oh-my-claude-sisyphus 3.3.2 → 3.3.3

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 (5) hide show
  1. package/README.md +42 -18
  2. package/commands/research.md +99 -0
  3. package/docs/CLAUDE.md +7 -0
  4. package/docs/FULL-README.md +1 -1
  5. package/package.json +1 -1
package/README.md CHANGED
@@ -68,37 +68,60 @@ Want explicit control? Include these words anywhere in your message:
68
68
 
69
69
  ---
70
70
 
71
- ## Data Analysis with Scientist Agent (v3.3.0)
71
+ ## Data Analysis & Research (v3.3.3)
72
72
 
73
- The scientist agent provides persistent Python execution for data analysis:
73
+ ### Scientist Agent Tiers
74
74
 
75
- ```
76
- # Variables persist across calls - no need to reload data!
75
+ Three tiers of scientist agents for quantitative analysis and data science:
76
+
77
+ | Agent | Model | Use For |
78
+ |-------|-------|---------|
79
+ | `scientist-low` | Haiku | Quick data inspection, simple statistics, file enumeration |
80
+ | `scientist` | Sonnet | Standard analysis, pattern detection, visualization |
81
+ | `scientist-high` | Opus | Complex reasoning, hypothesis validation, ML workflows |
82
+
83
+ **Features:**
84
+ - **Persistent Python REPL** - Variables persist across calls (no pickle/reload overhead)
85
+ - **Structured markers** - `[FINDING]`, `[STAT:*]`, `[DATA]`, `[LIMITATION]` for parsed output
86
+ - **Quality gates** - Every finding requires statistical evidence (CI, effect size, p-value)
87
+ - **Auto-visualization** - Charts saved to `.omc/scientist/figures/`
88
+ - **Report generation** - Markdown reports with embedded figures
89
+
90
+ ```python
91
+ # Variables persist across calls!
77
92
  python_repl(action="execute", researchSessionID="analysis",
78
93
  code="import pandas as pd; df = pd.read_csv('data.csv')")
79
94
 
80
- # df still exists in the next call
95
+ # df still exists - no need to reload
81
96
  python_repl(action="execute", researchSessionID="analysis",
82
97
  code="print(df.describe())")
83
98
  ```
84
99
 
85
- **Features:**
86
- - Variable persistence via Unix socket bridge
87
- - Structured markers: `[FINDING]`, `[STAT:*]`, `[DATA]`, `[LIMITATION]`
88
- - Memory tracking (RSS/VMS)
89
- - Session locking for safe concurrent access
90
-
91
- ### /research Command
100
+ ### /research Command (NEW)
92
101
 
93
- Orchestrate parallel scientist agents for comprehensive research:
102
+ Orchestrate parallel scientist agents for comprehensive research workflows:
94
103
 
95
104
  ```
96
- /research <goal> # Standard research with checkpoints
97
- /research AUTO: <goal> # Fully autonomous until complete
98
- /research status # Check current session
105
+ /research <goal> # Standard research with checkpoints
106
+ /research AUTO: <goal> # Fully autonomous until complete
107
+ /research status # Check current session
108
+ /research resume # Resume interrupted session
109
+ /research list # List all sessions
110
+ /research report <session-id> # Generate report for session
99
111
  ```
100
112
 
101
- Features multi-stage decomposition, smart model routing, cross-validation, and structured report generation.
113
+ **Research Protocol:**
114
+ 1. **Decomposition** - Breaks goal into 3-7 independent stages
115
+ 2. **Parallel Execution** - Fires scientist agents concurrently (max 5)
116
+ 3. **Cross-Validation** - Verifies consistency across findings
117
+ 4. **Synthesis** - Generates comprehensive markdown report
118
+
119
+ **Smart Model Routing:**
120
+ - Data gathering tasks → `scientist-low` (Haiku)
121
+ - Standard analysis → `scientist` (Sonnet)
122
+ - Complex reasoning → `scientist-high` (Opus)
123
+
124
+ **Session Management:** Research state persists at `.omc/research/{session-id}/` enabling resume after interruption.
102
125
 
103
126
  ---
104
127
 
@@ -117,7 +140,8 @@ I'll intelligently determine what to stop based on context.
117
140
 
118
141
  - **28 Specialized Agents** - architect, researcher, explore, designer, writer, vision, critic, analyst, executor, planner, qa-tester, scientist (with tier variants)
119
142
  - **30 Skills** - orchestrate, ultrawork, ralph, planner, deepsearch, deepinit, git-master, frontend-ui-ux, learner, research, and more
120
- - **Persistent Python REPL** - True variable persistence for data analysis (new in 3.3.0)
143
+ - **Persistent Python REPL** - True variable persistence for data analysis
144
+ - **Research Workflow** - Parallel scientist orchestration with `/research` command (new in 3.3.3)
121
145
  - **HUD Statusline** - Real-time visualization of orchestration state
122
146
  - **Learned Skills** - Extract reusable insights from sessions with `/learner`
123
147
  - **Memory System** - Persistent context that survives compaction
package/commands/research.md ADDED
@@ -0,0 +1,99 @@
1
+ ---
2
+ description: Orchestrate parallel scientist agents for comprehensive research with AUTO mode
3
+ ---
4
+
5
+ # Research Skill
6
+
7
+ [RESEARCH MODE ACTIVATED]
8
+
9
+ Orchestrate parallel scientist agents for comprehensive research workflows with optional AUTO mode for fully autonomous execution.
10
+
11
+ ## Usage Examples
12
+
13
+ ```
14
+ /research <goal> # Standard research with user checkpoints
15
+ /research AUTO: <goal> # Fully autonomous until complete
16
+ /research status # Check current research session status
17
+ /research resume # Resume interrupted research session
18
+ /research list # List all research sessions
19
+ /research report <session-id> # Generate report for session
20
+ ```
21
+
22
+ ## Research Protocol
23
+
24
+ ### Stage Decomposition
25
+
26
+ When given a research goal, decompose into 3-7 independent stages:
27
+
28
+ 1. **Decomposition** - Break research goal into independent stages/hypotheses
29
+ 2. **Execution** - Run parallel scientist agents on each stage
30
+ 3. **Verification** - Cross-validate findings, check consistency
31
+ 4. **Synthesis** - Aggregate results into comprehensive report
32
+
33
+ ### Parallel Scientist Invocation
34
+
35
+ Fire independent stages in parallel via Task tool:
36
+
37
+ ```
38
+ // Stage 1 - Simple data gathering
39
+ Task(subagent_type="oh-my-claudecode:scientist-low", model="haiku", prompt="[RESEARCH_STAGE:1] Investigate...")
40
+
41
+ // Stage 2 - Standard analysis
42
+ Task(subagent_type="oh-my-claudecode:scientist", model="sonnet", prompt="[RESEARCH_STAGE:2] Analyze...")
43
+
44
+ // Stage 3 - Complex reasoning
45
+ Task(subagent_type="oh-my-claudecode:scientist-high", model="opus", prompt="[RESEARCH_STAGE:3] Deep analysis of...")
46
+ ```
47
+
48
+ ### Smart Model Routing
49
+
50
+ | Task Complexity | Agent | Model | Use For |
51
+ |-----------------|-------|-------|---------|
52
+ | Data gathering | `scientist-low` | haiku | File enumeration, pattern counting, simple lookups |
53
+ | Standard analysis | `scientist` | sonnet | Code analysis, pattern detection, documentation review |
54
+ | Complex reasoning | `scientist-high` | opus | Architecture analysis, cross-cutting concerns, hypothesis validation |
55
+
56
+ ### Concurrency Limit
57
+
58
+ **Maximum 5 concurrent scientist agents** to prevent resource exhaustion.
59
+
60
+ ## AUTO Mode
61
+
62
+ AUTO mode runs the complete research workflow autonomously with loop control.
63
+
64
+ ### Promise Tags
65
+
66
+ | Tag | Meaning | When to Use |
67
+ |-----|---------|-------------|
68
+ | `[PROMISE:RESEARCH_COMPLETE]` | Research finished successfully | All stages done, verified, report generated |
69
+ | `[PROMISE:RESEARCH_BLOCKED]` | Cannot proceed | Missing data, access issues, circular dependency |
70
+
71
+ ### AUTO Mode Rules
72
+
73
+ 1. **Max Iterations:** 10
74
+ 2. **Continue until:** Promise tag emitted OR max iterations
75
+ 3. **State tracking:** Persist after each stage completion
76
+ 4. **Cancellation:** `/cancel-research` or "stop", "cancel"
77
+
78
+ ## Session Management
79
+
80
+ Sessions are stored at `.omc/research/{session-id}/` with:
81
+ - `state.json` - Session state and progress
82
+ - `stages/` - Individual stage findings
83
+ - `findings/` - Raw and verified findings
84
+ - `report.md` - Final synthesized report
85
+
86
+ ## Cancellation
87
+
88
+ ```
89
+ /cancel-research
90
+ ```
91
+
92
+ Or say: "stop research", "cancel research", "abort"
93
+
94
+ Progress is preserved for resume.
95
+
96
+ ---
97
+
98
+ Research goal:
99
+ {{PROMPT}}
package/docs/CLAUDE.md CHANGED
@@ -34,6 +34,7 @@ RULE 4: NEVER complete without Architect verification
34
34
  | **Deep analysis** | NEVER | architect / analyst |
35
35
  | **Codebase exploration** | NEVER | explore / explore-medium |
36
36
  | **Research tasks** | NEVER | researcher |
37
+ | **Data analysis** | NEVER | scientist / scientist-high |
37
38
  | **Visual analysis** | NEVER | vision |
38
39
 
39
40
  ### Mandatory Skill Invocation
@@ -52,6 +53,7 @@ When you detect these patterns, you MUST invoke the corresponding skill:
52
53
  | Git/commit work | `git-master` (silent) |
53
54
  | "analyze", "debug", "investigate" | `analyze` |
54
55
  | "search", "find in codebase" | `deepsearch` |
56
+ | "research", "analyze data", "statistics" | `research` |
55
57
  | "stop", "cancel", "abort" | appropriate cancel skill |
56
58
 
57
59
  ### Smart Model Routing (SAVE TOKENS)
@@ -186,6 +188,7 @@ User says "stop", "cancel", "abort" → You determine what to stop:
186
188
  | `cancel-ralph` | Cancel active ralph loop | "stop" in ralph | `/cancel-ralph` |
187
189
  | `cancel-ultrawork` | Cancel ultrawork mode | "stop" in ultrawork | `/cancel-ultrawork` |
188
190
  | `cancel-ultraqa` | Cancel ultraqa workflow | "stop" in ultraqa | `/cancel-ultraqa` |
191
+ | `research` | Parallel scientist orchestration | "research", "analyze data" | `/research` |
189
192
 
190
193
  ### All 28 Agents
191
194
 
@@ -208,6 +211,7 @@ Always use `oh-my-claudecode:` prefix when calling via Task tool.
208
211
  | **Build** | `build-fixer-low` | `build-fixer` | - |
209
212
  | **TDD** | `tdd-guide-low` | `tdd-guide` | - |
210
213
  | **Code Review** | `code-reviewer-low` | - | `code-reviewer` |
214
+ | **Data Science** | `scientist-low` | `scientist` | `scientist-high` |
211
215
 
212
216
  ### Agent Selection Guide
213
217
 
@@ -237,6 +241,9 @@ Always use `oh-my-claudecode:` prefix when calling via Task tool.
237
241
  | Quick test suggestions | `tdd-guide-low` | haiku |
238
242
  | Code review | `code-reviewer` | opus |
239
243
  | Quick code check | `code-reviewer-low` | haiku |
244
+ | Data analysis/stats | `scientist` | sonnet |
245
+ | Quick data inspection | `scientist-low` | haiku |
246
+ | Complex ML/hypothesis | `scientist-high` | opus |
240
247
 
241
248
  ---
242
249
 
package/docs/FULL-README.md CHANGED
@@ -10,7 +10,7 @@
10
10
 
11
11
  # oh-my-claudecode
12
12
 
13
- [![Version](https://img.shields.io/badge/version-3.2.0-ff6b6b)](https://github.com/Yeachan-Heo/oh-my-claudecode)
13
+ [![Version](https://img.shields.io/badge/version-3.3.3-ff6b6b)](https://github.com/Yeachan-Heo/oh-my-claudecode)
14
14
  [![npm version](https://img.shields.io/npm/v/oh-my-claudecode?color=cb3837)](https://www.npmjs.com/package/oh-my-claudecode)
15
15
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
16
16
  [![Node.js](https://img.shields.io/badge/Node.js-20+-339933?logo=node.js&logoColor=white)](https://nodejs.org/)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "oh-my-claude-sisyphus",
3
- "version": "3.3.2",
3
+ "version": "3.3.3",
4
4
  "description": "Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",