create-harness-vibe-coding 0.5.1 → 0.5.2

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 (6) hide show
  1. package/package.json +1 -1
  2. package/templates/common/.claude/commands/wf-max.md +1 -1
  3. package/templates/common/.claude/skills/subagent-orchestrator/SKILL.md +1 -1
  4. package/templates/common/.claude/skills/wf-mode/SKILL.md +1 -1
  5. package/templates/common/CLAUDE.md +1 -1
  6. package/templates/common/docs/README.md +3 -1
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "create-harness-vibe-coding",
3
- "version": "0.5.1",
3
+ "version": "0.5.2",
4
4
  "description": "Scaffold a 0-1 product harness for AI-assisted research, PRD, planning, architecture, build, test, and feedback loops",
5
5
  "type": "module",
6
6
  "bin": {
package/templates/common/.claude/commands/wf-max.md CHANGED
@@ -13,7 +13,7 @@ Enter maximum-parallelism workflow mode with an optional task description. Split
13
13
 
14
14
  ```text
15
15
  intake
16
- -> max-parallel exploration (5-14 read-only agents)
16
+ -> max-parallel exploration (5-10 read-only agents)
17
17
  -> synthesis + write-set coloring → dependency graph
18
18
  -> wave 1: N parallel implementers (disjoint file claims)
19
19
  -> wave 1 review: parallel spec/code/security reviewers
package/templates/common/.claude/skills/subagent-orchestrator/SKILL.md CHANGED
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: subagent-orchestrator
3
- description: Use when work needs bounded subagent coordination, parallel read-only exploration, independent review gates, broad context partitioning, or controlled handoffs after wf-mode has been selected when applicable.
3
+ description: Use when work needs bounded subagent coordination, parallel read-only exploration, independent review gates, broad context partitioning, or controlled handoffs after wf-mode has been selected.
4
4
  ---
5
5
 
6
6
  # Subagent Orchestrator
package/templates/common/.claude/skills/wf-mode/SKILL.md CHANGED
@@ -25,7 +25,7 @@ intake + 95% confidence gate
25
25
  -> bounded implementation
26
26
  -> review
27
27
  -> verification
28
- -> debugger recovery loop when verification fails (dispatch memory-master after 3 same-class failures)
28
+ -> debugger recovery loop when verification fails (dispatch context-master then memory-master, or use /wf-learn)
29
29
  -> context-master session analysis + knowledge extraction
30
30
  -> memory-master consolidation
31
31
  -> close with evidence
package/templates/common/CLAUDE.md CHANGED
@@ -11,7 +11,7 @@ Root entry for Claude Code. Keep this file short.
11
11
  - `Harness/README.md` is the task router. For every request, check `Harness/README.md#Load By Task`; if a row matches, read and follow those docs before acting.
12
12
  - `Harness/PROGRESS.md` is the global task index. Load at session start to see active task and task history.
13
13
  - If work spans more than one step, create a task capsule from `Harness/tasks/_template/` and update `Harness/tasks/<task-id>/PROGRESS.md`.
14
- - Use `/wf <task>`, `/wf-max [task]`, `/wf-learn`, `wf mode`, `workflow mode`, `wk mode`, `Harness/WF.md`, or `Harness/WF-MAX.md` for long, difficult, uncertain, multi-file, or repeated-failure work.
14
+ - Use `/wf <task>`, `/wf-max [task]`, `/wf-learn`, `wf mode`, `wf max`, `workflow mode`, `wk mode`, `Harness/WF.md`, or `Harness/WF-MAX.md` for long, difficult, uncertain, multi-file, or repeated-failure work.
15
15
  - Use `subagent-orchestrator` and `Harness/subagents.md` when coordinating multiple subagents.
16
16
  - Use `/wf update` to check for and apply scaffold updates from GitHub. See `.claude/skills/wf-update/SKILL.md`.
17
17
  - Subagents are readers and reporters. Only the main agent writes to `Harness/tasks/<task-id>/PROGRESS.md` and `Harness/tasks/<task-id>/PLAN.md`.
package/templates/common/docs/README.md CHANGED
@@ -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-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`.
54
+ Routing priority: if a request explicitly says `/wf <task>`, `/wf-max [task]`, `/wf-learn`, `wf mode`, `wf max`, `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
  | --- | --- | --- | --- |
@@ -102,6 +102,8 @@ Routing priority: if a request explicitly says `/wf <task>`, `/wf-max [task]`, `
102
102
  ```text
103
103
  Harness/README.md router only
104
104
  Harness/MEMORY.md resource index
105
+ Harness/PLAN.md active project plan
106
+ Harness/SETUP.md install/bootstrap contract
105
107
  Harness/PROGRESS.md global task index and cross-task decisions
106
108
  Harness/tasks/<id>/PROGRESS.md per-task progress, phase, heartbeat
107
109
  Harness/tasks/<id>/PLAN.md per-task implementation plan and evidence