@soleri/forge 9.2.0 → 9.3.1
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/dist/scaffold-filetree.js +1 -1
- package/dist/skills/brain-debrief/SKILL.md +12 -12
- package/dist/skills/brainstorming/SKILL.md +7 -7
- package/dist/skills/code-patrol/SKILL.md +15 -15
- package/dist/skills/context-resume/SKILL.md +8 -8
- package/dist/skills/deep-review/SKILL.md +22 -11
- package/dist/skills/executing-plans/SKILL.md +10 -9
- package/dist/skills/fix-and-learn/SKILL.md +8 -8
- package/dist/skills/health-check/SKILL.md +11 -11
- package/dist/skills/knowledge-harvest/SKILL.md +17 -17
- package/dist/skills/onboard-me/SKILL.md +10 -10
- package/dist/skills/parallel-execute/SKILL.md +46 -32
- package/dist/skills/retrospective/SKILL.md +9 -9
- package/dist/skills/second-opinion/SKILL.md +11 -8
- package/dist/skills/systematic-debugging/SKILL.md +8 -8
- package/dist/skills/test-driven-development/SKILL.md +11 -11
- package/dist/skills/vault-capture/SKILL.md +15 -15
- package/dist/skills/vault-navigator/SKILL.md +10 -10
- package/dist/skills/vault-smells/SKILL.md +24 -16
- package/dist/skills/verification-before-completion/SKILL.md +18 -18
- package/dist/skills/writing-plans/SKILL.md +9 -9
- package/dist/templates/shared-rules.js +96 -9
- package/dist/templates/shared-rules.js.map +1 -1
- package/package.json +1 -1
- package/src/scaffold-filetree.ts +1 -1
- package/src/skills/brain-debrief/SKILL.md +12 -12
- package/src/skills/brainstorming/SKILL.md +7 -7
- package/src/skills/code-patrol/SKILL.md +15 -15
- package/src/skills/context-resume/SKILL.md +8 -8
- package/src/skills/deep-review/SKILL.md +22 -11
- package/src/skills/executing-plans/SKILL.md +10 -9
- package/src/skills/fix-and-learn/SKILL.md +8 -8
- package/src/skills/health-check/SKILL.md +11 -11
- package/src/skills/knowledge-harvest/SKILL.md +17 -17
- package/src/skills/onboard-me/SKILL.md +10 -10
- package/src/skills/parallel-execute/SKILL.md +46 -32
- package/src/skills/retrospective/SKILL.md +9 -9
- package/src/skills/second-opinion/SKILL.md +11 -8
- package/src/skills/systematic-debugging/SKILL.md +8 -8
- package/src/skills/test-driven-development/SKILL.md +11 -11
- package/src/skills/vault-capture/SKILL.md +15 -15
- package/src/skills/vault-navigator/SKILL.md +10 -10
- package/src/skills/vault-smells/SKILL.md +24 -16
- package/src/skills/verification-before-completion/SKILL.md +18 -18
- package/src/skills/writing-plans/SKILL.md +9 -9
- package/src/templates/shared-rules.ts +97 -9
|
@@ -91,13 +91,13 @@ YOUR_AGENT_core op:session_capture
|
|
|
91
91
|
|
|
92
92
|
## Quick Reference
|
|
93
93
|
|
|
94
|
-
| Phase
|
|
95
|
-
|
|
96
|
-
| 0. Search
|
|
97
|
-
| 1. Root Cause
|
|
98
|
-
| 2. Pattern
|
|
99
|
-
| 3. Hypothesis
|
|
100
|
-
| 4. Implementation | Test, fix, verify
|
|
101
|
-
| 5. Capture
|
|
94
|
+
| Phase | Key Activities | Tools |
|
|
95
|
+
| ----------------- | ------------------------------ | -------------------------------------------------------- |
|
|
96
|
+
| 0. Search | Vault, web, memory | `search_intelligent`, `brain_strengths`, `memory_search` |
|
|
97
|
+
| 1. Root Cause | Read errors, reproduce, trace | `loop_iterate` |
|
|
98
|
+
| 2. Pattern | Find working examples, compare | `search_intelligent` |
|
|
99
|
+
| 3. Hypothesis | Form theory, test minimally | `loop_iterate` |
|
|
100
|
+
| 4. Implementation | Test, fix, verify | `loop_iterate` |
|
|
101
|
+
| 5. Capture | Persist root cause | `capture_knowledge`, `loop_complete` |
|
|
102
102
|
|
|
103
103
|
**Related skills:** test-driven-development, verification-before-completion, fix-and-learn
|
|
@@ -75,17 +75,17 @@ YOUR_AGENT_core op:capture_quick
|
|
|
75
75
|
- Test passes immediately (testing existing behavior, not new)
|
|
76
76
|
- Multiple behaviors in one test ("and" in name means split it)
|
|
77
77
|
|
|
78
|
-
| Problem
|
|
79
|
-
|
|
80
|
-
| Don't know how to test | Write wished-for API first
|
|
81
|
-
| Must mock everything
|
|
82
|
-
| Test setup huge
|
|
78
|
+
| Problem | Solution |
|
|
79
|
+
| ---------------------- | ---------------------------------- |
|
|
80
|
+
| Don't know how to test | Write wished-for API first |
|
|
81
|
+
| Must mock everything | Code too coupled — use DI |
|
|
82
|
+
| Test setup huge | Extract helpers or simplify design |
|
|
83
83
|
|
|
84
84
|
## Quick Reference
|
|
85
85
|
|
|
86
|
-
| Op
|
|
87
|
-
|
|
88
|
-
| `search_intelligent`
|
|
89
|
-
| `brain_strengths`
|
|
90
|
-
| `loop_start` / `loop_iterate` / `loop_complete` | TDD cycle tracking
|
|
91
|
-
| `capture_quick`
|
|
86
|
+
| Op | When to Use |
|
|
87
|
+
| ----------------------------------------------- | ---------------------------- |
|
|
88
|
+
| `search_intelligent` | Find testing patterns |
|
|
89
|
+
| `brain_strengths` | Proven testing approaches |
|
|
90
|
+
| `loop_start` / `loop_iterate` / `loop_complete` | TDD cycle tracking |
|
|
91
|
+
| `capture_quick` | Capture new testing patterns |
|
|
@@ -25,13 +25,13 @@ If similar entry exists, update it instead of creating a duplicate.
|
|
|
25
25
|
|
|
26
26
|
### 2. Classify the Knowledge
|
|
27
27
|
|
|
28
|
-
| Type
|
|
29
|
-
|
|
30
|
-
| **pattern**
|
|
31
|
-
| **anti-pattern** | Fails and should be avoided
|
|
32
|
-
| **workflow**
|
|
33
|
-
| **principle**
|
|
34
|
-
| **decision**
|
|
28
|
+
| Type | Description |
|
|
29
|
+
| ---------------- | ----------------------------------- |
|
|
30
|
+
| **pattern** | Works and should be repeated |
|
|
31
|
+
| **anti-pattern** | Fails and should be avoided |
|
|
32
|
+
| **workflow** | Steps for a specific task |
|
|
33
|
+
| **principle** | Guiding rule or heuristic |
|
|
34
|
+
| **decision** | Architectural choice with rationale |
|
|
35
35
|
|
|
36
36
|
### 3. Capture
|
|
37
37
|
|
|
@@ -76,11 +76,11 @@ For cross-project knowledge: `op:memory_promote_to_global params: { entryId: "<i
|
|
|
76
76
|
|
|
77
77
|
## Quick Reference
|
|
78
78
|
|
|
79
|
-
| Op
|
|
80
|
-
|
|
81
|
-
| `search_intelligent`
|
|
82
|
-
| `capture_knowledge` / `capture_quick` | Persist to vault
|
|
83
|
-
| `curator_groom` / `curator_enrich`
|
|
84
|
-
| `curator_contradictions`
|
|
85
|
-
| `memory_promote_to_global`
|
|
86
|
-
| `admin_health`
|
|
79
|
+
| Op | When to Use |
|
|
80
|
+
| ------------------------------------- | -------------------- |
|
|
81
|
+
| `search_intelligent` | Check for duplicates |
|
|
82
|
+
| `capture_knowledge` / `capture_quick` | Persist to vault |
|
|
83
|
+
| `curator_groom` / `curator_enrich` | Post-capture quality |
|
|
84
|
+
| `curator_contradictions` | Find conflicts |
|
|
85
|
+
| `memory_promote_to_global` | Share cross-project |
|
|
86
|
+
| `admin_health` | Verify health |
|
|
@@ -72,13 +72,13 @@ If all vault strategies return nothing, search the web. If web finds something u
|
|
|
72
72
|
|
|
73
73
|
## Quick Reference
|
|
74
74
|
|
|
75
|
-
| Op
|
|
76
|
-
|
|
77
|
-
| `search_intelligent`
|
|
78
|
-
| `search`
|
|
79
|
-
| `vault_tags` / `vault_domains`
|
|
80
|
-
| `vault_recent`
|
|
81
|
-
| `vault_age_report`
|
|
82
|
-
| `memory_cross_project_search`
|
|
83
|
-
| `brain_strengths` / `brain_global_patterns` | Proven patterns
|
|
84
|
-
| `capture_quick`
|
|
75
|
+
| Op | When to Use |
|
|
76
|
+
| ------------------------------------------- | ------------------------------ |
|
|
77
|
+
| `search_intelligent` | Default semantic search |
|
|
78
|
+
| `search` | Structured search with filters |
|
|
79
|
+
| `vault_tags` / `vault_domains` | Browse knowledge landscape |
|
|
80
|
+
| `vault_recent` | Recently modified entries |
|
|
81
|
+
| `vault_age_report` | Stale entries |
|
|
82
|
+
| `memory_cross_project_search` | Cross-project search |
|
|
83
|
+
| `brain_strengths` / `brain_global_patterns` | Proven patterns |
|
|
84
|
+
| `capture_quick` | Capture web findings |
|
|
@@ -23,6 +23,7 @@ YOUR_AGENT_core op:curator_contradictions
|
|
|
23
23
|
```
|
|
24
24
|
|
|
25
25
|
**What to look for:**
|
|
26
|
+
|
|
26
27
|
- Two patterns that recommend opposite approaches for the same situation
|
|
27
28
|
- An anti-pattern that contradicts an active pattern
|
|
28
29
|
- Entries from different time periods with conflicting advice (the older one may be stale)
|
|
@@ -38,6 +39,7 @@ YOUR_AGENT_core op:vault_age_report
|
|
|
38
39
|
```
|
|
39
40
|
|
|
40
41
|
**Indicators:**
|
|
42
|
+
|
|
41
43
|
- Entries >60 days without access or update
|
|
42
44
|
- Patterns referencing APIs, libraries, or versions that have changed
|
|
43
45
|
- Entries tagged with technologies the project no longer uses
|
|
@@ -55,6 +57,7 @@ YOUR_AGENT_core op:curator_detect_duplicates
|
|
|
55
57
|
```
|
|
56
58
|
|
|
57
59
|
**Indicators:**
|
|
60
|
+
|
|
58
61
|
- Entries with zero inbound or outbound links
|
|
59
62
|
- Entries never returned in search results (check search insights)
|
|
60
63
|
- Entries with no tags or only generic tags
|
|
@@ -73,6 +76,7 @@ YOUR_AGENT_core op:curator_detect_duplicates
|
|
|
73
76
|
```
|
|
74
77
|
|
|
75
78
|
**Indicators:**
|
|
79
|
+
|
|
76
80
|
- High similarity scores between entries
|
|
77
81
|
- Same tags and category but different titles
|
|
78
82
|
- Entries captured in different sessions about the same topic
|
|
@@ -89,6 +93,7 @@ YOUR_AGENT_core op:curator_health_audit
|
|
|
89
93
|
```
|
|
90
94
|
|
|
91
95
|
**Indicators:**
|
|
96
|
+
|
|
92
97
|
- Description under 50 characters
|
|
93
98
|
- No examples or context
|
|
94
99
|
- Missing "why" — only states "what" without rationale
|
|
@@ -107,6 +112,7 @@ YOUR_AGENT_core op:vault_tags
|
|
|
107
112
|
```
|
|
108
113
|
|
|
109
114
|
**Indicators:**
|
|
115
|
+
|
|
110
116
|
- Near-duplicate categories (e.g., "error-handling" and "errors" and "exception-handling")
|
|
111
117
|
- Categories with only 1-2 entries (too granular)
|
|
112
118
|
- Tags used inconsistently (same concept, different tag names)
|
|
@@ -123,6 +129,7 @@ YOUR_AGENT_core op:brain_strengths
|
|
|
123
129
|
```
|
|
124
130
|
|
|
125
131
|
**Indicators:**
|
|
132
|
+
|
|
126
133
|
- Patterns with high initial strength that have decayed below 0.3
|
|
127
134
|
- Patterns that were strong but haven't received positive feedback in >30 days
|
|
128
135
|
- Patterns with mixed feedback (both positive and negative) — unresolved
|
|
@@ -131,13 +138,14 @@ YOUR_AGENT_core op:brain_strengths
|
|
|
131
138
|
|
|
132
139
|
### 8. Knowledge Gap Smells
|
|
133
140
|
|
|
134
|
-
Areas where the vault
|
|
141
|
+
Areas where the vault _should_ have knowledge but doesn't.
|
|
135
142
|
|
|
136
143
|
```
|
|
137
144
|
YOUR_AGENT_core op:admin_search_insights
|
|
138
145
|
```
|
|
139
146
|
|
|
140
147
|
**Indicators:**
|
|
148
|
+
|
|
141
149
|
- Repeated search queries that return no results
|
|
142
150
|
- Domains the project uses but vault has no entries for
|
|
143
151
|
- Anti-patterns captured without corresponding patterns (what to do instead?)
|
|
@@ -166,11 +174,11 @@ YOUR_AGENT_core op:admin_search_insights
|
|
|
166
174
|
|
|
167
175
|
For each smell category, assess severity:
|
|
168
176
|
|
|
169
|
-
| Severity
|
|
170
|
-
|
|
171
|
-
| 🟢 Clean
|
|
172
|
-
| 🟡 Minor
|
|
173
|
-
| 🟠 Moderate | Multiple instances, degrading quality
|
|
177
|
+
| Severity | Meaning |
|
|
178
|
+
| ----------- | ------------------------------------------ |
|
|
179
|
+
| 🟢 Clean | No issues in this category |
|
|
180
|
+
| 🟡 Minor | 1-3 instances, low impact |
|
|
181
|
+
| 🟠 Moderate | Multiple instances, degrading quality |
|
|
174
182
|
| 🔴 Critical | Widespread, actively causing bad decisions |
|
|
175
183
|
|
|
176
184
|
### Step 3: Present the Report
|
|
@@ -237,15 +245,15 @@ After fixes: `op:brain_build_intelligence` to rebuild with clean data.
|
|
|
237
245
|
|
|
238
246
|
## Quick Reference
|
|
239
247
|
|
|
240
|
-
| Smell
|
|
241
|
-
|
|
242
|
-
| Contradictions
|
|
243
|
-
| Staleness
|
|
244
|
-
| Orphans
|
|
245
|
-
| Duplicates
|
|
246
|
-
| Shallow entries
|
|
247
|
-
| Category drift
|
|
248
|
-
| Confidence decay | `brain_strengths`
|
|
249
|
-
| Knowledge gaps
|
|
248
|
+
| Smell | Detection Op | Fix Op |
|
|
249
|
+
| ---------------- | ------------------------------ | ------------------------------- |
|
|
250
|
+
| Contradictions | `curator_contradictions` | `curator_resolve_contradiction` |
|
|
251
|
+
| Staleness | `vault_age_report` | Review + archive/update |
|
|
252
|
+
| Orphans | `admin_vault_analytics` | Link or archive |
|
|
253
|
+
| Duplicates | `curator_detect_duplicates` | `curator_groom` (merge) |
|
|
254
|
+
| Shallow entries | `curator_health_audit` | Enrich or archive |
|
|
255
|
+
| Category drift | `vault_domains` + `vault_tags` | `curator_groom_all` |
|
|
256
|
+
| Confidence decay | `brain_strengths` | Reinforce or retire |
|
|
257
|
+
| Knowledge gaps | `admin_search_insights` | `capture_knowledge` |
|
|
250
258
|
|
|
251
259
|
**Related skills:** health-check (operational status), vault-curate (active cleanup), knowledge-harvest (fill gaps)
|
|
@@ -43,12 +43,12 @@ If any check reports problems, address before claiming completion.
|
|
|
43
43
|
|
|
44
44
|
## Common Failures
|
|
45
45
|
|
|
46
|
-
| Claim
|
|
47
|
-
|
|
48
|
-
| Tests pass
|
|
49
|
-
| Build succeeds
|
|
50
|
-
| Bug fixed
|
|
51
|
-
| Requirements met | Line-by-line checklist
|
|
46
|
+
| Claim | Requires | Not Sufficient |
|
|
47
|
+
| ---------------- | ----------------------- | ----------------------------- |
|
|
48
|
+
| Tests pass | Test output: 0 failures | Previous run, "should pass" |
|
|
49
|
+
| Build succeeds | Build command: exit 0 | Linter passing |
|
|
50
|
+
| Bug fixed | Original symptom passes | "Code changed, assumed fixed" |
|
|
51
|
+
| Requirements met | Line-by-line checklist | Tests passing alone |
|
|
52
52
|
|
|
53
53
|
## Red Flags — STOP
|
|
54
54
|
|
|
@@ -57,12 +57,12 @@ If any check reports problems, address before claiming completion.
|
|
|
57
57
|
- About to commit/push/PR without verification
|
|
58
58
|
- Relying on partial verification
|
|
59
59
|
|
|
60
|
-
| Excuse
|
|
61
|
-
|
|
62
|
-
| "Should work now"
|
|
63
|
-
| "I'm confident"
|
|
64
|
-
| "Just this once"
|
|
65
|
-
| "Partial check is enough" | Partial proves nothing
|
|
60
|
+
| Excuse | Reality |
|
|
61
|
+
| ------------------------- | -------------------------- |
|
|
62
|
+
| "Should work now" | RUN the verification |
|
|
63
|
+
| "I'm confident" | Confidence is not evidence |
|
|
64
|
+
| "Just this once" | No exceptions |
|
|
65
|
+
| "Partial check is enough" | Partial proves nothing |
|
|
66
66
|
|
|
67
67
|
## After Verification
|
|
68
68
|
|
|
@@ -77,9 +77,9 @@ Capture session summary: `YOUR_AGENT_core op:session_capture params: { summary:
|
|
|
77
77
|
|
|
78
78
|
## Quick Reference
|
|
79
79
|
|
|
80
|
-
| Op
|
|
81
|
-
|
|
82
|
-
| `admin_health`
|
|
83
|
-
| `admin_diagnostic`
|
|
84
|
-
| `admin_vault_analytics` | Knowledge quality metrics
|
|
85
|
-
| `session_capture`
|
|
80
|
+
| Op | When to Use |
|
|
81
|
+
| ----------------------- | ----------------------------------- |
|
|
82
|
+
| `admin_health` | Quick system health check |
|
|
83
|
+
| `admin_diagnostic` | Comprehensive diagnostic |
|
|
84
|
+
| `admin_vault_analytics` | Knowledge quality metrics |
|
|
85
|
+
| `session_capture` | Persist verified completion context |
|
|
@@ -97,12 +97,12 @@ Offer execution choice: subagent-driven (this session) or parallel session with
|
|
|
97
97
|
|
|
98
98
|
## Quick Reference
|
|
99
99
|
|
|
100
|
-
| Op
|
|
101
|
-
|
|
102
|
-
| `search_intelligent`
|
|
103
|
-
| `brain_strengths`
|
|
104
|
-
| `create_plan`
|
|
105
|
-
| `plan_grade` / `plan_auto_improve` | Grade and improve
|
|
106
|
-
| `plan_iterate`
|
|
107
|
-
| `plan_split`
|
|
108
|
-
| `approve_plan`
|
|
100
|
+
| Op | When to Use |
|
|
101
|
+
| ---------------------------------- | ----------------------------- |
|
|
102
|
+
| `search_intelligent` | Find patterns before planning |
|
|
103
|
+
| `brain_strengths` | Proven approaches |
|
|
104
|
+
| `create_plan` | Create tracked plan |
|
|
105
|
+
| `plan_grade` / `plan_auto_improve` | Grade and improve |
|
|
106
|
+
| `plan_iterate` | Iterate with feedback |
|
|
107
|
+
| `plan_split` | Split into tasks |
|
|
108
|
+
| `approve_plan` | Lock in approved plan |
|
|
@@ -109,8 +109,7 @@ const ENGINE_RULES_LINES = [
|
|
|
109
109
|
'## Planning',
|
|
110
110
|
'<!-- soleri:planning -->',
|
|
111
111
|
'',
|
|
112
|
-
'-
|
|
113
|
-
'- Use `op:create_plan` before writing ANY code. Show the plan, wait for approval.',
|
|
112
|
+
'- For complex tasks, use `op:create_plan` before writing code. Simple tasks can execute directly — but always run `op:orchestrate_complete`.',
|
|
114
113
|
'- Two-gate approval: Gate 1 (`op:approve_plan`), Gate 2 (`op:plan_split`). Never skip either.',
|
|
115
114
|
'- Wait for explicit "yes" / "approve" before proceeding past each gate.',
|
|
116
115
|
'- After execution: `op:plan_reconcile` (drift report) then `op:plan_complete_lifecycle` (knowledge capture, archive).',
|
|
@@ -118,6 +117,26 @@ const ENGINE_RULES_LINES = [
|
|
|
118
117
|
'- On session start: check for plans in `executing`/`reconciling` state and remind.',
|
|
119
118
|
'- Exceptions: read-only operations, user says "just do it", single-line fixes.',
|
|
120
119
|
'',
|
|
120
|
+
'### Task Auto-Assessment',
|
|
121
|
+
'',
|
|
122
|
+
'When picking up a work task (including GH issues decomposed from a parent plan), autonomously assess complexity — do NOT ask the user whether to create a plan.',
|
|
123
|
+
'',
|
|
124
|
+
'| Signal | Classification | Action |',
|
|
125
|
+
'|--------|---------------|--------|',
|
|
126
|
+
'| Single file, clear acceptance criteria | **Simple** | Execute directly |',
|
|
127
|
+
'| Approach already described in parent plan | **Simple** | Execute directly |',
|
|
128
|
+
'| Touches 3+ files or has cross-cutting concerns | **Complex** | Create scoped plan |',
|
|
129
|
+
'| Unresolved design decisions not in parent plan | **Complex** | Create scoped plan |',
|
|
130
|
+
'| New dependencies or architectural choices needed | **Complex** | Create scoped plan |',
|
|
131
|
+
'',
|
|
132
|
+
'**Simple task flow:** Vault search (quick) → execute → `op:orchestrate_complete` (captures knowledge).',
|
|
133
|
+
'',
|
|
134
|
+
'**Complex task flow:** Vault search → create lightweight scoped plan → two-gate approval → execute → reconcile → complete.',
|
|
135
|
+
'',
|
|
136
|
+
'**Key rule:** Knowledge gets captured either way via `op:orchestrate_complete`. Planning ceremony is for *decision-making*, not record-keeping.',
|
|
137
|
+
'',
|
|
138
|
+
'**Anti-pattern:** Creating a full graded plan for trivial tasks (add a CSS class, rename a variable, single-line fix).',
|
|
139
|
+
'',
|
|
121
140
|
'### Grade Gate',
|
|
122
141
|
'',
|
|
123
142
|
'**MANDATORY**: Plans must grade **A or higher** before approval. The engine enforces this programmatically.',
|
|
@@ -242,12 +261,40 @@ const ENGINE_RULES_LINES = [
|
|
|
242
261
|
'## Work Task Routing',
|
|
243
262
|
'<!-- soleri:task-routing -->',
|
|
244
263
|
'',
|
|
245
|
-
'
|
|
246
|
-
'
|
|
247
|
-
'-
|
|
248
|
-
'
|
|
264
|
+
'On every work task, assess complexity then route:',
|
|
265
|
+
'',
|
|
266
|
+
'### Auto-Assessment',
|
|
267
|
+
'',
|
|
268
|
+
'Evaluate these signals before deciding the execution path:',
|
|
269
|
+
'',
|
|
270
|
+
'| Signal | Simple (< 40) | Complex (≥ 40) |',
|
|
271
|
+
'|--------|---------------|----------------|',
|
|
272
|
+
'| Files touched | 1-2 | 3+ |',
|
|
273
|
+
'| Cross-cutting concerns | No | Yes |',
|
|
274
|
+
'| New dependencies | None | Yes |',
|
|
275
|
+
'| Design decisions | Already decided | Unresolved |',
|
|
276
|
+
'| Approach described | In parent plan/issue | Not yet |',
|
|
277
|
+
'',
|
|
278
|
+
'### Routing',
|
|
279
|
+
'',
|
|
280
|
+
'- **Simple tasks** → execute directly → `op:orchestrate_complete` (always)',
|
|
281
|
+
'- **Complex tasks** → `op:orchestrate_plan` → approve → execute → `op:orchestrate_complete` (always)',
|
|
282
|
+
'',
|
|
283
|
+
'### The Non-Negotiable Rule',
|
|
249
284
|
'',
|
|
250
|
-
'
|
|
285
|
+
'`op:orchestrate_complete` runs for EVERY task — simple or complex. This captures:',
|
|
286
|
+
'- Knowledge to vault (patterns learned, decisions made)',
|
|
287
|
+
'- Session summary (what was done, files changed)',
|
|
288
|
+
'- Brain feedback (what worked, what didn\'t)',
|
|
289
|
+
'',
|
|
290
|
+
'Without completion, the knowledge trail is lost. The code is in git, but the WHY disappears.',
|
|
291
|
+
'',
|
|
292
|
+
'### Exceptions (skip assessment, execute directly)',
|
|
293
|
+
'',
|
|
294
|
+
'- Read-only operations (search, status, health check)',
|
|
295
|
+
'- User explicitly says "just do it"',
|
|
296
|
+
'- Single-line fixes (typo, rename, one-liner)',
|
|
297
|
+
'- Questions and explanations',
|
|
251
298
|
'',
|
|
252
299
|
// ─── Intent Detection ────────────────────────────────────
|
|
253
300
|
'## Intent Detection',
|
|
@@ -322,15 +369,55 @@ const ENGINE_RULES_LINES = [
|
|
|
322
369
|
'',
|
|
323
370
|
'**Do NOT suggest tools when:** the user is having a conversation (not a task), already declined, or explicitly says "just tell me".',
|
|
324
371
|
'',
|
|
372
|
+
// ─── Overlay Mode ─────────────────────────────────────────
|
|
373
|
+
'## Overlay Mode — Active Agent Protocol',
|
|
374
|
+
'<!-- soleri:overlay-mode -->',
|
|
375
|
+
'',
|
|
376
|
+
'When you are activated as an agent (via greeting or activation command), you ARE this agent — not Claude with tools on the side. You drive the full cycle through your toolset.',
|
|
377
|
+
'',
|
|
378
|
+
'### Tool-First Routing (MANDATORY when active)',
|
|
379
|
+
'',
|
|
380
|
+
'On every user request:',
|
|
381
|
+
'1. **Discover capabilities** — call `op:admin_tool_list` on first request of the session (or after context compaction resets your state)',
|
|
382
|
+
'2. **Parse intent** — what does the user want? Use semantic-first analysis.',
|
|
383
|
+
'3. **Route through agent tools** — always prefer your MCP tools over raw Claude reasoning:',
|
|
384
|
+
' - **Knowledge questions** → vault search before answering from training data',
|
|
385
|
+
' - **Recommendations** → brain recommend before proposing approaches',
|
|
386
|
+
' - **Work tasks** → orchestrate plan before writing code',
|
|
387
|
+
' - **Quality checks** → curator or admin health before manual inspection',
|
|
388
|
+
' - **Learning moments** → capture to vault, don\'t just say "I\'ll remember"',
|
|
389
|
+
'4. **Fall back only when no tool fits** — file read/write/edit, git operations, shell commands, casual conversation',
|
|
390
|
+
'',
|
|
391
|
+
'### Self-Healing Discovery',
|
|
392
|
+
'',
|
|
393
|
+
'- After activation or context compaction, call `op:admin_tool_list` to refresh your capability inventory',
|
|
394
|
+
'- Do NOT rely on memorized tool lists from earlier in the conversation',
|
|
395
|
+
'- The tool list adapts when packs are installed — always discover dynamically',
|
|
396
|
+
'',
|
|
397
|
+
'### Character Persistence',
|
|
398
|
+
'',
|
|
399
|
+
'- All communication flows through your persona\'s voice — tone, vocabulary, opinions',
|
|
400
|
+
'- Stay in character until explicitly deactivated',
|
|
401
|
+
'- Context compaction does not change who you are — these rules persist in CLAUDE.md',
|
|
402
|
+
'- If you notice yourself dropping character, re-read your activation context',
|
|
403
|
+
'',
|
|
404
|
+
'### What NOT to Route Through Tools',
|
|
405
|
+
'',
|
|
406
|
+
'- Pure file read/write/edit operations (use Read, Edit, Write tools directly)',
|
|
407
|
+
'- Git operations (commit, push, branch, status)',
|
|
408
|
+
'- Shell commands the user explicitly requests',
|
|
409
|
+
'- Casual conversation, greetings, explanations',
|
|
410
|
+
'- One-line fixes where planning overhead exceeds the work',
|
|
411
|
+
'',
|
|
325
412
|
// ─── Session Lifecycle ───────────────────────────────────
|
|
326
413
|
'## Session Lifecycle',
|
|
327
414
|
'<!-- soleri:session -->',
|
|
328
415
|
'',
|
|
329
416
|
'### Session Start Protocol',
|
|
330
417
|
'',
|
|
331
|
-
'
|
|
332
|
-
'Call `op:session_start` only when you need project context for a task (not on every message).',
|
|
418
|
+
'On activation, discover capabilities via `op:admin_tool_list`. Call `op:register` when project context is needed for a task.',
|
|
333
419
|
'Call `op:activate` only when checking evolved capabilities or recovering session state.',
|
|
420
|
+
'After context compaction, re-discover capabilities — do not assume your tool inventory is still cached.',
|
|
334
421
|
'',
|
|
335
422
|
'### Context Compaction',
|
|
336
423
|
'',
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"shared-rules.js","sourceRoot":"","sources":["../../src/templates/shared-rules.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,MAAM,aAAa,GAAG,qBAAqB,CAAC;AAE5C,MAAM,UAAU,eAAe;IAC7B,OAAO,aAAa,CAAC;AACvB,CAAC;AAED,qEAAqE;AACrE,MAAM,UAAU,qBAAqB;IACnC,OAAO,kBAAkB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AACvC,CAAC;AAED,MAAM,kBAAkB,GAAa;IACnC,QAAQ,aAAa,MAAM;IAC3B,EAAE;IACF,uBAAuB;IACvB,EAAE;IACF,qGAAqG;IACrG,EAAE;IAEF,2DAA2D;IAC3D,mBAAmB;IACnB,gCAAgC;IAChC,EAAE;IACF,2MAA2M;IAC3M,EAAE;IACF,kIAAkI;IAClI,qHAAqH;IACrH,iFAAiF;IACjF,iGAAiG;IACjG,8GAA8G;IAC9G,EAAE;IACF,uBAAuB;IACvB,EAAE;IACF,2EAA2E;IAC3E,EAAE;IACF,4EAA4E;IAC5E,2DAA2D;IAC3D,qDAAqD;IACrD,gFAAgF;IAChF,gEAAgE;IAChE,EAAE;IACF,+BAA+B;IAC/B,EAAE;IACF,iFAAiF;IACjF,EAAE;IACF,oGAAoG;IACpG,oFAAoF;IACpF,wEAAwE;IACxE,EAAE;IACF,oIAAoI;IACpI,EAAE;IAEF,2DAA2D;IAC3D,uBAAuB;IACvB,oCAAoC;IACpC,EAAE;IACF,8FAA8F;IAC9F,uFAAuF;IACvF,EAAE;IAEF,2DAA2D;IAC3D,+BAA+B;IAC/B,wCAAwC;IACxC,EAAE;IACF,+GAA+G;IAC/G,EAAE;IACF,iGAAiG;IACjG,yEAAyE;IACzE,iGAAiG;IACjG,uEAAuE;IACvE,EAAE;IACF,yOAAyO;IACzO,EAAE;IACF,mBAAmB;IACnB,mBAAmB;IACnB,yFAAyF;IACzF,mGAAmG;IACnG,+FAA+F;IAC/F,EAAE;IAEF,0DAA0D;IAC1D,wBAAwB;IACxB,gCAAgC;IAChC,EAAE;IACF,2FAA2F;IAC3F,EAAE;IACF,2GAA2G;IAC3G,+KAA+K;IAC/K,EAAE;IACF,qFAAqF;IACrF,EAAE;IAEF,4DAA4D;IAC5D,4CAA4C;IAC5C,gCAAgC;IAChC,EAAE;IACF,2KAA2K;IAC3K,EAAE;IACF,8FAA8F;IAC9F,wHAAwH;IACxH,+HAA+H;IAC/H,uGAAuG;IACvG,qEAAqE;IACrE,sGAAsG;IACtG,EAAE;IAEF,4DAA4D;IAC5D,aAAa;IACb,0BAA0B;IAC1B,EAAE;IACF,
|
|
1
|
+
{"version":3,"file":"shared-rules.js","sourceRoot":"","sources":["../../src/templates/shared-rules.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,MAAM,aAAa,GAAG,qBAAqB,CAAC;AAE5C,MAAM,UAAU,eAAe;IAC7B,OAAO,aAAa,CAAC;AACvB,CAAC;AAED,qEAAqE;AACrE,MAAM,UAAU,qBAAqB;IACnC,OAAO,kBAAkB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AACvC,CAAC;AAED,MAAM,kBAAkB,GAAa;IACnC,QAAQ,aAAa,MAAM;IAC3B,EAAE;IACF,uBAAuB;IACvB,EAAE;IACF,qGAAqG;IACrG,EAAE;IAEF,2DAA2D;IAC3D,mBAAmB;IACnB,gCAAgC;IAChC,EAAE;IACF,2MAA2M;IAC3M,EAAE;IACF,kIAAkI;IAClI,qHAAqH;IACrH,iFAAiF;IACjF,iGAAiG;IACjG,8GAA8G;IAC9G,EAAE;IACF,uBAAuB;IACvB,EAAE;IACF,2EAA2E;IAC3E,EAAE;IACF,4EAA4E;IAC5E,2DAA2D;IAC3D,qDAAqD;IACrD,gFAAgF;IAChF,gEAAgE;IAChE,EAAE;IACF,+BAA+B;IAC/B,EAAE;IACF,iFAAiF;IACjF,EAAE;IACF,oGAAoG;IACpG,oFAAoF;IACpF,wEAAwE;IACxE,EAAE;IACF,oIAAoI;IACpI,EAAE;IAEF,2DAA2D;IAC3D,uBAAuB;IACvB,oCAAoC;IACpC,EAAE;IACF,8FAA8F;IAC9F,uFAAuF;IACvF,EAAE;IAEF,2DAA2D;IAC3D,+BAA+B;IAC/B,wCAAwC;IACxC,EAAE;IACF,+GAA+G;IAC/G,EAAE;IACF,iGAAiG;IACjG,yEAAyE;IACzE,iGAAiG;IACjG,uEAAuE;IACvE,EAAE;IACF,yOAAyO;IACzO,EAAE;IACF,mBAAmB;IACnB,mBAAmB;IACnB,yFAAyF;IACzF,mGAAmG;IACnG,+FAA+F;IAC/F,EAAE;IAEF,0DAA0D;IAC1D,wBAAwB;IACxB,gCAAgC;IAChC,EAAE;IACF,2FAA2F;IAC3F,EAAE;IACF,2GAA2G;IAC3G,+KAA+K;IAC/K,EAAE;IACF,qFAAqF;IACrF,EAAE;IAEF,4DAA4D;IAC5D,4CAA4C;IAC5C,gCAAgC;IAChC,EAAE;IACF,2KAA2K;IAC3K,EAAE;IACF,8FAA8F;IAC9F,wHAAwH;IACxH,+HAA+H;IAC/H,uGAAuG;IACvG,qEAAqE;IACrE,sGAAsG;IACtG,EAAE;IAEF,4DAA4D;IAC5D,aAAa;IACb,0BAA0B;IAC1B,EAAE;IACF,8IAA8I;IAC9I,+FAA+F;IAC/F,yEAAyE;IACzE,uHAAuH;IACvH,2FAA2F;IAC3F,oFAAoF;IACpF,gFAAgF;IAChF,EAAE;IACF,0BAA0B;IAC1B,EAAE;IACF,iKAAiK;IACjK,EAAE;IACF,sCAAsC;IACtC,qCAAqC;IACrC,4EAA4E;IAC5E,+EAA+E;IAC/E,uFAAuF;IACvF,uFAAuF;IACvF,yFAAyF;IACzF,EAAE;IACF,wGAAwG;IACxG,EAAE;IACF,4HAA4H;IAC5H,EAAE;IACF,iJAAiJ;IACjJ,EAAE;IACF,wHAAwH;IACxH,EAAE;IACF,gBAAgB;IAChB,EAAE;IACF,6GAA6G;IAC7G,EAAE;IACF,wFAAwF;IACxF,8HAA8H;IAC9H,4GAA4G;IAC5G,6EAA6E;IAC7E,EAAE;IACF,sBAAsB;IACtB,EAAE;IACF,mCAAmC;IACnC,mCAAmC;IACnC,mDAAmD;IACnD,2CAA2C;IAC3C,+CAA+C;IAC/C,0DAA0D;IAC1D,4BAA4B;IAC5B,EAAE;IACF,uBAAuB;IACvB,EAAE;IACF,8CAA8C;IAC9C,EAAE;IACF,KAAK;IACL,wBAAwB;IACxB,EAAE;IACF,mBAAmB;IACnB,mBAAmB;IACnB,4BAA4B;IAC5B,8BAA8B;IAC9B,uCAAuC;IACvC,2BAA2B;IAC3B,uCAAuC;IACvC,EAAE;IACF,+BAA+B;IAC/B,EAAE;IACF,YAAY;IACZ,yBAAyB;IACzB,yBAAyB;IACzB,yBAAyB;IACzB,EAAE;IACF,eAAe;IACf,iBAAiB;IACjB,iBAAiB;IACjB,qBAAqB;IACrB,KAAK;IACL,EAAE;IACF,wEAAwE;IACxE,EAAE;IACF,kBAAkB;IAClB,EAAE;IACF,KAAK;IACL,mBAAmB;IACnB,mBAAmB;IACnB,wCAAwC;IACxC,+BAA+B;IAC/B,EAAE;IACF,6CAA6C;IAC7C,6CAA6C;IAC7C,kCAAkC;IAClC,KAAK;IACL,EAAE;IAEF,4DAA4D;IAC5D,sBAAsB;IACtB,mCAAmC;IACnC,EAAE;IACF,6EAA6E;IAC7E,EAAE;IACF,qCAAqC;IACrC,KAAK;IACL,kCAAkC;IAClC,kCAAkC;IAClC,2BAA2B;IAC3B,KAAK;IACL,EAAE;IACF,wEAAwE;IACxE,EAAE;IACF,4FAA4F;IAC5F,EAAE;IAEF,4DAA4D;IAC5D,kBAAkB;IAClB,+BAA+B;IAC/B,EAAE;IACF,sDAAsD;IACtD,EAAE;IACF,mBAAmB;IACnB,0CAA0C;IAC1C,2BAA2B;IAC3B,2CAA2C;IAC3C,8EAA8E;IAC9E,EAAE;IACF,2BAA2B;IAC3B,KAAK;IACL,+BAA+B;IAC/B,kCAAkC;IAClC,wCAAwC;IACxC,KAAK;IACL,EAAE;IAEF,2DAA2D;IAC3D,sBAAsB;IACtB,mCAAmC;IACnC,EAAE;IACF,2FAA2F;IAC3F,EAAE;IACF,+CAA+C;IAC/C,+CAA+C;IAC/C,2DAA2D;IAC3D,2DAA2D;IAC3D,oEAAoE;IACpE,6DAA6D;IAC7D,EAAE;IACF,gEAAgE;IAChE,EAAE;IACF,6BAA6B;IAC7B,8BAA8B;IAC9B,6DAA6D;IAC7D,mEAAmE;IACnE,gDAAgD;IAChD,uDAAuD;IACvD,EAAE;IAEF,4DAA4D;IAC5D,sBAAsB;IACtB,8BAA8B;IAC9B,EAAE;IACF,mDAAmD;IACnD,EAAE;IACF,qBAAqB;IACrB,EAAE;IACF,4DAA4D;IAC5D,EAAE;IACF,6CAA6C;IAC7C,6CAA6C;IAC7C,8BAA8B;IAC9B,uCAAuC;IACvC,mCAAmC;IACnC,qDAAqD;IACrD,yDAAyD;IACzD,EAAE;IACF,aAAa;IACb,EAAE;IACF,4EAA4E;IAC5E,sGAAsG;IACtG,EAAE;IACF,6BAA6B;IAC7B,EAAE;IACF,mFAAmF;IACnF,yDAAyD;IACzD,kDAAkD;IAClD,8CAA8C;IAC9C,EAAE;IACF,8FAA8F;IAC9F,EAAE;IACF,oDAAoD;IACpD,EAAE;IACF,uDAAuD;IACvD,qCAAqC;IACrC,+CAA+C;IAC/C,8BAA8B;IAC9B,EAAE;IAEF,4DAA4D;IAC5D,qBAAqB;IACrB,kCAAkC;IAClC,EAAE;IACF,4EAA4E;IAC5E,EAAE;IACF,qBAAqB;IACrB,qBAAqB;IACrB,0DAA0D;IAC1D,yDAAyD;IACzD,oDAAoD;IACpD,uDAAuD;IACvD,wDAAwD;IACxD,mDAAmD;IACnD,EAAE;IACF,iFAAiF;IACjF,EAAE;IAEF,4DAA4D;IAC5D,8BAA8B;IAC9B,iCAAiC;IACjC,EAAE;IACF,gHAAgH;IAChH,uHAAuH;IACvH,EAAE;IACF,mCAAmC;IACnC,oCAAoC;IACpC,2DAA2D;IAC3D,kDAAkD;IAClD,EAAE;IAEF,4DAA4D;IAC5D,wBAAwB;IACxB,uBAAuB;IACvB,EAAE;IACF,2GAA2G;IAC3G,6HAA6H;IAC7H,2FAA2F;IAC3F,EAAE;IAEF,4DAA4D;IAC5D,yBAAyB;IACzB,+BAA+B;IAC/B,EAAE;IACF,wFAAwF;IACxF,iFAAiF;IACjF,EAAE;IAEF,0DAA0D;IAC1D,kBAAkB;IAClB,+BAA+B;IAC/B,EAAE;IACF,wJAAwJ;IACxJ,EAAE;IACF,kOAAkO;IAClO,EAAE;IACF,2BAA2B;IAC3B,EAAE;IACF,4CAA4C;IAC5C,2CAA2C;IAC3C,oJAAoJ;IACpJ,wJAAwJ;IACxJ,wIAAwI;IACxI,kJAAkJ;IAClJ,kHAAkH;IAClH,4HAA4H;IAC5H,0IAA0I;IAC1I,sJAAsJ;IACtJ,mIAAmI;IACnI,oHAAoH;IACpH,EAAE;IACF,oBAAoB;IACpB,EAAE;IACF,mHAAmH;IACnH,EAAE;IACF,qIAAqI;IACrI,EAAE;IAEF,6DAA6D;IAC7D,yCAAyC;IACzC,8BAA8B;IAC9B,EAAE;IACF,iLAAiL;IACjL,EAAE;IACF,gDAAgD;IAChD,EAAE;IACF,wBAAwB;IACxB,0IAA0I;IAC1I,6EAA6E;IAC7E,4FAA4F;IAC5F,iFAAiF;IACjF,wEAAwE;IACxE,4DAA4D;IAC5D,4EAA4E;IAC5E,gFAAgF;IAChF,qHAAqH;IACrH,EAAE;IACF,4BAA4B;IAC5B,EAAE;IACF,0GAA0G;IAC1G,wEAAwE;IACxE,+EAA+E;IAC/E,EAAE;IACF,2BAA2B;IAC3B,EAAE;IACF,sFAAsF;IACtF,kDAAkD;IAClD,qFAAqF;IACrF,8EAA8E;IAC9E,EAAE;IACF,qCAAqC;IACrC,EAAE;IACF,+EAA+E;IAC/E,iDAAiD;IACjD,+CAA+C;IAC/C,gDAAgD;IAChD,2DAA2D;IAC3D,EAAE;IAEF,4DAA4D;IAC5D,sBAAsB;IACtB,yBAAyB;IACzB,EAAE;IACF,4BAA4B;IAC5B,EAAE;IACF,8HAA8H;IAC9H,yFAAyF;IACzF,yGAAyG;IACzG,EAAE;IACF,wBAAwB;IACxB,EAAE;IACF,yEAAyE;IACzE,gEAAgE;IAChE,EAAE;IAEF,2DAA2D;IAC3D,eAAe;IACf,qBAAqB;IACrB,EAAE;IACF,mJAAmJ;IACnJ,EAAE;IACF,qBAAqB;IACrB,EAAE;IACF,4BAA4B;IAC5B,2BAA2B;IAC3B,uFAAuF;IACvF,gGAAgG;IAChG,kHAAkH;IAClH,kFAAkF;IAClF,mEAAmE;IACnE,8DAA8D;IAC9D,+DAA+D;IAC/D,EAAE;IACF,uBAAuB;IACvB,EAAE;IACF,4BAA4B;IAC5B,2BAA2B;IAC3B,8FAA8F;IAC9F,kFAAkF;IAClF,kFAAkF;IAClF,qDAAqD;IACrD,sEAAsE;IACtE,2EAA2E;IAC3E,+DAA+D;IAC/D,EAAE;IACF,gBAAgB;IAChB,EAAE;IACF,4BAA4B;IAC5B,2BAA2B;IAC3B,4DAA4D;IAC5D,uEAAuE;IACvE,+EAA+E;IAC/E,mEAAmE;IACnE,EAAE;IACF,oBAAoB;IACpB,EAAE;IACF,4BAA4B;IAC5B,2BAA2B;IAC3B,4EAA4E;IAC5E,uFAAuF;IACvF,4DAA4D;IAC5D,uDAAuD;IACvD,2DAA2D;IAC3D,EAAE;IACF,0BAA0B;IAC1B,EAAE;IACF,4BAA4B;IAC5B,2BAA2B;IAC3B,kGAAkG;IAClG,wDAAwD;IACxD,+DAA+D;IAC/D,8FAA8F;IAC9F,mEAAmE;IACnE,EAAE;IACF,kCAAkC;IAClC,EAAE;IACF,2BAA2B;IAC3B,2BAA2B;IAC3B,4FAA4F;IAC5F,6FAA6F;IAC7F,oFAAoF;IACpF,wCAAwC;IACxC,wEAAwE;IACxE,EAAE;IAEF,8DAA8D;IAC9D,0BAA0B;IAC1B,uCAAuC;IACvC,EAAE;IACF,mEAAmE;IACnE,EAAE;IACF,cAAc;IACd,EAAE;IACF,mDAAmD;IACnD,wEAAwE;IACxE,0DAA0D;IAC1D,EAAE;IACF,kBAAkB;IAClB,EAAE;IACF,uEAAuE;IACvE,uDAAuD;IACvD,yDAAyD;IACzD,EAAE;IACF,WAAW;IACX,EAAE;IACF,mDAAmD;IACnD,iEAAiE;IACjE,0DAA0D;IAC1D,EAAE;IAEF,SAAS,aAAa,MAAM;CAC7B,CAAC"}
|
package/package.json
CHANGED
package/src/scaffold-filetree.ts
CHANGED
|
@@ -95,7 +95,7 @@ When building a new feature, adding functionality, or creating components.
|
|
|
95
95
|
tools: `tools:
|
|
96
96
|
- soleri_vault op:search_intelligent
|
|
97
97
|
- soleri_vault op:capture_knowledge
|
|
98
|
-
-
|
|
98
|
+
- soleri_links op:link_entries
|
|
99
99
|
- soleri_plan op:create_plan
|
|
100
100
|
- soleri_plan op:approve_plan
|
|
101
101
|
- soleri_brain op:recommend
|
|
@@ -56,15 +56,15 @@ Format as a report with: Strengths, Risks (recurring anti-patterns), Gaps, Stale
|
|
|
56
56
|
|
|
57
57
|
## Quick Reference
|
|
58
58
|
|
|
59
|
-
| Op
|
|
60
|
-
|
|
61
|
-
| `brain_stats`
|
|
62
|
-
| `brain_strengths`
|
|
63
|
-
| `brain_global_patterns`
|
|
64
|
-
| `brain_recommend`
|
|
65
|
-
| `brain_build_intelligence`
|
|
66
|
-
| `memory_topics` / `memory_stats` | Knowledge clusters and health
|
|
67
|
-
| `vault_age_report`
|
|
68
|
-
| `curator_health_audit`
|
|
69
|
-
| `admin_vault_analytics`
|
|
70
|
-
| `admin_search_insights`
|
|
59
|
+
| Op | When to Use |
|
|
60
|
+
| -------------------------------- | ---------------------------------- |
|
|
61
|
+
| `brain_stats` | Aggregate metrics |
|
|
62
|
+
| `brain_strengths` | Proven patterns ranked |
|
|
63
|
+
| `brain_global_patterns` | Cross-project patterns |
|
|
64
|
+
| `brain_recommend` | Project-similarity recommendations |
|
|
65
|
+
| `brain_build_intelligence` | Rebuild intelligence pipeline |
|
|
66
|
+
| `memory_topics` / `memory_stats` | Knowledge clusters and health |
|
|
67
|
+
| `vault_age_report` | Stale entries |
|
|
68
|
+
| `curator_health_audit` | Vault quality score |
|
|
69
|
+
| `admin_vault_analytics` | Knowledge quality metrics |
|
|
70
|
+
| `admin_search_insights` | Search miss analysis |
|
|
@@ -79,11 +79,11 @@ Write validated design to `docs/plans/YYYY-MM-DD-<topic>-design.md` and commit.
|
|
|
79
79
|
|
|
80
80
|
## Quick Reference
|
|
81
81
|
|
|
82
|
-
| Op
|
|
83
|
-
|
|
84
|
-
| `route_intent`
|
|
85
|
-
| `search_intelligent`
|
|
82
|
+
| Op | When to Use |
|
|
83
|
+
| ------------------------------ | -------------------------- |
|
|
84
|
+
| `route_intent` | Classify work type |
|
|
85
|
+
| `search_intelligent` | Search vault for prior art |
|
|
86
86
|
| `vault_tags` / `vault_domains` | Browse knowledge landscape |
|
|
87
|
-
| `brain_strengths`
|
|
88
|
-
| `memory_cross_project_search`
|
|
89
|
-
| `capture_knowledge`
|
|
87
|
+
| `brain_strengths` | Check proven patterns |
|
|
88
|
+
| `memory_cross_project_search` | Check other projects |
|
|
89
|
+
| `capture_knowledge` | Persist design decision |
|
|
@@ -32,13 +32,13 @@ YOUR_AGENT_core op:brain_strengths
|
|
|
32
32
|
|
|
33
33
|
### 3. Review the Code
|
|
34
34
|
|
|
35
|
-
| Check
|
|
36
|
-
|
|
37
|
-
| Violates critical rule
|
|
38
|
-
| Matches known anti-pattern
|
|
39
|
-
| Doesn't follow proven pattern | `brain_strengths`
|
|
40
|
-
| Breaks project conventions
|
|
41
|
-
| Misses pattern opportunity
|
|
35
|
+
| Check | Source | Severity |
|
|
36
|
+
| ----------------------------- | ----------------------------- | ------------- |
|
|
37
|
+
| Violates critical rule | `search (severity: critical)` | Must fix |
|
|
38
|
+
| Matches known anti-pattern | `search (type: anti-pattern)` | Must fix |
|
|
39
|
+
| Doesn't follow proven pattern | `brain_strengths` | Should fix |
|
|
40
|
+
| Breaks project conventions | `project_list_rules` | Should fix |
|
|
41
|
+
| Misses pattern opportunity | `search_intelligent` | Could improve |
|
|
42
42
|
|
|
43
43
|
### 4. Present the Review
|
|
44
44
|
|
|
@@ -76,11 +76,11 @@ Re-run patrol after user applies fixes. Check `admin_health`.
|
|
|
76
76
|
|
|
77
77
|
## Quick Reference
|
|
78
78
|
|
|
79
|
-
| Op
|
|
80
|
-
|
|
81
|
-
| `route_intent`
|
|
82
|
-
| `search_intelligent`
|
|
83
|
-
| `search`
|
|
84
|
-
| `project_list_rules` / `get_behavior_rules` | Project conventions
|
|
85
|
-
| `brain_strengths`
|
|
86
|
-
| `capture_quick` / `capture_knowledge`
|
|
79
|
+
| Op | When to Use |
|
|
80
|
+
| ------------------------------------------- | ------------------------------------- |
|
|
81
|
+
| `route_intent` | Classify code domain |
|
|
82
|
+
| `search_intelligent` | Find relevant patterns |
|
|
83
|
+
| `search` | Find anti-patterns and critical rules |
|
|
84
|
+
| `project_list_rules` / `get_behavior_rules` | Project conventions |
|
|
85
|
+
| `brain_strengths` | Proven patterns |
|
|
86
|
+
| `capture_quick` / `capture_knowledge` | Capture new discoveries |
|
|
@@ -85,11 +85,11 @@ YOUR_AGENT_core op:admin_health
|
|
|
85
85
|
|
|
86
86
|
## Quick Reference
|
|
87
87
|
|
|
88
|
-
| Op
|
|
89
|
-
|
|
90
|
-
| `plan_stats` / `get_plan` / `plan_list_tasks` | Active plans
|
|
91
|
-
| `memory_search` / `memory_list`
|
|
92
|
-
| `vault_recent`
|
|
93
|
-
| `loop_is_active` / `loop_status`
|
|
94
|
-
| `brain_strengths`
|
|
95
|
-
| `admin_health`
|
|
88
|
+
| Op | When to Use |
|
|
89
|
+
| --------------------------------------------- | --------------------------- |
|
|
90
|
+
| `plan_stats` / `get_plan` / `plan_list_tasks` | Active plans |
|
|
91
|
+
| `memory_search` / `memory_list` | Session summaries |
|
|
92
|
+
| `vault_recent` | Recently captured knowledge |
|
|
93
|
+
| `loop_is_active` / `loop_status` | In-flight loops |
|
|
94
|
+
| `brain_strengths` | Relevant proven patterns |
|
|
95
|
+
| `admin_health` | System health check |
|