@fernado03/zoo-flow 0.8.2 → 0.8.4

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
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@fernado03/zoo-flow",
3
3
  "description": "Workflow control plane for Zoo Code.",
4
- "version": "0.8.2",
4
+ "version": "0.8.4",
5
5
  "type": "module",
6
6
  "bin": {
7
7
  "zoo-flow": "bin/zoo-flow.js"
@@ -85,4 +85,4 @@ MUST finish:
85
85
 
86
86
  ## 7. Save
87
87
 
88
- Write the full diagnosis (hypotheses, instrumentation, root cause, fix) to `.scratch/diagnoses/<date>/diagnose-<slug>.md`. Reference this file path in `attempt_completion` so the orchestrator can read and present it.
88
+ Write the full diagnosis (hypotheses, instrumentation, root cause, fix) to `.scratch/diagnoses/<date>/diagnose-<slug>.md`.
@@ -38,13 +38,3 @@ Do not re-read unchanged files; use prior findings unless the file changed.
38
38
  - Update `CONTEXT.md` immediately for resolved terms.
39
39
  - Keep `CONTEXT.md` glossary-only; no impl/spec notes.
40
40
  - Offer ADR only when hard to reverse + surprising + real trade-off; use `ADR-FORMAT.md`.
41
-
42
- ## Complete
43
-
44
- Call `attempt_completion` with:
45
- - questions resolved (count)
46
- - docs updated (CONTEXT.md, ADRs created/updated)
47
- - status (complete / blocked with reason)
48
- - recommended next command
49
-
50
- Do NOT use `ask_followup_question` or write results as plain text without calling the tool.
@@ -53,13 +53,3 @@ Use searches to identify dependency/call patterns before reading full modules. R
53
53
  3. If term sharpened, update `CONTEXT.md` immediately.
54
54
  4. Durable rejected reason useful later → offer ADR.
55
55
  5. Interface options requested → run interface-design workflow.
56
-
57
- ## Complete
58
-
59
- Call `attempt_completion` with:
60
- - report location (`{tmpdir}/architecture-review-{timestamp}.html`)
61
- - candidates found (count)
62
- - status (complete / blocked with reason)
63
- - recommended next command
64
-
65
- Do NOT use `ask_followup_question` or write results as plain text without calling the tool.
@@ -216,3 +216,13 @@ paths.
216
216
 
217
217
  Confirm? (yes / edit / cancel)
218
218
  ```
219
+
220
+ ## Complete
221
+
222
+ Call `attempt_completion` with:
223
+ - file paths written (CONTEXT.md, ADRs, optional docs)
224
+ - terms added (count)
225
+ - status (complete / blocked with reason)
226
+ - recommended next command
227
+
228
+ Do NOT use `ask_followup_question` or write results as plain text without calling the tool.
@@ -75,3 +75,12 @@ Seed files: GitHub=`issue-tracker-github.md`; GitLab=`issue-tracker-gitlab.md`;
75
75
  ## Done
76
76
 
77
77
  Report created/updated files. State engineering skills now read `docs/agents/*.md`; user may edit directly.
78
+
79
+ ## Complete
80
+
81
+ Call `attempt_completion` with:
82
+ - files created/updated (AGENTS.md/CLAUDE.md, docs/agents/*.md)
83
+ - issue tracker configured
84
+ - status (complete / blocked with reason)
85
+
86
+ Do NOT use `ask_followup_question` or write results as plain text without calling the tool.
@@ -43,12 +43,3 @@ Issue tracker + label vocabulary should exist; run `/setup-matt-pocock-skills` i
43
43
  ```
44
44
 
45
45
  If no blockers: `None - can start immediately`.
46
-
47
- ## Complete
48
-
49
- Call `attempt_completion` with:
50
- - issues created (count, tracker URL or `.scratch/{feature-slug}/issues/`)
51
- - status (published / blocked with reason)
52
- - recommended next command
53
-
54
- Do NOT use `ask_followup_question` or write results as plain text without calling the tool.
@@ -55,12 +55,3 @@ RULE: Do not interview user. Synthesize current context.
55
55
 
56
56
  {other notes}
57
57
  ```
58
-
59
- ## Complete
60
-
61
- Call `attempt_completion` with:
62
- - PRD location (issue tracker URL or `.scratch/{feature-slug}/PRD.md`)
63
- - status (published / blocked with reason)
64
- - recommended next command
65
-
66
- Do NOT use `ask_followup_question` or write results as plain text without calling the tool.
@@ -17,3 +17,13 @@ Read full files only when structure, ordering, or surrounding context is require
17
17
  Do not re-read unchanged files; use prior findings unless the file changed.
18
18
 
19
19
  Start with `list_files` and `search_files`/`codebase_search`. Read representative files and key entrypoints, not every file in the area.
20
+
21
+ ## Complete
22
+
23
+ Call `attempt_completion` with:
24
+ - modules mapped (list)
25
+ - key findings (summary)
26
+ - status (complete / blocked with reason)
27
+ - recommended next command
28
+
29
+ Do NOT use `ask_followup_question` or write results as plain text without calling the tool.