners' task files

package/maestro-flow/agents/workflow-plan-checker.md

@@ -30,7 +30,9 @@ You validate the quality of execution plans before they proceed to implementatio
    - Each criterion must reference a concrete artifact, output, or behavior
    - Criteria should be sufficient to prove the task is complete
 7. **Check files array** -- Verify each task's `files[]` array is consistent with its description
-8. **Report** -- Write check report with issues or approval
+8. **Check read_first** -- Verify each task has `read_first[]` containing: the file being modified + source-of-truth files. Missing or empty `read_first` is a critical issue.
+9. **Check action concreteness** -- Verify each task's `action` contains concrete values (function signatures, config keys, import paths), not vague verbs like "Implement" or references like "align X with Y"
+10. **Report** -- Write check report with issues or approval
 
 ### Revision Loop (max 3 rounds)
 - If issues found: write report with specific issues and suggested fixes
@@ -72,6 +74,14 @@ Check report written to the output location above:
 ## Files Array Consistency
 - TASK-006: description mentions "update config" but files[] does not include any config file
 
+## Read First Completeness
+- TASK-001 read_first: Missing — must include src/auth.ts (file being modified) + src/types/auth.ts (type definitions)
+- TASK-003 read_first: Has target file but missing source-of-truth reference
+
+## Action Concreteness
+- TASK-002 action: Too vague ("Implement auth") — should include: "Add verifyToken(token: string): Promise<AuthPayload> to src/auth.ts, import from jsonwebtoken"
+- TASK-005 action: Contains "align with existing pattern" — must specify the exact target state
+
 ## Summary
 <Overall assessment>
 ```

package/maestro-flow/agents/workflow-planner.md

@@ -92,9 +92,10 @@ When invoked with `quick` flag:
   "type": "feature",
   "priority": "medium",
   "effort": "medium",
-  "action": "Implement",
+  "action": "<concrete action with exact values: function signatures, config keys, import paths>",
   "scope": "<module path>",
   "focus_paths": ["src/tools/"],
+  "read_first": ["src/tools/existing-tool.ts", "src/types/tool.ts"],
   "depends_on": [],
   "parallel_group": null,
   "convergence": {
@@ -164,6 +165,8 @@ These rules prevent over-splitting that wastes tokens on unnecessary agent spawn
 - Each task must be substantial (15-60 min of work); group related changes, avoid file-per-task
 - Each task must have convergence.criteria (min 2 testable conditions)
 - convergence.criteria must be specific and testable (not "works correctly")
+- Each task must have `read_first[]` — files the executor MUST read before implementation (the file being modified + source-of-truth files)
+- `action` must contain concrete values (function signatures, config keys, import paths), not just a verb like "Implement"
 - files must use array format `[{path, action, target, change}]`
 - Wave ordering must respect dependencies (no task before its dependency)
 - Task descriptions must be clear enough for the executor to implement without ambiguity

package/maestro-flow/commands/lifecycle/analyze.md

@@ -48,7 +48,7 @@ $ARGUMENTS -- phase number for micro mode, topic text for macro/adhoc mode, no a
 - `-y` / `--yes`: Auto mode — skip interactive scoping, use recommended defaults, auto-deepen
 - `-c` / `--continue`: Resume from existing session (auto-detect session folder + discussion.md)
 - `-q` / `--quick`: Quick mode — skip exploration + scoring, go straight to decision extraction (context.md only)
-- `--from <source>`: Load upstream context package (brainstorm:ID, blueprint:BLP-xxx, @file, or path)
+- `--from <source>`: Load upstream context package (grill:ID, brainstorm:ID, blueprint:BLP-xxx, @file, or path)
 - `--gaps [ISS-ID]`: Issue root cause analysis mode. If ISS-ID provided, analyze single issue. If omitted, analyze all open/registered issues from issues.jsonl.
 
 Scope routing, output directory format, artifact registration schema, and output artifact listing are defined in workflow analyze.md (Scope Routing and Output Structure sections).

package/maestro-flow/commands/lifecycle/brainstorm.md

@@ -68,7 +68,7 @@ Interview the user relentlessly until shared understanding is reached. Active on
 - Branch jumps allowed: the user may switch freely between mode / role / upstream / sub-pipeline branches; sequence is not enforced, but every decision point must end with a definite answer.
 - Scope guard: only ask about decisions owned by `brainstorm`. Do not pre-resolve roadmap/plan choices.
 
-Decision points: mode (auto / single-role / review-only) / role selection and `--count` / `--from` upstream source / whether to enable design-research and the DESIGN.md sub-pipeline.
+Decision points: mode (auto / single-role / review-only) / role selection and `--count` / `--from` upstream source (grill:ID, blueprint:ID, @file, path) / whether to enable design-research and the DESIGN.md sub-pipeline.
 
 Exit: on consensus or explicit user signal to proceed, finalize session metadata. The §11 table (already populated incrementally) uses this schema:
 `| # | Decision | Choice | Source (user / code / default) |`
@@ -84,6 +84,7 @@ Auto mode:
 - Project initialized, need formal spec package → Skill({ skill: "maestro-blueprint", args: "--from brainstorm:{artifact_id}" })
 - Project initialized, quick roadmap → Skill({ skill: "maestro-roadmap", args: "--from brainstorm:{artifact_id}" })
 - Need deeper analysis first → Skill({ skill: "maestro-analyze", args: "{topic} --from brainstorm:{artifact_id}" })
+- Need stress-testing first → Skill({ skill: "maestro-grill", args: "{topic}" })
 - `html-prototypes/` produced with 2+ files and user wants to browse → load `~/.maestro/workflows/brainstorm-visualize.md` and launch visualizer server (optional, user-triggered)
 - DESIGN.md established during Step 3.5 → suggest: "Run `/maestro-impeccable build <feature-description>` to build with the established design system"
 

package/maestro-flow/commands/lifecycle/companion.md

@@ -0,0 +1,531 @@
+---
+name: maestro-companion
+description: Knowledge companion — load context, record companion doc, capture insights, route to skills
+argument-hint: "[before|note|after|route] [--task <description>] [--type <task_type>] [--category <cat>]"
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - Glob
+  - Grep
+  - Skill
+  - AskUserQuestion
+---
+
+<purpose>
+Task companion command — pairs with any task to provide knowledge context loading,
+structured companion document recording, insight capture, and skill routing.
+
+Does not create sessions or modify workflow state. Pure side-car utility.
+
+Four modes:
+- **before** — Pre-task: load spec + knowhow index + codebase index, create companion doc
+- **note** — Mid-task: append a structured entry to the active companion doc
+- **after** — Post-task: review companion doc, promote entries to spec/knowhow, suggest next steps
+- **route** — Routing: recommend next skill/command based on intent
+
+No arguments → auto-detect: uncommitted changes → `after`, else → `before`.
+</purpose>
+
+<context>
+$ARGUMENTS — mode + optional flags.
+
+**Mode detection priority:**
+1. Explicit `before` / `note` / `after` / `route`
+2. Intent text that is not a mode keyword → `route`
+3. No arguments → auto-detect (`git status` has changes → `after`, else → `before`)
+
+**Flags:**
+- `--task <description>` — Current task description (for targeted knowledge loading and doc title)
+- `--type <task_type>` — Task type for field template selection (see task types below)
+- `--category <cat>` — Spec category filter: coding / arch / test / review / debug / learning / ui
+
+**Task types** (determines which recording sections are active):
+
+| Type | Description | Key sections |
+|------|-------------|--------------|
+| `implement` | Feature development, code writing | working_files, dependencies, decisions, tests_affected |
+| `debug` | Bug investigation, root cause analysis | symptoms, hypotheses, evidence, root_cause, fix_applied |
+| `analyze` | Code/architecture/performance analysis | scope, findings, risks, recommendations |
+| `design` | Architecture/UI/API design | constraints, alternatives, trade_offs, chosen_approach |
+| `plan` | Task decomposition, roadmap planning | goals, breakdown, estimates, dependencies |
+| `review` | Code review, PR review | files_reviewed, findings, severity_counts, verdict |
+| `test` | Test writing, UAT, coverage expansion | coverage_before, coverage_after, gaps, test_files |
+| `refactor` | Code restructuring, tech debt | affected_modules, before_after, breaking_changes |
+| `learn` | Codebase exploration, knowledge building | questions, answers, mental_model, references |
+| `general` | Default / unclassified | (all universal sections) |
+
+Auto-detection: if `--type` not provided, infer from `--task` description keywords.
+
+**Companion document:**
+- Path: `.workflow/.scratchpad/companion-{YYYYMMDD-HHmmss}.md`
+- Active doc tracking: `.workflow/.scratchpad/.companion-active` (stores path of current companion doc)
+- Format: YAML frontmatter (rich metadata) + typed sections + timestamped entries
+</context>
+
+<state_machine>
+
+<states>
+S_PARSE    — Parse arguments, detect mode, resolve task type
+S_BEFORE   — Load knowledge context, create companion doc with typed template
+S_NOTE     — Append structured entry to active companion doc
+S_AFTER    — Review companion doc, populate outcome, promote entries, suggest next steps
+S_ROUTE    — Skill routing via maestro-next
+</states>
+
+<transitions>
+
+S_PARSE:
+  → S_BEFORE   WHEN: mode == "before" OR (no args AND no uncommitted changes)
+  → S_NOTE     WHEN: mode == "note"
+  → S_AFTER    WHEN: mode == "after" OR (no args AND has uncommitted changes)
+  → S_ROUTE    WHEN: mode == "route" OR intent text present
+
+</transitions>
+
+</state_machine>
+
+<execution>
+
+## S_BEFORE — Knowledge Loading + Companion Doc Creation
+
+Execute in order, skip unavailable steps:
+
+### 1. Load specs
+
+```bash
+# With --category: load by category
+maestro spec load --category <cat>
+
+# With --task: load by keyword extracted from task description
+maestro spec load --keyword <extracted_keyword>
+
+# No flags: load coding (most universal)
+maestro spec load --category coding
+```
+
+Display loaded rules summary (entry count + key rule names).
+
+### 2. Browse knowhow index
+
+```bash
+# List recent knowhow entries
+maestro knowhow list --store workflow
+
+# With --task: search relevant entries
+maestro knowhow search "<task_keyword>"
+```
+
+Display available knowhow entries (ID + title). Hint: `maestro wiki load <id>` for details.
+
+### 3. Check codebase index
+
+```bash
+ls .workflow/codebase/doc-index.json
+```
+
+- Exists → display "Codebase docs ready, last updated: {timestamp}"
+- Missing → suggest `/manage-codebase-rebuild`
+- Stale (>7 days) → suggest `/manage-codebase-refresh`
+
+### 4. Create companion document
+
+Create `.workflow/.scratchpad/` if needed. Resolve task type from `--type` flag or infer from `--task` keywords.
+
+Write companion doc with the full field template:
+
+```markdown
+---
+# === Identity ===
+task: "{task_description or 'Untitled task'}"
+task_type: "{resolved type: implement|debug|analyze|design|plan|review|test|refactor|learn|general}"
+created: "{ISO timestamp}"
+status: active
+
+# === Context Loaded ===
+specs_loaded: "{category or 'coding'}"
+specs_count: {N}
+knowhow_searched: "{keyword or 'none'}"
+knowhow_available: {M}
+codebase_index: "{ready|missing|stale}"
+branch: "{current git branch}"
+phase: "{current phase from state.json or 'none'}"
+milestone: "{current milestone from state.json or 'none'}"
+
+# === Scope ===
+working_files: []
+dependencies: []
+related_artifacts: []
+
+# === Outcome (populated by after mode) ===
+outcome: ""
+files_changed: []
+promoted_specs: 0
+promoted_knowhow: 0
+follow_up: []
+completed: ""
+---
+
+# Companion Doc — {task_description}
+
+> `/maestro-companion note "<content>"` — add entries
+> `/maestro-companion after` — review, promote, close
+
+## Context
+
+{Type-specific context section — see templates below}
+
+## Entries
+
+## Summary
+```
+
+**Type-specific context templates** (written into `## Context`):
+
+**implement:**
+```markdown
+### Working Files
+| File | Role | Status |
+|------|------|--------|
+
+### Dependencies
+- (modules, APIs, or services this task depends on)
+
+### Decisions
+| # | Decision | Rationale | Alternatives Considered |
+|---|----------|-----------|------------------------|
+
+### Tests Affected
+- (test files that need creation or update)
+```
+
+**debug:**
+```markdown
+### Symptoms
+- (observable behavior vs expected behavior)
+
+### Hypotheses
+| # | Hypothesis | Status | Evidence |
+|---|-----------|--------|----------|
+
+### Evidence Trail
+| Time | Source | Type | Finding |
+|------|--------|------|---------|
+
+### Root Cause
+- (populated when identified)
+
+### Fix Applied
+- (description of fix, files changed)
+```
+
+**analyze:**
+```markdown
+### Scope
+- (what is being analyzed and boundaries)
+
+### Findings
+| # | Finding | Severity | Location |
+|---|---------|----------|----------|
+
+### Risks
+- (identified risks or concerns)
+
+### Recommendations
+- (actionable recommendations)
+```
+
+**design:**
+```markdown
+### Constraints
+- (hard limits, requirements, compatibility needs)
+
+### Alternatives
+| # | Approach | Pros | Cons |
+|---|----------|------|------|
+
+### Trade-offs
+- (key trade-off decisions and rationale)
+
+### Chosen Approach
+- (selected design with justification)
+```
+
+**plan:**
+```markdown
+### Goals
+- (what success looks like)
+
+### Breakdown
+| # | Task | Estimate | Depends On | Status |
+|---|------|----------|------------|--------|
+
+### Dependencies
+- (external dependencies, blockers, prerequisites)
+```
+
+**review:**
+```markdown
+### Files Reviewed
+| File | Lines | Findings |
+|------|-------|----------|
+
+### Findings
+| # | Severity | Category | File:Line | Description |
+|---|----------|----------|-----------|-------------|
+
+### Verdict
+- (pass / pass-with-concerns / fail)
+```
+
+**test:**
+```markdown
+### Coverage
+- Before: {%}
+- After: {%}
+- Target: {%}
+
+### Test Files
+| File | Type | Tests Added | Status |
+|------|------|------------|--------|
+
+### Gaps
+- (uncovered paths or scenarios)
+```
+
+**refactor:**
+```markdown
+### Affected Modules
+- (modules being restructured)
+
+### Before / After
+| Aspect | Before | After |
+|--------|--------|-------|
+
+### Breaking Changes
+- (API or behavior changes that affect consumers)
+```
+
+**learn:**
+```markdown
+### Questions
+| # | Question | Answered | Source |
+|---|----------|----------|--------|
+
+### Mental Model
+- (evolving understanding of how it works)
+
+### References
+- (files, docs, wiki entries consulted)
+```
+
+**general:**
+```markdown
+### Notes
+- (general working notes)
+```
+
+Write the companion doc path to `.workflow/.scratchpad/.companion-active`.
+
+### 5. Output summary card
+
+```
+Knowledge context loaded
+  Spec:     {N} rules ({category})
+  Knowhow:  {M} entries available
+  Codebase: {status}
+  Doc:      {companion_doc_path} [{task_type}]
+
+Mid-task commands:
+  /maestro-companion note "finding or decision"
+  /maestro-companion note --file src/auth.ts "changed token validation"
+  /spec-load --keyword <keyword>
+  maestro wiki search "<query>"
+```
+
+---
+
+## S_NOTE — Append Structured Entry to Companion Doc
+
+### 1. Locate active companion doc
+
+Read `.workflow/.scratchpad/.companion-active` to get the doc path.
+If missing or file not found → create a new companion doc (same as S_BEFORE step 4, minimal — no spec/knowhow loading).
+
+### 2. Parse entry content and flags
+
+Parse $ARGUMENTS after `note` keyword:
+- `--file <path>` — associate entry with a specific file (appended to frontmatter `working_files`)
+- `--severity <level>` — for findings: critical / high / medium / low
+- Remaining text = entry content
+
+### 3. Classify entry type
+
+Auto-classify from content signals:
+
+| Content signal | Type tag |
+|---------------|----------|
+| "decided/decision/chose/picked/went with" | `decision` |
+| "pattern/convention/rule/always/never/must" | `spec-candidate` |
+| "pitfall/gotcha/careful/warning/trap/beware" | `pitfall` |
+| "learned/realized/discovered/understood/turns out" | `insight` |
+| "hypothesis/suspect/might be/could be" | `hypothesis` |
+| "found bug/root cause/because of/caused by" | `evidence` |
+| "risk/concern/worry/might break" | `risk` |
+| "todo/need to/should also/follow up/remaining" | `todo` |
+| "question/why does/how does/unclear" | `question` |
+| "blocked/stuck/can't/impossible" | `blocker` |
+| Default | `note` |
+
+### 4. Append entry
+
+Append to the companion doc under `## Entries`:
+
+```markdown
+### [{type}] {HH:mm} — {first line of content}
+
+{full content}
+
+{if --file: **File:** `{path}`}
+{if --severity: **Severity:** {level}}
+```
+
+### 5. Update frontmatter fields
+
+- If `--file` provided and not already in `working_files` → append to `working_files`
+- If type is `decision` → also append row to `### Decisions` table (if implement/design type doc)
+- If type is `hypothesis` → also append row to `### Hypotheses` table (if debug type doc)
+- If type is `evidence` → also append row to `### Evidence Trail` table (if debug type doc)
+- If type is `risk` → also append to `### Risks` list (if analyze/design type doc)
+- If type is `question` → also append row to `### Questions` table (if learn type doc)
+
+### 6. Confirm
+
+```
+[{type}] entry added to companion doc
+  /maestro-companion note "..."  — add more
+  /maestro-companion after       — review & promote
+```
+
+---
+
+## S_AFTER — Review Companion Doc + Populate Outcome + Promote Entries + Route
+
+### 1. Load companion doc
+
+Read `.workflow/.scratchpad/.companion-active` → read the companion doc.
+If no active doc or doc is empty → skip to step 4 (accumulation reminder).
+
+### 2. Populate outcome fields
+
+Collect task outcome data:
+
+```bash
+# Detect files changed since companion doc creation
+git diff --name-only --since="{companion_created_timestamp}"
+```
+
+Update frontmatter:
+- `files_changed` — from git diff
+- `completed` — current ISO timestamp
+- `status` — `completed`
+
+Display entry summary:
+```
+Companion doc review — {task_type}
+  Entries:    {total} ({by type breakdown})
+  Files:      {files_changed count} changed
+  Duration:   {elapsed since created}
+
+Promotable entries:
+  {list of decision/spec-candidate/pitfall/insight entries}
+```
+
+### 3. Promote entries
+
+If promotable entries exist, AskUserQuestion:
+
+- Option 1: "Promote to spec" — short coding/arch/test constraint
+- Option 2: "Promote to knowhow" — detailed recipe/template/decision/tip
+- Option 3: "Promote both" — spec index entry + knowhow document
+- Option 4: "Skip — nothing to promote"
+
+**Routing by selection:**
+
+| Selection | Action |
+|-----------|--------|
+| Spec | `Skill("spec-add", args)` — guide user through category + content |
+| Knowhow | `Skill("manage-knowhow-capture", args)` — guide through type + content |
+| Both | `Skill("spec-add")` first, then `Skill("manage-knowhow-capture")` |
+| Skip | Proceed to step 4 |
+
+Update frontmatter: `promoted_specs`, `promoted_knowhow` counts.
+
+Extract any `todo` entries → write to `follow_up` in frontmatter.
+
+Clear `.workflow/.scratchpad/.companion-active`.
+
+### 4. Output accumulation reminder + routing
+
+```
+Knowledge accumulation reminders:
+  Reusable pattern found?        /spec-add <category> "title" "content"
+  Solved a complex problem?      /manage-knowhow-capture recipe "description"
+  Made an architecture decision? /manage-knowhow-capture decision "description"
+  Discovered a useful trick?     /manage-knowhow-capture tip "content"
+
+Next steps:
+  /maestro-next          — recommend next command
+  /maestro "<intent>"    — route intent to full workflow
+  /manage-status         — view project dashboard
+```
+
+---
+
+## S_ROUTE — Skill Routing
+
+### 1. Parse intent
+
+Extract intent text from $ARGUMENTS after removing the `route` keyword.
+
+### 2. Delegate to maestro-next
+
+```
+Skill("maestro-next", "<intent_text>")
+```
+
+Reuses maestro-next routing table and scoring logic to recommend the best single command.
+
+</execution>
+
+<error_codes>
+| Code | Severity | Condition | Recovery |
+|------|----------|-----------|----------|
+| W001 | warning | `.workflow/specs/` not initialized | Suggest `/spec-setup` |
+| W002 | warning | `.workflow/knowhow/` is empty | Normal, skip knowhow index |
+| W003 | warning | `.workflow/codebase/` does not exist | Suggest `/manage-codebase-rebuild` |
+| W004 | warning | No active companion doc found (note/after mode) | Create new doc or skip |
+</error_codes>
+
+<success_criteria>
+- [ ] Mode correctly detected (before/note/after/route)
+- [ ] Task type resolved from --type flag or inferred from --task keywords
+- [ ] before: spec + knowhow + codebase indexes loaded or hints given
+- [ ] before: companion doc created with full YAML frontmatter (identity + context + scope + outcome placeholders)
+- [ ] before: type-specific context template written (matching task_type)
+- [ ] before: active doc path written to `.companion-active`
+- [ ] before: summary card output with mid-task command hints
+- [ ] note: active companion doc located and entry appended with type tag
+- [ ] note: entry type auto-classified from content signals (11 type tags)
+- [ ] note: --file flag updates working_files in frontmatter
+- [ ] note: typed entries cross-posted to matching context tables (decisions→Decisions, hypothesis→Hypotheses, etc.)
+- [ ] after: companion doc entries reviewed and promotable items identified
+- [ ] after: outcome fields populated (files_changed, completed, status)
+- [ ] after: AskUserQuestion routes to spec-add or manage-knowhow-capture
+- [ ] after: todo entries extracted to follow_up field
+- [ ] after: companion doc marked completed, active pointer cleared
+- [ ] after: accumulation reminder + next-step routing displayed
+- [ ] route: intent correctly forwarded to maestro-next
+- [ ] No session created, no state.json modified
+</success_criteria>