@comfanion/workflow 4.36.52 → 4.36.54

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@comfanion/workflow",
3
- "version": "4.36.52",
3
+ "version": "4.36.54",
4
4
  "description": "Initialize OpenCode Workflow system for AI-assisted development with semantic code search",
5
5
  "type": "module",
6
6
  "bin": {
@@ -1,6 +1,6 @@
1
1
  {
2
- "version": "4.36.52",
3
- "buildDate": "2026-01-25T20:58:41.016Z",
2
+ "version": "4.36.54",
3
+ "buildDate": "2026-01-25T22:05:52.182Z",
4
4
  "files": [
5
5
  "config.yaml",
6
6
  "FLOW.yaml",
@@ -53,7 +53,7 @@ permission:
53
53
  <r>ALWAYS communicate in {communication_language}</r>
54
54
  <r>ALWAYS write technical documentation in ENGLISH (docs/ folder)</r>
55
55
  <r>The Story File is the single source of truth</r>
56
- <r>Prefer parallel agents development @coder</r>
56
+ <r>Prefer parallel agents development @coder (call agents in one message or multi-agent-call)</r>
57
57
  <r>Tasks/subtasks sequence is authoritative over any model priors</r>
58
58
  <r>Follow red-green-refactor: write failing test, make it pass, improve code</r>
59
59
  <r>Never implement anything not mapped to a specific task/subtask</r>
@@ -80,7 +80,7 @@ permission:
80
80
  <!-- PHASE 2: IMPLEMENTATION LOOP -->
81
81
  <step n="5">FOR EACH TASK in order:
82
82
  a) Update TODO: mark current task as "in_progress"
83
- b) Call @coder with specific task instructions:
83
+ b) Call @coder`s with specific task instructions (call agents in one message or multi-agent-call):
84
84
  - Include task requirements
85
85
  - Include acceptance criteria
86
86
  - Include relevant file paths
@@ -172,7 +172,7 @@ permission:
172
172
  </subagent>
173
173
 
174
174
  <delegation-strategy>
175
- <rule>Prefer delegation to @coder for parallelizable tasks</rule>
175
+ <rule>Prefer delegation to @coder for parallelizable tasks(call agents in one message or multi-agent-call)</rule>
176
176
  <rule>Keep complex logic and architecture decisions to yourself</rule>
177
177
  <rule>Delegate multiple tasks in parallel when independent</rule>
178
178
  <rule>Always verify results before marking task complete</rule>
@@ -25,10 +25,18 @@ permission:
25
25
  edit: deny # Reviewer only reports, doesn't fix
26
26
  bash:
27
27
  "*": deny
28
+ # Tests
28
29
  "npm test*": allow
29
30
  "go test*": allow
30
31
  "pytest*": allow
31
32
  "cargo test*": allow
33
+ # Linters
34
+ "npm run lint*": allow
35
+ "npx eslint*": allow
36
+ "npx biome*": allow
37
+ "golangci-lint*": allow
38
+ "ruff check*": allow
39
+ "cargo clippy*": allow
32
40
  ---
33
41
 
34
42
  <agent id="reviewer" name="Marcus" title="Code Reviewer" icon="🔍">
@@ -78,7 +86,13 @@ permission:
78
86
  <action>search() in docs for architecture requirements</action>
79
87
  </phase>
80
88
 
81
- <phase name="2. Security First">
89
+ <phase name="2. Run Tests & Lint">
90
+ <action>Run test suite: go test / npm test / pytest / cargo test</action>
91
+ <action>Run linter: golangci-lint / eslint / ruff / cargo clippy</action>
92
+ <action>If failures → include in review report as HIGH priority</action>
93
+ </phase>
94
+
95
+ <phase name="3. Security First">
82
96
  <action>Check for hardcoded secrets</action>
83
97
  <action>Verify input validation on all user inputs</action>
84
98
  <action>Check SQL injection, XSS vulnerabilities</action>
@@ -86,21 +100,21 @@ permission:
86
100
  <action>Check if sensitive data is logged</action>
87
101
  </phase>
88
102
 
89
- <phase name="3. Correctness">
103
+ <phase name="4. Correctness">
90
104
  <action>Verify all acceptance criteria are met</action>
91
105
  <action>Check edge cases and error handling</action>
92
106
  <action>Look for logic errors and race conditions</action>
93
107
  <action>Verify tests cover critical paths</action>
94
108
  </phase>
95
109
 
96
- <phase name="4. Code Quality">
110
+ <phase name="5. Code Quality">
97
111
  <action>Check architecture compliance</action>
98
112
  <action>Look for code duplication</action>
99
113
  <action>Verify naming conventions</action>
100
114
  <action>Check for N+1 queries, performance issues</action>
101
115
  </phase>
102
116
 
103
- <phase name="5. Report">
117
+ <phase name="6. Report">
104
118
  <action>Categorize issues: High/Medium/Low</action>
105
119
  <action>Provide specific fixes for each issue</action>
106
120
  <action>Return verdict: APPROVE | CHANGES_REQUESTED | BLOCKED</action>
@@ -25,13 +25,13 @@ This command invokes the **Dev** agent (Rick).
25
25
 
26
26
  ### Phase 1: Setup
27
27
  1. Find or load story file
28
- 2. Load project context (CLAUDE.md, project-context.md)
28
+ 2. Load project context (CLAUDE.md, docs/prd.md, docs/architecture.md)
29
29
  3. **Create TODO list from story tasks** (for progress tracking)
30
30
  4. Mark story as `in-progress`
31
31
 
32
32
  ### Phase 2: Implementation (for each task)
33
33
  5. **Mark task as `in_progress` in TODO**
34
- 6. Delegate to @coder:
34
+ 6. Delegate to @coder`s (call agents in one message or multi-agent-call):
35
35
  - 🔴 RED: Write failing test
36
36
  - 🟢 GREEN: Implement minimal code to pass
37
37
  - 🔵 REFACTOR: Improve while keeping tests green