@plumpslabs/kuma 2.4.9 → 2.4.11
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/README.md +7 -4
- package/dist/index.js +2486 -1518
- package/package.json +3 -3
- package/packages/ide/studio/dist/index.js +184 -4
- package/packages/ide/studio/public/index.html +1075 -149
- package/plugin.json +1 -1
- package/skills/kuma/SKILL.md +80 -0
package/README.md
CHANGED
|
@@ -68,7 +68,10 @@ Kuma exposes **3 coarse-grained tools** with **15 core actions** — the full ag
|
|
|
68
68
|
| `init` | Lean project brief + restore session + branch tracking | 🔴 Required first |
|
|
69
69
|
| `research` | 5-step pipeline: cache → graph → scan → impact → decision | 🔴 Required before edits |
|
|
70
70
|
| `map` | Monorepo package topology & workspace boundary mapping | 🔴 High |
|
|
71
|
-
| `
|
|
71
|
+
| `cluster` | Concept-level subsystem clusters with typed relationship verbs | 🔴 High |
|
|
72
|
+
| `skeleton` | Compressed AST code outline (85-93% token reduction) | 🔴 High |
|
|
73
|
+
| `reuse` | Anti-duplication helper discovery before writing new code | 🔴 High |
|
|
74
|
+
| `impact` | Blast radius analysis with PageRank centrality scoring | 🔴 High |
|
|
72
75
|
| `history` | Why is this file written this way (cross-session trace) | 🔴 High |
|
|
73
76
|
| `flow` | Read a recorded architecture flow | 🔴 High |
|
|
74
77
|
|
|
@@ -87,7 +90,7 @@ Kuma exposes **3 coarse-grained tools** with **15 core actions** — the full ag
|
|
|
87
90
|
| Action | Purpose | Impact |
|
|
88
91
|
|--------|---------|--------|
|
|
89
92
|
| `guard` | Detect anti-patterns, drift, runaway loops | 🔴 Required |
|
|
90
|
-
| `verify` |
|
|
93
|
+
| `verify` | Post-edit blast radius & affected test targeting (<50ms static resolution) | 🔴 High |
|
|
91
94
|
| `checkpoint` | Labeled snapshot before risky work | 🟡 Linear |
|
|
92
95
|
| `rollback_label` | Restore a labeled snapshot | 🟡 Linear |
|
|
93
96
|
|
|
@@ -99,9 +102,9 @@ Kuma exposes exactly **3 coarse-grained tools** — the agent picks an *action*,
|
|
|
99
102
|
|
|
100
103
|
| Tool | Core Actions | Purpose |
|
|
101
104
|
|------|--------------|---------|
|
|
102
|
-
| `kuma_context` | `init`, `research`, `
|
|
105
|
+
| `kuma_context` | `init`, `research`, `map`, `cluster`, `skeleton`, `reuse`, `impact`, `history`, `flow` | Load project context, understand unfamiliar code |
|
|
103
106
|
| `kuma_memory` | `gotcha`, `decision`, `arch_flow`, `research_save`, `search` | Persistent knowledge that saves future sessions |
|
|
104
|
-
| `kuma_safety` | `guard`, `verify`, `checkpoint`, `rollback_label` | Pre-risk
|
|
107
|
+
| `kuma_safety` | `guard`, `verify`, `checkpoint`, `rollback_label` | Pre-risk guard, post-edit blast radius verification, snapshot/restore |
|
|
105
108
|
|
|
106
109
|
Everything else is an internal action — not exposed to the agent. The agent uses its **own native tools** for editing, searching, and execution — Kuma is memory & safety, not a code manager.
|
|
107
110
|
|