@cluesmith/codev 2.0.6 → 2.0.7

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.
Files changed (181) hide show
  1. package/dashboard/dist/assets/{index-B-s8BA2l.js → index-BblS3DWL.js} +30 -30
  2. package/dashboard/dist/assets/index-BblS3DWL.js.map +1 -0
  3. package/dashboard/dist/assets/index-Cr9PyjqX.css +32 -0
  4. package/dashboard/dist/index.html +2 -2
  5. package/dist/agent-farm/cli.d.ts.map +1 -1
  6. package/dist/agent-farm/cli.js +23 -48
  7. package/dist/agent-farm/cli.js.map +1 -1
  8. package/dist/agent-farm/commands/architect.d.ts +5 -5
  9. package/dist/agent-farm/commands/architect.d.ts.map +1 -1
  10. package/dist/agent-farm/commands/architect.js +37 -20
  11. package/dist/agent-farm/commands/architect.js.map +1 -1
  12. package/dist/agent-farm/commands/attach.d.ts.map +1 -1
  13. package/dist/agent-farm/commands/attach.js +1 -21
  14. package/dist/agent-farm/commands/attach.js.map +1 -1
  15. package/dist/agent-farm/commands/cleanup.d.ts +12 -0
  16. package/dist/agent-farm/commands/cleanup.d.ts.map +1 -1
  17. package/dist/agent-farm/commands/cleanup.js +108 -7
  18. package/dist/agent-farm/commands/cleanup.js.map +1 -1
  19. package/dist/agent-farm/commands/spawn-worktree.d.ts +1 -2
  20. package/dist/agent-farm/commands/spawn-worktree.d.ts.map +1 -1
  21. package/dist/agent-farm/commands/spawn-worktree.js +12 -18
  22. package/dist/agent-farm/commands/spawn-worktree.js.map +1 -1
  23. package/dist/agent-farm/commands/spawn.d.ts.map +1 -1
  24. package/dist/agent-farm/commands/spawn.js +30 -26
  25. package/dist/agent-farm/commands/spawn.js.map +1 -1
  26. package/dist/agent-farm/commands/start.d.ts.map +1 -1
  27. package/dist/agent-farm/commands/start.js +2 -6
  28. package/dist/agent-farm/commands/start.js.map +1 -1
  29. package/dist/agent-farm/commands/status.d.ts.map +1 -1
  30. package/dist/agent-farm/commands/status.js +4 -23
  31. package/dist/agent-farm/commands/status.js.map +1 -1
  32. package/dist/agent-farm/commands/stop.d.ts.map +1 -1
  33. package/dist/agent-farm/commands/stop.js +2 -6
  34. package/dist/agent-farm/commands/stop.js.map +1 -1
  35. package/dist/agent-farm/commands/tower-cloud.d.ts +2 -9
  36. package/dist/agent-farm/commands/tower-cloud.d.ts.map +1 -1
  37. package/dist/agent-farm/commands/tower-cloud.js +12 -47
  38. package/dist/agent-farm/commands/tower-cloud.js.map +1 -1
  39. package/dist/agent-farm/commands/tower.d.ts.map +1 -1
  40. package/dist/agent-farm/commands/tower.js +6 -23
  41. package/dist/agent-farm/commands/tower.js.map +1 -1
  42. package/dist/agent-farm/db/index.d.ts.map +1 -1
  43. package/dist/agent-farm/db/index.js +52 -2
  44. package/dist/agent-farm/db/index.js.map +1 -1
  45. package/dist/agent-farm/db/schema.d.ts +1 -1
  46. package/dist/agent-farm/db/schema.d.ts.map +1 -1
  47. package/dist/agent-farm/db/schema.js +1 -1
  48. package/dist/agent-farm/lib/cloud-config.d.ts +1 -0
  49. package/dist/agent-farm/lib/cloud-config.d.ts.map +1 -1
  50. package/dist/agent-farm/lib/cloud-config.js +2 -2
  51. package/dist/agent-farm/lib/cloud-config.js.map +1 -1
  52. package/dist/agent-farm/lib/tower-client.d.ts +49 -0
  53. package/dist/agent-farm/lib/tower-client.d.ts.map +1 -1
  54. package/dist/agent-farm/lib/tower-client.js +32 -2
  55. package/dist/agent-farm/lib/tower-client.js.map +1 -1
  56. package/dist/agent-farm/servers/overview.d.ts +47 -1
  57. package/dist/agent-farm/servers/overview.d.ts.map +1 -1
  58. package/dist/agent-farm/servers/overview.js +298 -58
  59. package/dist/agent-farm/servers/overview.js.map +1 -1
  60. package/dist/agent-farm/servers/tower-instances.d.ts.map +1 -1
  61. package/dist/agent-farm/servers/tower-instances.js +2 -1
  62. package/dist/agent-farm/servers/tower-instances.js.map +1 -1
  63. package/dist/agent-farm/servers/tower-routes.d.ts.map +1 -1
  64. package/dist/agent-farm/servers/tower-routes.js +21 -20
  65. package/dist/agent-farm/servers/tower-routes.js.map +1 -1
  66. package/dist/agent-farm/servers/tower-server.js +3 -4
  67. package/dist/agent-farm/servers/tower-server.js.map +1 -1
  68. package/dist/agent-farm/servers/tower-terminals.d.ts +1 -1
  69. package/dist/agent-farm/servers/tower-terminals.d.ts.map +1 -1
  70. package/dist/agent-farm/servers/tower-terminals.js +4 -4
  71. package/dist/agent-farm/servers/tower-terminals.js.map +1 -1
  72. package/dist/agent-farm/servers/tower-tunnel.d.ts.map +1 -1
  73. package/dist/agent-farm/servers/tower-tunnel.js +3 -19
  74. package/dist/agent-farm/servers/tower-tunnel.js.map +1 -1
  75. package/dist/agent-farm/servers/tower-websocket.d.ts.map +1 -1
  76. package/dist/agent-farm/servers/tower-websocket.js +2 -1
  77. package/dist/agent-farm/servers/tower-websocket.js.map +1 -1
  78. package/dist/agent-farm/types.d.ts +1 -1
  79. package/dist/agent-farm/types.d.ts.map +1 -1
  80. package/dist/agent-farm/utils/display.d.ts +8 -0
  81. package/dist/agent-farm/utils/display.d.ts.map +1 -0
  82. package/dist/agent-farm/utils/display.js +26 -0
  83. package/dist/agent-farm/utils/display.js.map +1 -0
  84. package/dist/agent-farm/utils/notifications.d.ts.map +1 -1
  85. package/dist/agent-farm/utils/notifications.js +7 -16
  86. package/dist/agent-farm/utils/notifications.js.map +1 -1
  87. package/dist/agent-farm/utils/server-utils.d.ts +4 -0
  88. package/dist/agent-farm/utils/server-utils.d.ts.map +1 -1
  89. package/dist/agent-farm/utils/server-utils.js +20 -0
  90. package/dist/agent-farm/utils/server-utils.js.map +1 -1
  91. package/dist/agent-farm/utils/shell.d.ts +5 -0
  92. package/dist/agent-farm/utils/shell.d.ts.map +1 -1
  93. package/dist/agent-farm/utils/shell.js +15 -11
  94. package/dist/agent-farm/utils/shell.js.map +1 -1
  95. package/dist/cli.d.ts.map +1 -1
  96. package/dist/cli.js +25 -19
  97. package/dist/cli.js.map +1 -1
  98. package/dist/commands/consult/index.d.ts +10 -9
  99. package/dist/commands/consult/index.d.ts.map +1 -1
  100. package/dist/commands/consult/index.js +401 -259
  101. package/dist/commands/consult/index.js.map +1 -1
  102. package/dist/commands/consult/usage-extractor.d.ts +3 -0
  103. package/dist/commands/consult/usage-extractor.d.ts.map +1 -1
  104. package/dist/commands/consult/usage-extractor.js +52 -29
  105. package/dist/commands/consult/usage-extractor.js.map +1 -1
  106. package/dist/commands/porch/index.d.ts.map +1 -1
  107. package/dist/commands/porch/index.js +13 -12
  108. package/dist/commands/porch/index.js.map +1 -1
  109. package/dist/commands/porch/next.d.ts.map +1 -1
  110. package/dist/commands/porch/next.js +7 -18
  111. package/dist/commands/porch/next.js.map +1 -1
  112. package/dist/commands/porch/plan.d.ts.map +1 -1
  113. package/dist/commands/porch/plan.js +17 -2
  114. package/dist/commands/porch/plan.js.map +1 -1
  115. package/dist/commands/porch/prompts.d.ts.map +1 -1
  116. package/dist/commands/porch/prompts.js +6 -3
  117. package/dist/commands/porch/prompts.js.map +1 -1
  118. package/dist/commands/porch/state.d.ts +13 -0
  119. package/dist/commands/porch/state.d.ts.map +1 -1
  120. package/dist/commands/porch/state.js +46 -1
  121. package/dist/commands/porch/state.js.map +1 -1
  122. package/dist/lib/github.d.ts +10 -9
  123. package/dist/lib/github.d.ts.map +1 -1
  124. package/dist/lib/github.js +49 -9
  125. package/dist/lib/github.js.map +1 -1
  126. package/dist/terminal/index.d.ts +2 -0
  127. package/dist/terminal/index.d.ts.map +1 -1
  128. package/dist/terminal/index.js +2 -0
  129. package/dist/terminal/index.js.map +1 -1
  130. package/dist/terminal/pty-manager.js +2 -2
  131. package/dist/terminal/pty-manager.js.map +1 -1
  132. package/dist/terminal/pty-session.js +1 -1
  133. package/dist/terminal/pty-session.js.map +1 -1
  134. package/package.json +1 -1
  135. package/skeleton/.claude/skills/af/SKILL.md +9 -9
  136. package/skeleton/.claude/skills/consult/SKILL.md +55 -38
  137. package/skeleton/.claude/skills/porch/SKILL.md +53 -0
  138. package/skeleton/DEPENDENCIES.md +2 -2
  139. package/skeleton/builders.md +8 -19
  140. package/skeleton/protocol-schema.json +1 -1
  141. package/skeleton/protocols/bugfix/prompts/pr.md +3 -3
  142. package/skeleton/protocols/bugfix/protocol.json +1 -1
  143. package/skeleton/protocols/maintain/consult-types/impl-review.md +72 -0
  144. package/skeleton/protocols/maintain/consult-types/pr-review.md +72 -0
  145. package/skeleton/protocols/maintain/protocol.json +4 -4
  146. package/skeleton/protocols/maintain/protocol.md +3 -3
  147. package/skeleton/protocols/protocol-schema.json +1 -1
  148. package/skeleton/protocols/spir/consult-types/impl-review.md +72 -0
  149. package/skeleton/protocols/spir/consult-types/phase-review.md +72 -0
  150. package/skeleton/protocols/spir/consult-types/pr-review.md +72 -0
  151. package/skeleton/protocols/spir/prompts/plan.md +4 -4
  152. package/skeleton/protocols/spir/prompts/review.md +8 -8
  153. package/skeleton/protocols/spir/prompts/specify.md +6 -6
  154. package/skeleton/protocols/spir/protocol.json +11 -11
  155. package/skeleton/protocols/spir/templates/review.md +2 -2
  156. package/skeleton/protocols/tick/consult-types/impl-review.md +72 -0
  157. package/skeleton/protocols/tick/consult-types/plan-review.md +59 -0
  158. package/skeleton/protocols/tick/consult-types/pr-review.md +72 -0
  159. package/skeleton/protocols/tick/consult-types/spec-review.md +55 -0
  160. package/skeleton/protocols/tick/protocol.json +2 -7
  161. package/skeleton/resources/commands/agent-farm.md +13 -11
  162. package/skeleton/resources/commands/codev.md +0 -35
  163. package/skeleton/resources/commands/consult.md +88 -234
  164. package/skeleton/resources/commands/overview.md +6 -7
  165. package/skeleton/resources/workflow-reference.md +24 -24
  166. package/skeleton/roles/architect.md +17 -21
  167. package/skeleton/roles/builder.md +13 -13
  168. package/skeleton/templates/AGENTS.md +1 -1
  169. package/skeleton/templates/CLAUDE.md +1 -1
  170. package/skeleton/templates/cheatsheet.md +22 -18
  171. package/skeleton/templates/pr-overview.md +5 -5
  172. package/dashboard/dist/assets/index-B-s8BA2l.js.map +0 -1
  173. package/dashboard/dist/assets/index-DB2AxRP7.css +0 -32
  174. package/dist/agent-farm/commands/consult.d.ts +0 -15
  175. package/dist/agent-farm/commands/consult.d.ts.map +0 -1
  176. package/dist/agent-farm/commands/consult.js +0 -39
  177. package/dist/agent-farm/commands/consult.js.map +0 -1
  178. /package/skeleton/{consult-types → protocols/bugfix/consult-types}/impl-review.md +0 -0
  179. /package/skeleton/{consult-types/pr-ready.md → protocols/bugfix/consult-types/pr-review.md} +0 -0
  180. /package/skeleton/{consult-types → protocols/spir/consult-types}/plan-review.md +0 -0
  181. /package/skeleton/{consult-types → protocols/spir/consult-types}/spec-review.md +0 -0
@@ -149,7 +149,7 @@
149
149
  },
150
150
  "type": {
151
151
  "type": "string",
152
- "description": "Review type (spec-review, plan-review, impl-review, pr-ready)"
152
+ "description": "Review type (spec, plan, impl, pr, phase, integration)"
153
153
  },
154
154
  "parallel": {
155
155
  "type": "boolean",
@@ -0,0 +1,72 @@
1
+ # Implementation Review Prompt
2
+
3
+ ## Context
4
+ You are reviewing implementation work during the Implement phase. A builder has completed a plan phase and needs feedback before proceeding. Your job is to verify the implementation matches the spec and plan.
5
+
6
+ ## CRITICAL: Verify Before Flagging
7
+
8
+ Before requesting changes for missing configuration, incorrect patterns, or framework issues:
9
+ 1. **Check `package.json`** for actual dependency versions — framework conventions change between major versions
10
+ 2. **Read the actual config files** (or confirm their deliberate absence) before flagging missing configs
11
+ 3. **Do not assume** your training data reflects the version in use — verify against project files
12
+ 4. If "Previous Iteration Context" is provided, read it carefully before re-raising concerns that were already disputed
13
+
14
+ ## Focus Areas
15
+
16
+ 1. **Spec Adherence**
17
+ - Does the implementation fulfill the spec requirements for this phase?
18
+ - Are acceptance criteria met?
19
+
20
+ 2. **Code Quality**
21
+ - Is the code readable and maintainable?
22
+ - Are there obvious bugs or issues?
23
+ - Are error cases handled appropriately?
24
+
25
+ 3. **Test Coverage**
26
+ - Are the tests adequate for this phase?
27
+ - Do tests cover the main paths AND edge cases?
28
+
29
+ 4. **Plan Alignment**
30
+ - Does the implementation follow the plan?
31
+ - Are there plan items skipped or partially completed?
32
+
33
+ 5. **UX Verification** (if spec has UX requirements)
34
+ - Does the actual user experience match what the spec describes?
35
+ - If spec says "async" or "non-blocking", is it actually async?
36
+
37
+ ## Verdict Format
38
+
39
+ After your review, provide your verdict in exactly this format:
40
+
41
+ ```
42
+ ---
43
+ VERDICT: [APPROVE | REQUEST_CHANGES | COMMENT]
44
+ SUMMARY: [One-line summary of your assessment]
45
+ CONFIDENCE: [HIGH | MEDIUM | LOW]
46
+ ---
47
+ KEY_ISSUES:
48
+ - [Issue 1 or "None"]
49
+ - [Issue 2]
50
+ ...
51
+ ```
52
+
53
+ **Verdict meanings:**
54
+ - `APPROVE`: Phase is complete, builder can proceed
55
+ - `REQUEST_CHANGES`: Issues that must be fixed before proceeding
56
+ - `COMMENT`: Minor suggestions, can proceed but note feedback
57
+
58
+ ## Scoping (Multi-Phase Plans)
59
+
60
+ When the implementation plan has multiple phases (e.g., scaffolding, landing, media_rtl):
61
+ - **ONLY review work belonging to the current plan phase**
62
+ - The query will specify which phase you are reviewing
63
+ - Do NOT request changes for functionality scheduled in later phases
64
+ - Do NOT flag missing features that are out of scope for this phase
65
+ - If unsure whether something belongs to this phase, check the plan file
66
+
67
+ ## Notes
68
+
69
+ - This is a phase-level review, not the final PR review
70
+ - Focus on "does this phase work" not "is the whole feature done"
71
+ - If referencing line numbers, use `file:line` format
72
+ - The builder needs actionable feedback to continue
@@ -0,0 +1,72 @@
1
+ # Implementation Review Prompt
2
+
3
+ ## Context
4
+ You are reviewing implementation work during the Implement phase. A builder has completed a plan phase and needs feedback before proceeding. Your job is to verify the implementation matches the spec and plan.
5
+
6
+ ## CRITICAL: Verify Before Flagging
7
+
8
+ Before requesting changes for missing configuration, incorrect patterns, or framework issues:
9
+ 1. **Check `package.json`** for actual dependency versions — framework conventions change between major versions
10
+ 2. **Read the actual config files** (or confirm their deliberate absence) before flagging missing configs
11
+ 3. **Do not assume** your training data reflects the version in use — verify against project files
12
+ 4. If "Previous Iteration Context" is provided, read it carefully before re-raising concerns that were already disputed
13
+
14
+ ## Focus Areas
15
+
16
+ 1. **Spec Adherence**
17
+ - Does the implementation fulfill the spec requirements for this phase?
18
+ - Are acceptance criteria met?
19
+
20
+ 2. **Code Quality**
21
+ - Is the code readable and maintainable?
22
+ - Are there obvious bugs or issues?
23
+ - Are error cases handled appropriately?
24
+
25
+ 3. **Test Coverage**
26
+ - Are the tests adequate for this phase?
27
+ - Do tests cover the main paths AND edge cases?
28
+
29
+ 4. **Plan Alignment**
30
+ - Does the implementation follow the plan?
31
+ - Are there plan items skipped or partially completed?
32
+
33
+ 5. **UX Verification** (if spec has UX requirements)
34
+ - Does the actual user experience match what the spec describes?
35
+ - If spec says "async" or "non-blocking", is it actually async?
36
+
37
+ ## Verdict Format
38
+
39
+ After your review, provide your verdict in exactly this format:
40
+
41
+ ```
42
+ ---
43
+ VERDICT: [APPROVE | REQUEST_CHANGES | COMMENT]
44
+ SUMMARY: [One-line summary of your assessment]
45
+ CONFIDENCE: [HIGH | MEDIUM | LOW]
46
+ ---
47
+ KEY_ISSUES:
48
+ - [Issue 1 or "None"]
49
+ - [Issue 2]
50
+ ...
51
+ ```
52
+
53
+ **Verdict meanings:**
54
+ - `APPROVE`: Phase is complete, builder can proceed
55
+ - `REQUEST_CHANGES`: Issues that must be fixed before proceeding
56
+ - `COMMENT`: Minor suggestions, can proceed but note feedback
57
+
58
+ ## Scoping (Multi-Phase Plans)
59
+
60
+ When the implementation plan has multiple phases (e.g., scaffolding, landing, media_rtl):
61
+ - **ONLY review work belonging to the current plan phase**
62
+ - The query will specify which phase you are reviewing
63
+ - Do NOT request changes for functionality scheduled in later phases
64
+ - Do NOT flag missing features that are out of scope for this phase
65
+ - If unsure whether something belongs to this phase, check the plan file
66
+
67
+ ## Notes
68
+
69
+ - This is a phase-level review, not the final PR review
70
+ - Focus on "does this phase work" not "is the whole feature done"
71
+ - If referencing line numbers, use `file:line` format
72
+ - The builder needs actionable feedback to continue
@@ -0,0 +1,72 @@
1
+ # PR Ready Review Prompt
2
+
3
+ ## Context
4
+ You are performing a final self-check during the Review phase. The builder has completed all implementation phases and is about to create a PR. This is the last check before the work goes to the architect for integration review.
5
+
6
+ ## Focus Areas
7
+
8
+ 1. **Completeness**
9
+ - Are all spec requirements implemented?
10
+ - Are all plan phases complete?
11
+ - Is the review document written (`codev/reviews/XXXX-name.md`)?
12
+ - Are all commits properly formatted (`[Spec XXXX][Phase]`)?
13
+
14
+ 2. **Test Status**
15
+ - Do all tests pass?
16
+ - Is test coverage adequate for the changes?
17
+ - Are there any skipped or flaky tests?
18
+
19
+ 3. **Code Cleanliness**
20
+ - Is there any debug code left in?
21
+ - Are there any TODO comments that should be resolved?
22
+ - Are there any `// REVIEW:` comments that weren't addressed?
23
+ - Is the code properly formatted?
24
+
25
+ 4. **Documentation**
26
+ - Are inline comments clear where needed?
27
+ - Is the review document comprehensive?
28
+ - Are any new APIs documented?
29
+
30
+ 5. **PR Readiness**
31
+ - Is the branch up to date with main?
32
+ - Are commits atomic and well-described?
33
+ - Is the change diff reasonable in size?
34
+
35
+ ## Verdict Format
36
+
37
+ After your review, provide your verdict in exactly this format:
38
+
39
+ ```
40
+ ---
41
+ VERDICT: [APPROVE | REQUEST_CHANGES | COMMENT]
42
+ SUMMARY: [One-line summary of your assessment]
43
+ CONFIDENCE: [HIGH | MEDIUM | LOW]
44
+ ---
45
+ KEY_ISSUES:
46
+ - [Issue 1 or "None"]
47
+ - [Issue 2]
48
+ ...
49
+
50
+ PR_SUMMARY: |
51
+ ## Summary
52
+ [2-3 sentences describing what this PR does]
53
+
54
+ ## Key Changes
55
+ - [Change 1]
56
+ - [Change 2]
57
+
58
+ ## Test Plan
59
+ - [How to test]
60
+ ```
61
+
62
+ **Verdict meanings:**
63
+ - `APPROVE`: Ready to create PR
64
+ - `REQUEST_CHANGES`: Issues to fix before PR creation
65
+ - `COMMENT`: Minor items, can create PR but note feedback
66
+
67
+ ## Notes
68
+
69
+ - This is the builder's final self-review before hand-off
70
+ - The PR_SUMMARY in your output can be used as the PR description
71
+ - Focus on "is this ready for someone else to review" not "is this perfect"
72
+ - Any issues found here are cheaper to fix than during integration review
@@ -11,8 +11,8 @@ Transform the approved specification into an executable implementation plan with
11
11
  - **Project ID**: {{project_id}}
12
12
  - **Project Title**: {{title}}
13
13
  - **Current State**: {{current_state}}
14
- - **Spec File**: `codev/specs/{{project_id}}-{{title}}.md`
15
- - **Plan File**: `codev/plans/{{project_id}}-{{title}}.md`
14
+ - **Spec File**: `codev/specs/{{artifact_name}}.md`
15
+ - **Plan File**: `codev/plans/{{artifact_name}}.md`
16
16
 
17
17
  ## Prerequisites
18
18
 
@@ -74,7 +74,7 @@ After completing the plan draft, signal completion. Porch will run 3-way consult
74
74
 
75
75
  ## Output
76
76
 
77
- Create the plan file at `codev/plans/{{project_id}}-{{title}}.md`.
77
+ Create the plan file at `codev/plans/{{artifact_name}}.md`.
78
78
 
79
79
  Use the plan template from `codev/protocols/spir/templates/plan.md` if available.
80
80
 
@@ -129,7 +129,7 @@ Make commits at these milestones:
129
129
 
130
130
  **CRITICAL**: Never use `git add .` or `git add -A`. Always stage specific files:
131
131
  ```bash
132
- git add codev/plans/{{project_id}}-{{title}}.md
132
+ git add codev/plans/{{artifact_name}}.md
133
133
  ```
134
134
 
135
135
  ## Important Notes
@@ -11,9 +11,9 @@ Perform a comprehensive review, document lessons learned, and prepare for PR sub
11
11
  - **Project ID**: {{project_id}}
12
12
  - **Project Title**: {{title}}
13
13
  - **Current State**: {{current_state}}
14
- - **Spec File**: `codev/specs/{{project_id}}-{{title}}.md`
15
- - **Plan File**: `codev/plans/{{project_id}}-{{title}}.md`
16
- - **Review File**: `codev/reviews/{{project_id}}-{{title}}.md`
14
+ - **Spec File**: `codev/specs/{{artifact_name}}.md`
15
+ - **Plan File**: `codev/plans/{{artifact_name}}.md`
16
+ - **Review File**: `codev/reviews/{{artifact_name}}.md`
17
17
 
18
18
  ## Prerequisites
19
19
 
@@ -57,7 +57,7 @@ Compare final implementation to original specification:
57
57
 
58
58
  ### 3. Create Review Document
59
59
 
60
- Create `codev/reviews/{{project_id}}-{{title}}.md`:
60
+ Create `codev/reviews/{{artifact_name}}.md`:
61
61
 
62
62
  ```markdown
63
63
  # Review: {{title}}
@@ -118,7 +118,7 @@ Before PR:
118
118
 
119
119
  **IMPORTANT: Create the PR BEFORE signaling completion.** The PR must exist so that
120
120
  porch consultation reviews the actual PR, and the architect can review a real PR
121
- when the pr-ready gate fires.
121
+ when the pr gate fires.
122
122
 
123
123
  ```bash
124
124
  gh pr create --title "[Spec {{project_id}}] {{title}}" --body "$(cat <<'EOF'
@@ -135,10 +135,10 @@ gh pr create --title "[Spec {{project_id}}] {{title}}" --body "$(cat <<'EOF'
135
135
  - Manual testing completed for [Y]
136
136
 
137
137
  ## Spec
138
- Link: codev/specs/{{project_id}}-{{title}}.md
138
+ Link: codev/specs/{{artifact_name}}.md
139
139
 
140
140
  ## Review
141
- Link: codev/reviews/{{project_id}}-{{title}}.md
141
+ Link: codev/reviews/{{artifact_name}}.md
142
142
  EOF
143
143
  )"
144
144
  ```
@@ -151,7 +151,7 @@ changes, you'll be respawned with their feedback.
151
151
 
152
152
  ## Output
153
153
 
154
- - Review document at `codev/reviews/{{project_id}}-{{title}}.md`
154
+ - Review document at `codev/reviews/{{artifact_name}}.md`
155
155
  - Updated documentation (if needed)
156
156
  - Pull request created and ready for review
157
157
 
@@ -11,7 +11,7 @@ Create a comprehensive specification document that thoroughly explores the probl
11
11
  - **Project ID**: {{project_id}}
12
12
  - **Project Title**: {{title}}
13
13
  - **Current State**: {{current_state}}
14
- - **Spec File**: `codev/specs/{{project_id}}-{{title}}.md`
14
+ - **Spec File**: `codev/specs/{{artifact_name}}.md`
15
15
 
16
16
  ## Process
17
17
 
@@ -82,12 +82,12 @@ After completing the spec draft, signal completion. Porch will run 3-way consult
82
82
 
83
83
  ## Output
84
84
 
85
- Create or update the specification file at `codev/specs/{{project_id}}-{{title}}.md`.
85
+ Create or update the specification file at `codev/specs/{{artifact_name}}.md`.
86
86
 
87
87
  **IMPORTANT**: Keep spec/plan/review filenames in sync:
88
- - Spec: `codev/specs/{{project_id}}-{{title}}.md`
89
- - Plan: `codev/plans/{{project_id}}-{{title}}.md`
90
- - Review: `codev/reviews/{{project_id}}-{{title}}.md`
88
+ - Spec: `codev/specs/{{artifact_name}}.md`
89
+ - Plan: `codev/plans/{{artifact_name}}.md`
90
+ - Review: `codev/reviews/{{artifact_name}}.md`
91
91
 
92
92
  ## Signals
93
93
 
@@ -121,7 +121,7 @@ Make commits at these milestones:
121
121
 
122
122
  **CRITICAL**: Never use `git add .` or `git add -A`. Always stage specific files:
123
123
  ```bash
124
- git add codev/specs/{{project_id}}-{{title}}.md
124
+ git add codev/specs/{{artifact_name}}.md
125
125
  ```
126
126
 
127
127
  ## Important Notes
@@ -17,10 +17,10 @@
17
17
  "type": "build_verify",
18
18
  "build": {
19
19
  "prompt": "specify.md",
20
- "artifact": "codev/specs/${PROJECT_ID}-*.md"
20
+ "artifact": "codev/specs/${PROJECT_TITLE}.md"
21
21
  },
22
22
  "verify": {
23
- "type": "spec-review",
23
+ "type": "spec",
24
24
  "models": ["gemini", "codex", "claude"],
25
25
  "parallel": true
26
26
  },
@@ -39,10 +39,10 @@
39
39
  "type": "build_verify",
40
40
  "build": {
41
41
  "prompt": "plan.md",
42
- "artifact": "codev/plans/${PROJECT_ID}-*.md"
42
+ "artifact": "codev/plans/${PROJECT_TITLE}.md"
43
43
  },
44
44
  "verify": {
45
- "type": "plan-review",
45
+ "type": "plan",
46
46
  "models": ["gemini", "codex", "claude"],
47
47
  "parallel": true
48
48
  },
@@ -52,9 +52,9 @@
52
52
  "push": true
53
53
  },
54
54
  "checks": {
55
- "plan_exists": "test -f codev/plans/${PROJECT_ID}-*.md",
56
- "has_phases_json": "grep -q '\"phases\":' codev/plans/${PROJECT_ID}-*.md",
57
- "min_two_phases": "grep -o '\"id\": *\"[^\"]*\"' codev/plans/${PROJECT_ID}-*.md | wc -l | awk '$1 >= 2 {exit 0} {exit 1}'"
55
+ "plan_exists": "test -f codev/plans/${PROJECT_TITLE}.md",
56
+ "has_phases_json": "grep -q '\"phases\":' codev/plans/${PROJECT_TITLE}.md",
57
+ "min_two_phases": "grep -o '\"id\": *\"[^\"]*\"' codev/plans/${PROJECT_TITLE}.md | wc -l | awk '$1 >= 2 {exit 0} {exit 1}'"
58
58
  },
59
59
  "gate": "plan-approval",
60
60
  "next": "implement"
@@ -69,7 +69,7 @@
69
69
  "artifact": "src/**/*.{ts,tsx,js,jsx}"
70
70
  },
71
71
  "verify": {
72
- "type": "impl-review",
72
+ "type": "impl",
73
73
  "models": ["gemini", "codex", "claude"],
74
74
  "parallel": true
75
75
  },
@@ -103,10 +103,10 @@
103
103
  "type": "build_verify",
104
104
  "build": {
105
105
  "prompt": "review.md",
106
- "artifact": "codev/reviews/${PROJECT_ID}-*.md"
106
+ "artifact": "codev/reviews/${PROJECT_TITLE}.md"
107
107
  },
108
108
  "verify": {
109
- "type": "pr-ready",
109
+ "type": "pr",
110
110
  "models": ["gemini", "codex", "claude"],
111
111
  "parallel": true
112
112
  },
@@ -126,7 +126,7 @@
126
126
  "optional": true
127
127
  }
128
128
  },
129
- "gate": "pr-ready",
129
+ "gate": "pr",
130
130
  "next": null
131
131
  }
132
132
  ],
@@ -33,7 +33,7 @@ All times [timezone], [date range].
33
33
  | — | **GATE: [gate-name]** (human approval required) |
34
34
  | HH:MM | Implementation begins |
35
35
  | HH:MM | Phase N complete after N iterations |
36
- | HH:MM | **GATE: pr-ready** |
36
+ | HH:MM | **GATE: pr** |
37
37
 
38
38
  ### Autonomous Operation
39
39
 
@@ -43,7 +43,7 @@ All times [timezone], [date range].
43
43
  | Human gate wait | ~Nh Nm | Idle — waiting for approval |
44
44
  | Implementation → PR | ~Nh Nm | N phases, N consultation rounds |
45
45
 
46
- **Total wall clock** (first commit to pr-ready): **Xh Ym**
46
+ **Total wall clock** (first commit to pr): **Xh Ym**
47
47
  **Total autonomous work time** (excluding gate waits): **~Xh Ym**
48
48
  **Context window resets**: [N] (resumed automatically / required manual restart)
49
49
 
@@ -0,0 +1,72 @@
1
+ # Implementation Review Prompt
2
+
3
+ ## Context
4
+ You are reviewing implementation work during the Implement phase. A builder has completed a plan phase and needs feedback before proceeding. Your job is to verify the implementation matches the spec and plan.
5
+
6
+ ## CRITICAL: Verify Before Flagging
7
+
8
+ Before requesting changes for missing configuration, incorrect patterns, or framework issues:
9
+ 1. **Check `package.json`** for actual dependency versions — framework conventions change between major versions
10
+ 2. **Read the actual config files** (or confirm their deliberate absence) before flagging missing configs
11
+ 3. **Do not assume** your training data reflects the version in use — verify against project files
12
+ 4. If "Previous Iteration Context" is provided, read it carefully before re-raising concerns that were already disputed
13
+
14
+ ## Focus Areas
15
+
16
+ 1. **Spec Adherence**
17
+ - Does the implementation fulfill the spec requirements for this phase?
18
+ - Are acceptance criteria met?
19
+
20
+ 2. **Code Quality**
21
+ - Is the code readable and maintainable?
22
+ - Are there obvious bugs or issues?
23
+ - Are error cases handled appropriately?
24
+
25
+ 3. **Test Coverage**
26
+ - Are the tests adequate for this phase?
27
+ - Do tests cover the main paths AND edge cases?
28
+
29
+ 4. **Plan Alignment**
30
+ - Does the implementation follow the plan?
31
+ - Are there plan items skipped or partially completed?
32
+
33
+ 5. **UX Verification** (if spec has UX requirements)
34
+ - Does the actual user experience match what the spec describes?
35
+ - If spec says "async" or "non-blocking", is it actually async?
36
+
37
+ ## Verdict Format
38
+
39
+ After your review, provide your verdict in exactly this format:
40
+
41
+ ```
42
+ ---
43
+ VERDICT: [APPROVE | REQUEST_CHANGES | COMMENT]
44
+ SUMMARY: [One-line summary of your assessment]
45
+ CONFIDENCE: [HIGH | MEDIUM | LOW]
46
+ ---
47
+ KEY_ISSUES:
48
+ - [Issue 1 or "None"]
49
+ - [Issue 2]
50
+ ...
51
+ ```
52
+
53
+ **Verdict meanings:**
54
+ - `APPROVE`: Phase is complete, builder can proceed
55
+ - `REQUEST_CHANGES`: Issues that must be fixed before proceeding
56
+ - `COMMENT`: Minor suggestions, can proceed but note feedback
57
+
58
+ ## Scoping (Multi-Phase Plans)
59
+
60
+ When the implementation plan has multiple phases (e.g., scaffolding, landing, media_rtl):
61
+ - **ONLY review work belonging to the current plan phase**
62
+ - The query will specify which phase you are reviewing
63
+ - Do NOT request changes for functionality scheduled in later phases
64
+ - Do NOT flag missing features that are out of scope for this phase
65
+ - If unsure whether something belongs to this phase, check the plan file
66
+
67
+ ## Notes
68
+
69
+ - This is a phase-level review, not the final PR review
70
+ - Focus on "does this phase work" not "is the whole feature done"
71
+ - If referencing line numbers, use `file:line` format
72
+ - The builder needs actionable feedback to continue
@@ -0,0 +1,59 @@
1
+ # Plan Review Prompt
2
+
3
+ ## Context
4
+ You are reviewing an implementation plan during the Plan phase. The spec has been approved - now you must evaluate whether the plan adequately describes HOW to implement it.
5
+
6
+ ## Focus Areas
7
+
8
+ 1. **Spec Coverage**
9
+ - Does the plan address all requirements in the spec?
10
+ - Are there spec requirements not covered by any phase?
11
+ - Are there phases that go beyond the spec scope?
12
+
13
+ 2. **Phase Breakdown**
14
+ - Are phases appropriately sized (not too large or too small)?
15
+ - Is the sequence logical (dependencies respected)?
16
+ - Can each phase be completed and committed independently?
17
+
18
+ 3. **Technical Approach**
19
+ - Is the implementation approach sound?
20
+ - Are the right files/modules being modified?
21
+ - Are there obvious better approaches being missed?
22
+
23
+ 4. **Testability**
24
+ - Does each phase have clear test criteria?
25
+ - Will the Defend step (writing tests) be feasible?
26
+ - Are edge cases from the spec addressable?
27
+
28
+ 5. **Risk Assessment**
29
+ - Are there potential blockers not addressed?
30
+ - Are dependencies on other systems identified?
31
+ - Is the plan realistic given constraints?
32
+
33
+ ## Verdict Format
34
+
35
+ After your review, provide your verdict in exactly this format:
36
+
37
+ ```
38
+ ---
39
+ VERDICT: [APPROVE | REQUEST_CHANGES | COMMENT]
40
+ SUMMARY: [One-line summary of your assessment]
41
+ CONFIDENCE: [HIGH | MEDIUM | LOW]
42
+ ---
43
+ KEY_ISSUES:
44
+ - [Issue 1 or "None"]
45
+ - [Issue 2]
46
+ ...
47
+ ```
48
+
49
+ **Verdict meanings:**
50
+ - `APPROVE`: Plan is ready for human review
51
+ - `REQUEST_CHANGES`: Significant issues with approach or coverage
52
+ - `COMMENT`: Minor suggestions, plan is workable but could improve
53
+
54
+ ## Notes
55
+
56
+ - The spec has already been approved - don't re-litigate spec decisions
57
+ - Focus on the quality of the plan as a guide for builders
58
+ - Consider: Would a builder be able to follow this plan successfully?
59
+ - If referencing existing code, verify file paths seem accurate
@@ -0,0 +1,72 @@
1
+ # PR Ready Review Prompt
2
+
3
+ ## Context
4
+ You are performing a final self-check during the Review phase. The builder has completed all implementation phases and is about to create a PR. This is the last check before the work goes to the architect for integration review.
5
+
6
+ ## Focus Areas
7
+
8
+ 1. **Completeness**
9
+ - Are all spec requirements implemented?
10
+ - Are all plan phases complete?
11
+ - Is the review document written (`codev/reviews/XXXX-name.md`)?
12
+ - Are all commits properly formatted (`[Spec XXXX][Phase]`)?
13
+
14
+ 2. **Test Status**
15
+ - Do all tests pass?
16
+ - Is test coverage adequate for the changes?
17
+ - Are there any skipped or flaky tests?
18
+
19
+ 3. **Code Cleanliness**
20
+ - Is there any debug code left in?
21
+ - Are there any TODO comments that should be resolved?
22
+ - Are there any `// REVIEW:` comments that weren't addressed?
23
+ - Is the code properly formatted?
24
+
25
+ 4. **Documentation**
26
+ - Are inline comments clear where needed?
27
+ - Is the review document comprehensive?
28
+ - Are any new APIs documented?
29
+
30
+ 5. **PR Readiness**
31
+ - Is the branch up to date with main?
32
+ - Are commits atomic and well-described?
33
+ - Is the change diff reasonable in size?
34
+
35
+ ## Verdict Format
36
+
37
+ After your review, provide your verdict in exactly this format:
38
+
39
+ ```
40
+ ---
41
+ VERDICT: [APPROVE | REQUEST_CHANGES | COMMENT]
42
+ SUMMARY: [One-line summary of your assessment]
43
+ CONFIDENCE: [HIGH | MEDIUM | LOW]
44
+ ---
45
+ KEY_ISSUES:
46
+ - [Issue 1 or "None"]
47
+ - [Issue 2]
48
+ ...
49
+
50
+ PR_SUMMARY: |
51
+ ## Summary
52
+ [2-3 sentences describing what this PR does]
53
+
54
+ ## Key Changes
55
+ - [Change 1]
56
+ - [Change 2]
57
+
58
+ ## Test Plan
59
+ - [How to test]
60
+ ```
61
+
62
+ **Verdict meanings:**
63
+ - `APPROVE`: Ready to create PR
64
+ - `REQUEST_CHANGES`: Issues to fix before PR creation
65
+ - `COMMENT`: Minor items, can create PR but note feedback
66
+
67
+ ## Notes
68
+
69
+ - This is the builder's final self-review before hand-off
70
+ - The PR_SUMMARY in your output can be used as the PR description
71
+ - Focus on "is this ready for someone else to review" not "is this perfect"
72
+ - Any issues found here are cheaper to fix than during integration review