maestro-flow 0.5.36 → 0.5.37

package/.codex/skills/odyssey-planex/SKILL.md

@@ -115,9 +115,9 @@ SESSION_DIR/
 |------|------|------|
 | Codebase docs | Read `.workflow/codebase/ARCHITECTURE.md` | 模块边界 |
 | Wiki search | `maestro search "<requirement keywords>" --json` | 先前实现（top 5） |
-| Coding specs | `maestro spec load --category coding` | 编码规范 + knowhow 工具 |
-| UI specs（条件） | 若涉及前端 → `maestro spec load --category ui` | UI 规范 |
-| Role knowledge | `maestro search --category coding` → 选相关 → `maestro wiki load <id>` | 领域知识 |
+| Coding specs | `maestro load --type spec --category coding` | 编码规范 + knowhow 工具 |
+| UI specs（条件） | 若涉及前端 → `maestro load --type spec --category ui` | UI 规范 |
+| Role knowledge | `maestro search --category coding` → 选相关 → `maestro load --type knowhow --id <id>` | 领域知识 |
 | Prior sessions | `Glob(".workflow/scratch/*-planex-odyssey-*")` | 相关会话 |
 
 ### Knowledge Persistence（S_RECORD 中写入产出文件）

package/.codex/skills/odyssey-review-test-fix/SKILL.md

@@ -112,8 +112,8 @@ Lifecycle: `pending → done | skipped | failed` (all set `completion_confirmed`
 |------|------|------|
 | Codebase docs | Read `.workflow/codebase/ARCHITECTURE.md` | 模块边界 |
 | Wiki search | `maestro search "<target keywords>" --json` | 先前 review（top 5） |
-| Specs | `maestro spec load --category review` | review 标准、checklist |
-| Role knowledge | `maestro search --category review` → 选相关 → `maestro wiki load <id>` | 领域知识 |
+| Specs | `maestro load --type spec --category review` | review 标准、checklist |
+| Role knowledge | `maestro search --category review` → 选相关 → `maestro load --type knowhow --id <id>` | 领域知识 |
 | Prior sessions | `Glob(".workflow/scratch/*-review-odyssey-*")` | 相关会话 |
 
 ### Knowledge Persistence（S_RECORD 中写入产出文件）

package/.codex/skills/odyssey-ui/SKILL.md

@@ -114,9 +114,9 @@ Lifecycle: `pending -> done | skipped | failed` (all set `completion_confirmed`)
 |-------|---------|---------|
 | Codebase docs | Read `.workflow/codebase/ARCHITECTURE.md` | Module boundaries |
 | Wiki search | `maestro search "<target keywords>" --json` | Prior UI decisions (top 5) |
-| UI specs | `maestro spec load --category ui` | Design tokens, standards |
-| Coding specs | `maestro spec load --category coding` | Coding conventions |
-| Role knowledge | `maestro search --category ui` -> select -> `maestro wiki load <id>` | Domain knowledge |
+| UI specs | `maestro load --type spec --category ui` | Design tokens, standards |
+| Coding specs | `maestro load --type spec --category coding` | Coding conventions |
+| Role knowledge | `maestro search --category ui` -> select -> `maestro load --type knowhow --id <id>` | Domain knowledge |
 | Prior sessions | `Glob(".workflow/scratch/*-ui-odyssey-*")` | Related sessions |
 
 ### Knowledge Persistence (two-step model)

package/.codex/skills/quality-debug/SKILL.md

@@ -208,7 +208,7 @@ mkdir -p {sessionFolder}
 2b. **Load codebase + wiki context** (optional, informs hypothesis generation):
    - If `.workflow/codebase/ARCHITECTURE.md` exists: read module boundaries to scope impact analysis
    - Run `maestro search "<symptom keywords>" --json 2>/dev/null`; if results: check for prior investigations on similar issues
-   - Run `maestro spec load --category debug --keyword "<symptom keywords>"`; if tools found: extract known issues, workarounds, and root-cause notes to inform hypotheses
+   - Run `maestro load --type spec --category debug --keyword "<symptom keywords>"`; if tools found: extract known issues, workarounds, and root-cause notes to inform hypotheses
    - All are optional — proceed without if unavailable
 
 3. **Symptom collection**:

package/.codex/skills/quality-refactor/SKILL.md

@@ -123,7 +123,7 @@ Create `.workflow/scratch/refactor-{slug}-{date}/` with `.task/` and `.summaries
 
 ### Step 3: Scope Analysis
 
-Load project specs if available (`maestro spec load --category coding` for conventions, `maestro spec load --category review` for quality standards). Browse wiki: `maestro search --category coding`, load relevant entries.
+Load project specs if available (`maestro load --type spec --category coding` for conventions, `maestro load --type spec --category review` for quality standards). Browse wiki: `maestro search --category coding`, load relevant entries.
 
 Analyze scope for tech debt categories:
 

package/.codex/skills/quality-review/SKILL.md

@@ -197,7 +197,7 @@ Session folder: `.workflow/.csv-wave/{sessionId}/` — create via `mkdir -p`
 
 If `--dimensions` flag provided, override with explicit list.
 
-6. **Specs loading**: Run `maestro spec load --category review` to load review standards, checklists, AND discoverable knowhow tools (unless `--skip-specs`). Also run `maestro spec conflict list` to load existing conflict markers (review should prioritize verifying contested entries against code)
+6. **Specs loading**: Run `maestro load --type spec --category review` to load review standards, checklists, AND discoverable knowhow tools (unless `--skip-specs`). Also run `maestro spec conflict list` to load existing conflict markers (review should prioritize verifying contested entries against code)
 7. **CSV generation**: One row per dimension + one aggregation row
 
 **Wave computation**: Simple 2-wave -- all dimension tasks = wave 1, aggregation = wave 2.

package/.codex/skills/quality-test/SKILL.md

@@ -149,7 +149,7 @@ S_REPORT:
 
 1. Load verification context: verification.json, validation.json, index.json, plan.json, summaries
 2. Load quality artifacts: review findings (type=review) -> extra tests (source: review_finding); debug root causes (type=debug) -> regression tests (source: debug_root_cause)
-3. Load test tools: `maestro spec load --category test --keyword <feature>` -> additional scenarios (source: tool)
+3. Load test tools: `maestro load --type spec --category test --keyword <feature>` -> additional scenarios (source: tool)
 4. Design scenarios from user-observable outcomes: id (T-NNN), name, category (e2e/integration/unit), expected, requirement_ref, source
 5. Write test-plan.json
 

package/.codex/skills/spec-load/SKILL.md

@@ -49,7 +49,7 @@ Extract optional `--category` and `--keyword` flags.
 
 ### Step 3: Load via CLI
 
-Run `maestro spec load [--category <category>] [--keyword <word>]`. If CLI unavailable, read files directly and apply keyword/category filter.
+Run `maestro load --type spec [--category <category>] [--keyword <word>]`. If CLI unavailable, read files directly and apply keyword/category filter.
 
 ### Step 4: Display Results
 

package/.codex/skills/spec-setup/SKILL.md

@@ -1,73 +1,73 @@
----
-name: spec-setup
-description: Initialize specs from project structure
-argument-hint: ""
-allowed-tools: Read, Write, Bash, Glob, Grep
----
-
-<purpose>
-Initialize project specs by scanning the codebase and generating spec files in `.workflow/specs/`.
-Core files (coding, arch, learning) always created. Optional files created only when relevant signals detected.
-
-```bash
-$spec-setup
-```
-</purpose>
-
-<context>
-No arguments. Scans the codebase and generates spec files in `.workflow/specs/`.
-</context>
-
-<execution>
-
-### Step 1: Validate Preconditions
-
-Verify `.workflow/` exists (E001) and project contains source files (E002).
-
-### Step 2: Scan Codebase
-
-Detect conventions and tech stack by scanning:
-- Package files (`package.json`, `Cargo.toml`, `go.mod`, etc.)
-- Config files (`.eslintrc`, `tsconfig.json`, `.prettierrc`, etc.)
-- Source structure (directories, naming patterns, import style)
-- Test patterns (framework, naming, location)
-
-### Step 3: Generate Core Spec Files (always)
-
-Create `.workflow/specs/` directory and write:
-
-1. **`coding-conventions.md`** — Detected naming, import, formatting patterns (category: `coding`)
-2. **`architecture-constraints.md`** — Structural rules, layer boundaries (category: `arch`)
-3. **`learnings.md`** — Initialized with format instructions for future entries (category: `learning`)
-
-### Step 4: Generate Optional Spec Files (when signals detected)
-
-| File | Created when |
-|------|-------------|
-| `quality-rules.md` | Linter config, CI config, or lint scripts detected |
-| `test-conventions.md` | Test framework, test files, or test scripts detected |
-| `debug-notes.md` | Skipped — created on demand via `spec-add debug` |
-| `review-standards.md` | Skipped — created on demand via `spec-add review` |
-
-### Step 5: Display Report
-
-List created files with categories. Show next steps: `$spec-add <category> <content>`, available categories (core + extended), `$spec-remove`, wiki graph commands.
-
-</execution>
-
-<error_codes>
-
-| Code | Severity | Description |
-|------|----------|-------------|
-| E001 | fatal | `.workflow/` not initialized -- run `$maestro-init` first |
-| E002 | fatal | No source files found in project |
-| W001 | warning | Convention detection uncertain -- marked `[UNCERTAIN]` |
-
-</error_codes>
-
-<success_criteria>
-- [ ] `.workflow/specs/` directory created
-- [ ] 3 core spec files always created (coding, arch, learning)
-- [ ] Optional files created only when relevant signals detected
-- [ ] Completion report displayed with category labels
-</success_criteria>
+---
+name: spec-setup
+description: Initialize specs from project structure
+argument-hint: ""
+allowed-tools: Read, Write, Bash, Glob, Grep
+---
+
+<purpose>
+Initialize project specs by scanning the codebase and generating spec files in `.workflow/specs/`.
+Core files (coding, arch, learning) always created. Optional files created only when relevant signals detected.
+
+```bash
+$spec-setup
+```
+</purpose>
+
+<context>
+No arguments. Scans the codebase and generates spec files in `.workflow/specs/`.
+</context>
+
+<execution>
+
+### Step 1: Validate Preconditions
+
+Verify `.workflow/` exists (E001) and project contains source files (E002).
+
+### Step 2: Scan Codebase
+
+Detect conventions and tech stack by scanning:
+- Package files (`package.json`, `Cargo.toml`, `go.mod`, etc.)
+- Config files (`.eslintrc`, `tsconfig.json`, `.prettierrc`, etc.)
+- Source structure (directories, naming patterns, import style)
+- Test patterns (framework, naming, location)
+
+### Step 3: Generate Core Spec Files (always)
+
+Create `.workflow/specs/` directory and write:
+
+1. **`coding-conventions.md`** — Detected naming, import, formatting patterns (category: `coding`)
+2. **`architecture-constraints.md`** — Structural rules, layer boundaries (category: `arch`)
+3. **`learnings.md`** — Initialized with format instructions for future entries (category: `learning`)
+
+### Step 4: Generate Optional Spec Files (when signals detected)
+
+| File | Created when |
+|------|-------------|
+| `quality-rules.md` | Linter config, CI config, or lint scripts detected |
+| `test-conventions.md` | Test framework, test files, or test scripts detected |
+| `debug-notes.md` | Skipped — created on demand via `spec-add debug` |
+| `review-standards.md` | Skipped — created on demand via `spec-add review` |
+
+### Step 5: Display Report
+
+List created files with categories. Show next steps: `$spec-add <category> <content>`, available categories (core + extended), `$spec-remove`, wiki graph commands.
+
+</execution>
+
+<error_codes>
+
+| Code | Severity | Description |
+|------|----------|-------------|
+| E001 | fatal | `.workflow/` not initialized -- run `$maestro-init` first |
+| E002 | fatal | No source files found in project |
+| W001 | warning | Convention detection uncertain -- marked `[UNCERTAIN]` |
+
+</error_codes>
+
+<success_criteria>
+- [ ] `.workflow/specs/` directory created
+- [ ] 3 core spec files always created (coding, arch, learning)
+- [ ] Optional files created only when relevant signals detected
+- [ ] Completion report displayed with category labels
+</success_criteria>

package/.codex/skills/team-coordinate/SKILL.md

@@ -61,7 +61,7 @@ $team-coordinate --continue "20260518-team-auth-system"
 
 ### Pre-load specs (optional)
 
-1. `maestro spec load --category arch` — architecture constraints
+1. `maestro load --type spec --category arch` — architecture constraints
 2. `maestro search "<topic>"` — relevant knowhow
 3. Proceed without if unavailable.
 

package/.codex/skills/team-lifecycle-v4/roles/executor/role.md

@@ -43,7 +43,7 @@ Code implementation worker with dual execution modes.
 ## Phase 3: Execute Implementation
 
 Route by mode -> read commands/<command>.md:
-- agent / gemini / codex / qwen -> commands/implement.md
+- agent / agy / codex / qwen -> commands/implement.md
 - Revision task -> commands/fix.md
 
 ## Phase 4: Self-Validation + Report
@@ -61,7 +61,7 @@ Route by mode -> read commands/<command>.md:
      "role": "executor",
      "timestamp": "<ISO-8601>",
      "status": "completed|failed",
-     "mode_used": "<agent|gemini|codex|qwen>",
+     "mode_used": "<agent|agy|codex|qwen>",
      "files_modified": [],
      "convergence_results": { ... }
    }
@@ -85,5 +85,5 @@ Route by mode -> read commands/<command>.md:
 | Agent mode syntax errors | Retry with error context (max 3) |
 | CLI mode failure | Retry or resume with --resume |
 | pre_analysis failure | Follow on_error (fail/continue/skip) |
-| CLI tool unavailable | Fallback: gemini -> qwen -> codex |
+| CLI tool unavailable | Fallback: agy -> qwen -> codex |
 | Max retries exceeded | Report via report_agent_job_result with status "failed" |

package/.codex/skills/team-quality-assurance/roles/analyst/role.md

@@ -34,7 +34,7 @@ Analyze defect patterns, coverage gaps, test effectiveness, and generate compreh
 | Data Points | Mode |
 |-------------|------|
 | <= 5 issues + results | Direct inline analysis |
-| > 5 | CLI-assisted deep analysis via gemini |
+| > 5 | CLI-assisted deep analysis via agy |
 
 ## Phase 3: Multi-Dimensional Analysis
 

package/.codex/skills/team-quality-assurance/roles/executor/role.md

@@ -26,7 +26,7 @@ Run test suites, collect coverage data, and perform automatic fix cycles when te
 | Target layer | task description `layer: L1/L2/L3` | Yes |
 
 1. Extract session path and target layer from task description
-2. Load validation specs: Run `maestro spec load --category review` for verification rules and acceptance criteria
+2. Load validation specs: Run `maestro load --type spec --category review` for verification rules and acceptance criteria
 3. Read .msg/meta.json for strategy and generated test file list
 3. Detect test command by framework:
 

package/.codex/skills/team-quality-assurance/specs/team-config.json

@@ -23,8 +23,8 @@
       "message_types_sent": ["scan_ready", "issues_found", "error"],
       "message_types_received": [],
       "commands": ["scan"],
-      "cli_tools": ["gemini"],
-      "cli_tools": ["gemini"]
+      "cli_tools": ["agy"],
+      "cli_tools": ["agy"]
     },
     "strategist": {
       "name": "strategist",
@@ -34,8 +34,8 @@
       "message_types_sent": ["strategy_ready", "error"],
       "message_types_received": [],
       "commands": ["analyze-scope"],
-      "cli_tools": ["gemini"],
-      "cli_tools": ["gemini"]
+      "cli_tools": ["agy"],
+      "cli_tools": ["agy"]
     },
     "generator": {
       "name": "generator",
@@ -45,8 +45,8 @@
       "message_types_sent": ["tests_generated", "tests_revised", "error"],
       "message_types_received": [],
       "commands": ["generate-tests"],
-      "cli_tools": ["gemini"],
-      "cli_tools": ["gemini"]
+      "cli_tools": ["agy"],
+      "cli_tools": ["agy"]
     },
     "executor": {
       "name": "executor",
@@ -56,7 +56,7 @@
       "message_types_sent": ["tests_passed", "tests_failed", "coverage_report", "error"],
       "message_types_received": [],
       "commands": ["run-fix-cycle"],
-      "cli_tools": ["gemini"]
+      "cli_tools": ["agy"]
     },
     "analyst": {
       "name": "analyst",
@@ -66,7 +66,7 @@
       "message_types_sent": ["analysis_ready", "quality_report", "error"],
       "message_types_received": [],
       "commands": ["quality-report"],
-      "cli_tools": ["gemini"]
+      "cli_tools": ["agy"]
     }
   },
 

package/.codex/skills/team-review/roles/reviewer/role.md

@@ -21,7 +21,7 @@ Deep analysis on scan findings: triage, root cause / impact / optimization enric
 | .msg/meta.json | <session>/.msg/meta.json | No |
 
 1. Extract session path, input path, dimensions from task description
-2. Load review specs: Run `maestro spec load --category review` for review standards, checklists, and approval gates
+2. Load review specs: Run `maestro load --type spec --category review` for review standards, checklists, and approval gates
 3. Load scan results. If missing or empty -> report clean, complete immediately
 3. Load wisdom files from `<session>/wisdom/`
 4. Triage findings into two buckets:

package/.codex/skills/team-tech-debt/roles/assessor/role.md

@@ -29,7 +29,7 @@ Quantitative evaluator for tech debt items. Score each debt item on business imp
 | Item Count | Strategy |
 |------------|----------|
 | <= 10 | Heuristic: severity-based impact + effort-based cost |
-| 11-50 | CLI batch: single gemini analysis call |
+| 11-50 | CLI batch: single agy analysis call |
 | > 50 | CLI chunked: batches of 25 items |
 
 **Impact Score Mapping** (heuristic):
@@ -59,7 +59,7 @@ Quantitative evaluator for tech debt items. Score each debt item on business imp
 | <= 3 | <= 2 | backlog |
 | <= 3 | >= 3 | defer |
 
-For CLI mode, prompt gemini with full debt summary requesting JSON array of `{id, impact_score, cost_score, risk_if_unfixed, priority_quadrant}`. Unevaluated items fall back to heuristic scoring.
+For CLI mode, prompt agy with full debt summary requesting JSON array of `{id, impact_score, cost_score, risk_if_unfixed, priority_quadrant}`. Unevaluated items fall back to heuristic scoring.
 
 ## Phase 4: Generate Priority Matrix
 

package/.codex/skills/team-tech-debt/roles/planner/role.md

@@ -29,7 +29,7 @@ Remediation plan designer. Create phased remediation plan from priority matrix:
 | Item Count (quick-win + strategic) | Strategy |
 |------------------------------------|----------|
 | <= 5 | Inline: generate steps from item data |
-| > 5 | CLI-assisted: gemini generates detailed remediation steps |
+| > 5 | CLI-assisted: agy generates detailed remediation steps |
 
 **3-Phase Plan Structure**:
 
@@ -59,7 +59,7 @@ Remediation plan designer. Create phased remediation plan from priority matrix:
 | dependency | Configure automated dependency update bot (Renovate/Dependabot) |
 | documentation | Add JSDoc/docstring enforcement in linting rules |
 
-For CLI-assisted mode, prompt gemini with debt summary requesting specific fix steps per item, grouped into phases, with dependencies and estimated time.
+For CLI-assisted mode, prompt agy with debt summary requesting specific fix steps per item, grouped into phases, with dependencies and estimated time.
 
 ## Phase 4: Validate & Save
 

package/.codex/skills/team-tech-debt/roles/scanner/role.md

@@ -18,7 +18,7 @@ Multi-dimension tech debt scanner. Scan codebase across 5 dimensions (code, arch
 | .msg/meta.json | <session>/.msg/meta.json | Yes |
 
 1. Extract session path and scan scope from task description
-2. Load debug specs: Run `maestro spec load --category debug` for known issues, workarounds, and root-cause notes
+2. Load debug specs: Run `maestro load --type spec --category debug` for known issues, workarounds, and root-cause notes
 3. Read .msg/meta.json for team context
 3. Detect project type and framework:
 
@@ -45,7 +45,7 @@ Multi-dimension tech debt scanner. Scan codebase across 5 dimensions (code, arch
 
 | Score | Complexity | Strategy |
 |-------|------------|----------|
-| >= 4 | High | Triple Fan-out: CLI explore + CLI 5 dimensions + multi-perspective Gemini |
+| >= 4 | High | Triple Fan-out: CLI explore + CLI 5 dimensions + multi-perspective Agy |
 | 2-3 | Medium | Dual Fan-out: CLI explore + CLI 3 dimensions |
 | 0-1 | Low | Inline: ACE search + Grep |
 

package/.codex/skills/team-tech-debt/roles/validator/role.md

@@ -48,7 +48,7 @@ Execute 4-layer validation (all commands in worktree):
 - Count error occurrences
 
 **4. Quality Analysis** (optional, when > 5 modified files):
-- Use gemini CLI to compare code quality before/after
+- Use agy CLI to compare code quality before/after
 - Assess complexity, duplication, naming quality improvements
 
 **Debt Score Calculation**:

package/.codex/skills/team-tech-debt/specs/team-config.json

@@ -23,7 +23,7 @@
       "message_types_sent": ["scan_complete", "debt_items_found", "error"],
       "message_types_received": [],
       "commands": ["scan-debt"],
-      "cli_tools": ["gemini"]
+      "cli_tools": ["agy"]
     },
     "assessor": {
       "name": "assessor",
@@ -33,7 +33,7 @@
       "message_types_sent": ["assessment_complete", "error"],
       "message_types_received": [],
       "commands": ["evaluate"],
-      "cli_tools": ["gemini"]
+      "cli_tools": ["agy"]
     },
     "planner": {
       "name": "planner",
@@ -43,7 +43,7 @@
       "message_types_sent": ["plan_ready", "plan_revision", "error"],
       "message_types_received": [],
       "commands": ["create-plan"],
-      "cli_tools": ["gemini"]
+      "cli_tools": ["agy"]
     },
     "executor": {
       "name": "executor",
@@ -53,7 +53,7 @@
       "message_types_sent": ["fix_complete", "fix_progress", "error"],
       "message_types_received": [],
       "commands": ["remediate"],
-      "cli_tools": [{"tool": "gemini", "mode": "write"}]
+      "cli_tools": [{"tool": "agy", "mode": "write"}]
     },
     "validator": {
       "name": "validator",
@@ -63,7 +63,7 @@
       "message_types_sent": ["validation_complete", "regression_found", "error"],
       "message_types_received": [],
       "commands": ["verify"],
-      "cli_tools": [{"tool": "gemini", "mode": "write"}]
+      "cli_tools": [{"tool": "agy", "mode": "write"}]
     }
   },
 

package/.codex/skills/team-testing/roles/executor/role.md

@@ -24,7 +24,7 @@ Execute tests, collect coverage, attempt auto-fix for failures. Acts as the Crit
 | .msg/meta.json | <session>/wisdom/.msg/meta.json | No |
 
 1. Extract session path and test directory from task description
-2. Load test specs: Run `maestro spec load --category test` for test framework conventions and coverage targets
+2. Load test specs: Run `maestro load --type spec --category test` for test framework conventions and coverage targets
 3. Extract coverage target (default: 80%)
 3. Read .msg/meta.json for framework info (from strategist namespace)
 4. Determine test framework:
@@ -51,7 +51,7 @@ Glob("<session>/<test-dir>/**/*")
 | 2 | Parse results: pass rate + coverage |
 | 3 | pass_rate >= 0.95 AND coverage >= target -> success, exit |
 | 4 | Extract failing test details |
-| 5 | Delegate fix to CLI tool (gemini write mode) |
+| 5 | Delegate fix to CLI tool (agy write mode) |
 | 6 | Increment iteration; >= 3 -> exit with failures |
 
 ```

package/.codex/skills/team-testing/roles/generator/role.md

@@ -22,7 +22,7 @@ Generate test code by layer (L1 unit / L2 integration / L3 E2E). Acts as the Gen
 | .msg/meta.json | <session>/wisdom/.msg/meta.json | No |
 
 1. Extract session path and layer from task description
-2. Load test specs: Run `maestro spec load --category test` for test framework conventions and coverage targets
+2. Load test specs: Run `maestro load --type spec --category test` for test framework conventions and coverage targets
 3. Read test strategy:
 
 ```