create-harness-vibe-coding 0.5.0 → 0.5.1
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
|
@@ -30,7 +30,7 @@ Force a memory learning cycle. Context-master analyzes, memory-master consolidat
|
|
|
30
30
|
| Project | `Harness/memory/tool-usage-reflections.md` | tool/command patterns found |
|
|
31
31
|
| Project | `Harness/memory/user-corrections-preferences.md` | user preferences found |
|
|
32
32
|
| Project | `Harness/memory/agent-lessons-patterns.md` | review/debug lessons found |
|
|
33
|
-
| Global |
|
|
33
|
+
| Global | `<user>/.claude/projects/*/memory/` | cross-project patterns |
|
|
34
34
|
|
|
35
35
|
## Rules
|
|
36
36
|
|
|
@@ -63,7 +63,7 @@ Root entry for Claude Code. Keep this file short.
|
|
|
63
63
|
- **Tool reflection trigger**: record a lightweight reflection when the same tool/use pattern fails 3+ times, or when a better command pattern/environment fix is found. Write it newest-first in `Harness/memory/tool-usage-reflections.md`.
|
|
64
64
|
- **User correction trigger**: record a lightweight preference/correction when the user asks to remember it, or when the user corrects the same assumption/pattern 2+ times. Write it newest-first in `Harness/memory/user-corrections-preferences.md`.
|
|
65
65
|
- **Agent lesson trigger**: record reusable lessons from review/debug loops in `Harness/memory/agent-lessons-patterns.md` when they would prevent recurrence.
|
|
66
|
-
- **WF auto-trigger**:
|
|
66
|
+
- **WF auto-trigger**: before WF closeout, dispatch `context-master` then `memory-master` (or use `/wf-learn`). The old "3x same failure" auto-trigger is unreliable — make this a mandatory closeout gate.
|
|
67
67
|
- **Context threshold trigger**: when context approaches ~85% of the window, dispatch `context-master` to analyze and write a non-blocking compression suggestion to `Harness/tasks/<task-id>/PROGRESS.md#Heartbeat`.
|
|
68
68
|
- **Closeout trigger**: during WF closeout, dispatch `context-master` to extract durable knowledge, then `memory-master` to consolidate into `Harness/memory/*`.
|
|
69
69
|
- Never record secrets, credentials, tokens, or private data.
|
|
@@ -51,7 +51,7 @@ Keywords are retrieval hints, not project facts.
|
|
|
51
51
|
|
|
52
52
|
Load the matching row only. Add adjacent docs only when the loaded doc directly names them.
|
|
53
53
|
|
|
54
|
-
Routing priority: if a request explicitly says `/wf <task>`, `/wf-max [task]`, `wf mode`, `workflow mode`, or `wk mode`, or is long, difficult, uncertain, repeated-failure, migration, architecture-heavy, browser-visible, or broad multi-agent implementation work, choose the WF row first. `wf-mode` MUST then delegate subagent coordination to `subagent-orchestrator`.
|
|
54
|
+
Routing priority: if a request explicitly says `/wf <task>`, `/wf-max [task]`, `/wf-learn`, `wf mode`, `workflow mode`, or `wk mode`, or is long, difficult, uncertain, repeated-failure, migration, architecture-heavy, browser-visible, or broad multi-agent implementation work, choose the WF row first. `wf-mode` MUST then delegate subagent coordination to `subagent-orchestrator`.
|
|
55
55
|
|
|
56
56
|
| When to Read | Keywords | Load | Output |
|
|
57
57
|
| --- | --- | --- | --- |
|
|
@@ -122,7 +122,7 @@ If verification fails:
|
|
|
122
122
|
5. Run verifier again.
|
|
123
123
|
6. Repeat until verified or blocked by missing user input/external state.
|
|
124
124
|
|
|
125
|
-
|
|
125
|
+
Before asking the user after repeated failures, dispatch `context-master` then `memory-master` (or use `/wf-learn`) to record the failure pattern, attempted paths, and root cause hypothesis. Present evidence-backed options to the user.
|
|
126
126
|
|
|
127
127
|
## Heartbeat Protocol
|
|
128
128
|
|