oh-my-claude-sisyphus 3.3.5 → 3.3.7

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 (52) hide show
  1. package/README.md +70 -18
  2. package/agents/architect-medium.md +39 -0
  3. package/agents/architect.md +70 -0
  4. package/agents/code-reviewer.md +40 -0
  5. package/agents/critic.md +34 -0
  6. package/agents/executor-high.md +23 -0
  7. package/agents/executor.md +18 -2
  8. package/agents/planner.md +24 -7
  9. package/agents/scientist-high.md +3 -3
  10. package/agents/tdd-guide.md +26 -0
  11. package/commands/cancel-ralph.md +3 -3
  12. package/commands/cancel-ultraqa.md +5 -5
  13. package/commands/cancel-ultrawork.md +4 -4
  14. package/commands/hud.md +8 -8
  15. package/commands/learner.md +2 -2
  16. package/commands/mcp-setup.md +194 -0
  17. package/commands/note.md +11 -11
  18. package/commands/omc-setup.md +18 -2
  19. package/commands/ralph-init.md +1 -1
  20. package/commands/ralplan.md +59 -6
  21. package/commands/release.md +2 -2
  22. package/commands/research.md +7 -7
  23. package/commands/ultraqa.md +6 -6
  24. package/dist/__tests__/installer.test.js +1 -1
  25. package/dist/__tests__/skills.test.js +6 -5
  26. package/dist/__tests__/skills.test.js.map +1 -1
  27. package/dist/installer/index.d.ts +1 -1
  28. package/dist/installer/index.js +1 -1
  29. package/docs/CLAUDE.md +53 -27
  30. package/docs/FULL-README.md +26 -24
  31. package/docs/MIGRATION-v3.md +6 -6
  32. package/docs/MIGRATION.md +43 -43
  33. package/package.json +1 -1
  34. package/skills/analyze/SKILL.md +17 -0
  35. package/skills/autopilot/SKILL.md +8 -8
  36. package/skills/cancel-autopilot/SKILL.md +3 -3
  37. package/skills/cancel-ralph/SKILL.md +3 -3
  38. package/skills/cancel-ultraqa/SKILL.md +5 -5
  39. package/skills/cancel-ultrawork/SKILL.md +4 -4
  40. package/skills/hud/SKILL.md +9 -9
  41. package/skills/learner/SKILL.md +3 -3
  42. package/skills/mcp-setup/SKILL.md +196 -0
  43. package/skills/note/SKILL.md +11 -11
  44. package/skills/omc-setup/SKILL.md +18 -2
  45. package/skills/planner/SKILL.md +52 -0
  46. package/skills/ralph/SKILL.md +26 -0
  47. package/skills/ralph-init/SKILL.md +1 -1
  48. package/skills/ralplan/SKILL.md +59 -6
  49. package/skills/release/SKILL.md +2 -2
  50. package/skills/research/SKILL.md +17 -17
  51. package/skills/tdd/SKILL.md +80 -0
  52. package/skills/ultraqa/SKILL.md +6 -6
package/docs/CLAUDE.md CHANGED
@@ -160,35 +160,35 @@ User says "stop", "cancel", "abort" → You determine what to stop:
160
160
 
161
161
  | Skill | Purpose | Auto-Trigger | Manual |
162
162
  |-------|---------|--------------|--------|
163
- | `autopilot` | Full autonomous execution from idea to working code | "autopilot", "build me", "I want a" | `/autopilot` |
163
+ | `autopilot` | Full autonomous execution from idea to working code | "autopilot", "build me", "I want a" | `/oh-my-claudecode:autopilot` |
164
164
  | `orchestrate` | Core multi-agent orchestration | Always active | - |
165
- | `ralph` | Persistence until verified complete | "don't stop", "must complete" | `/ralph` |
166
- | `ultrawork` | Maximum parallel execution | "fast", "parallel", "ulw" | `/ultrawork` |
167
- | `planner` | Strategic planning with interview | "plan this", broad requests | `/planner` |
168
- | `plan` | Start planning session | "plan" keyword | `/plan` |
169
- | `ralplan` | Iterative planning (Planner+Architect+Critic) | "ralplan" keyword | `/ralplan` |
170
- | `review` | Review plan with Critic | "review plan" | `/review` |
171
- | `analyze` | Deep analysis/investigation | "analyze", "debug", "why" | `/analyze` |
172
- | `deepsearch` | Thorough codebase search | "search", "find", "where" | `/deepsearch` |
173
- | `deepinit` | Generate AGENTS.md hierarchy | "index codebase" | `/deepinit` |
165
+ | `ralph` | Persistence until verified complete | "don't stop", "must complete" | `/oh-my-claudecode:ralph` |
166
+ | `ultrawork` | Maximum parallel execution | "fast", "parallel", "ulw" | `/oh-my-claudecode:ultrawork` |
167
+ | `planner` | Strategic planning with interview | "plan this", broad requests | `/oh-my-claudecode:planner` |
168
+ | `plan` | Start planning session | "plan" keyword | `/oh-my-claudecode:plan` |
169
+ | `ralplan` | Iterative planning (Planner+Architect+Critic) | "ralplan" keyword | `/oh-my-claudecode:ralplan` |
170
+ | `review` | Review plan with Critic | "review plan" | `/oh-my-claudecode:review` |
171
+ | `analyze` | Deep analysis/investigation | "analyze", "debug", "why" | `/oh-my-claudecode:analyze` |
172
+ | `deepsearch` | Thorough codebase search | "search", "find", "where" | `/oh-my-claudecode:deepsearch` |
173
+ | `deepinit` | Generate AGENTS.md hierarchy | "index codebase" | `/oh-my-claudecode:deepinit` |
174
174
  | `frontend-ui-ux` | Design sensibility for UI | UI/component context | (silent) |
175
175
  | `git-master` | Git expertise, atomic commits | git/commit context | (silent) |
176
- | `ultraqa` | QA cycling: test/fix/repeat | "test", "QA", "verify" | `/ultraqa` |
177
- | `learner` | Extract reusable skill from session | "extract skill" | `/learner` |
178
- | `note` | Save to notepad for memory | "remember", "note" | `/note` |
179
- | `hud` | Configure HUD statusline | - | `/hud` |
180
- | `doctor` | Diagnose installation issues | - | `/doctor` |
176
+ | `ultraqa` | QA cycling: test/fix/repeat | "test", "QA", "verify" | `/oh-my-claudecode:ultraqa` |
177
+ | `learner` | Extract reusable skill from session | "extract skill" | `/oh-my-claudecode:learner` |
178
+ | `note` | Save to notepad for memory | "remember", "note" | `/oh-my-claudecode:note` |
179
+ | `hud` | Configure HUD statusline | - | `/oh-my-claudecode:hud` |
180
+ | `doctor` | Diagnose installation issues | - | `/oh-my-claudecode:doctor` |
181
181
  | `help` | Show OMC usage guide | - | `/oh-my-claudecode:help` |
182
182
  | `omc-setup` | One-time setup wizard | - | `/oh-my-claudecode:omc-setup` |
183
183
  | `omc-default` | Configure local project | - | (internal) |
184
184
  | `omc-default-global` | Configure global settings | - | (internal) |
185
- | `ralph-init` | Initialize PRD for structured ralph | - | `/ralph-init` |
186
- | `release` | Automated release workflow | - | `/release` |
187
- | `cancel-autopilot` | Cancel active autopilot session | "stop autopilot", "cancel autopilot" | `/cancel-autopilot` |
188
- | `cancel-ralph` | Cancel active ralph loop | "stop" in ralph | `/cancel-ralph` |
189
- | `cancel-ultrawork` | Cancel ultrawork mode | "stop" in ultrawork | `/cancel-ultrawork` |
190
- | `cancel-ultraqa` | Cancel ultraqa workflow | "stop" in ultraqa | `/cancel-ultraqa` |
191
- | `research` | Parallel scientist orchestration | "research", "analyze data" | `/research` |
185
+ | `ralph-init` | Initialize PRD for structured ralph | - | `/oh-my-claudecode:ralph-init` |
186
+ | `release` | Automated release workflow | - | `/oh-my-claudecode:release` |
187
+ | `cancel-autopilot` | Cancel active autopilot session | "stop autopilot", "cancel autopilot" | `/oh-my-claudecode:cancel-autopilot` |
188
+ | `cancel-ralph` | Cancel active ralph loop | "stop" in ralph | `/oh-my-claudecode:cancel-ralph` |
189
+ | `cancel-ultrawork` | Cancel ultrawork mode | "stop" in ultrawork | `/oh-my-claudecode:cancel-ultrawork` |
190
+ | `cancel-ultraqa` | Cancel ultraqa workflow | "stop" in ultraqa | `/oh-my-claudecode:cancel-ultraqa` |
191
+ | `research` | Parallel scientist orchestration | "research", "analyze data" | `/oh-my-claudecode:research` |
192
192
 
193
193
  ### All 28 Agents
194
194
 
@@ -330,6 +330,32 @@ When in planning/interview mode, use the `AskUserQuestion` tool for preference q
330
330
  5. If REJECTED → fix issues and re-verify
331
331
  ```
332
332
 
333
+ ### Verification-Before-Completion Protocol
334
+
335
+ **Iron Law:** NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
336
+
337
+ Before ANY agent says "done", "fixed", or "complete":
338
+
339
+ | Step | Action |
340
+ |------|--------|
341
+ | 1 | IDENTIFY: What command proves this claim? |
342
+ | 2 | RUN: Execute verification command |
343
+ | 3 | READ: Check output - did it pass? |
344
+ | 4 | CLAIM: Make claim WITH evidence |
345
+
346
+ **Red Flags (agent must STOP and verify):**
347
+ - Using "should", "probably", "seems to"
348
+ - Expressing satisfaction before verification
349
+ - Claiming completion without fresh test/build run
350
+
351
+ **Evidence Types:**
352
+ | Claim | Required Evidence |
353
+ |-------|-------------------|
354
+ | "Fixed" | Test showing it passes now |
355
+ | "Implemented" | lsp_diagnostics clean + build pass |
356
+ | "Refactored" | All tests still pass |
357
+ | "Debugged" | Root cause identified with file:line |
358
+
333
359
  ### Parallelization Rules
334
360
 
335
361
  - **2+ independent tasks** with >30 seconds work → Run in parallel
@@ -403,8 +429,8 @@ Say "setup omc" or run `/oh-my-claudecode:omc-setup` to configure. After that, e
403
429
 
404
430
  ### Troubleshooting
405
431
 
406
- - `/doctor` - Diagnose and fix installation issues
407
- - `/hud setup` - Install/repair HUD statusline
432
+ - `/oh-my-claudecode:doctor` - Diagnose and fix installation issues
433
+ - `/oh-my-claudecode:hud setup` - Install/repair HUD statusline
408
434
 
409
435
  ---
410
436
 
@@ -422,9 +448,9 @@ Autopilot activates automatically and handles the rest. No commands needed.
422
448
  ## Migration from 2.x
423
449
 
424
450
  All old commands still work:
425
- - `/ralph "task"` → Still works (or just say "don't stop until done")
426
- - `/ultrawork "task"` → Still works (or just say "fast" or use `ulw`)
427
- - `/planner "task"` → Still works (or just say "plan this")
451
+ - `/oh-my-claudecode:ralph "task"` → Still works (or just say "don't stop until done")
452
+ - `/oh-my-claudecode:ultrawork "task"` → Still works (or just say "fast" or use `ulw`)
453
+ - `/oh-my-claudecode:planner "task"` → Still works (or just say "plan this")
428
454
 
429
455
  The difference? You don't NEED them anymore. Everything auto-activates.
430
456
 
@@ -10,7 +10,7 @@
10
10
 
11
11
  # oh-my-claudecode
12
12
 
13
- [![Version](https://img.shields.io/badge/version-3.3.4-ff6b6b)](https://github.com/Yeachan-Heo/oh-my-claudecode)
13
+ [![Version](https://img.shields.io/badge/version-3.3.7-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/)
@@ -46,7 +46,7 @@
46
46
  <remember priority>API client at src/api/client.ts</remember>
47
47
 
48
48
  # Or save notes manually
49
- /note Database schema uses PostgreSQL with Prisma ORM
49
+ /oh-my-claudecode:note Database schema uses PostgreSQL with Prisma ORM
50
50
  ```
51
51
 
52
52
  ### 📋 Ralph Loop PRD Support
@@ -154,7 +154,7 @@ Choose **ONE** installation method below. Do not mix methods.
154
154
  claude plugin install oh-my-claude-sisyphus
155
155
 
156
156
  # Or from within Claude Code:
157
- /plugin oh-my-claude-sisyphus
157
+ /oh-my-claudecode:plugin oh-my-claude-sisyphus
158
158
  ```
159
159
 
160
160
  Uses Node.js hooks from the plugin directory. Integrates directly with Claude Code's plugin system.
@@ -197,7 +197,7 @@ chmod +x scripts/install.sh
197
197
  Configure omc for the current project only:
198
198
 
199
199
  ```
200
- /omc-default
200
+ /oh-my-claudecode:omc-default
201
201
  ```
202
202
 
203
203
  - Creates `./.claude/CLAUDE.md` in your current project
@@ -210,7 +210,7 @@ Configure omc for the current project only:
210
210
  Configure omc for all Claude Code sessions:
211
211
 
212
212
  ```
213
- /omc-default-global
213
+ /oh-my-claudecode:omc-default-global
214
214
  ```
215
215
 
216
216
  - Creates `~/.claude/CLAUDE.md` globally
@@ -293,18 +293,18 @@ The installer adds to your Claude Code config (`~/.claude/`):
293
293
  │ ├── planner.md # Strategic planner (Opus)
294
294
  │ └── qa-tester.md # CLI/service testing (Sonnet)
295
295
  ├── commands/
296
- │ ├── orchestrate.md # /orchestrate command
297
- │ ├── omc-default.md # /omc-default command (project-scoped)
298
- │ ├── omc-default-global.md # /omc-default-global command (global)
299
- │ ├── ultrawork.md # /ultrawork command
300
- │ ├── deepsearch.md # /deepsearch command
301
- │ ├── analyze.md # /analyze command
302
- │ ├── plan.md # /plan command (planner)
303
- │ ├── review.md # /review command (critic)
304
- │ ├── planner.md # /planner command
305
- │ ├── orchestrator.md # /orchestrator command
306
- │ ├── ralph-loop.md # /ralph-loop command
307
- │ └── cancel-ralph.md # /cancel-ralph command
296
+ │ ├── orchestrate.md # /oh-my-claudecode:orchestrate command
297
+ │ ├── omc-default.md # /oh-my-claudecode:omc-default command (project-scoped)
298
+ │ ├── omc-default-global.md # /oh-my-claudecode:omc-default-global command (global)
299
+ │ ├── ultrawork.md # /oh-my-claudecode:ultrawork command
300
+ │ ├── deepsearch.md # /oh-my-claudecode:deepsearch command
301
+ │ ├── analyze.md # /oh-my-claudecode:analyze command
302
+ │ ├── plan.md # /oh-my-claudecode:plan command (planner)
303
+ │ ├── review.md # /oh-my-claudecode:review command (critic)
304
+ │ ├── planner.md # /oh-my-claudecode:planner command
305
+ │ ├── orchestrator.md # /oh-my-claudecode:orchestrator command
306
+ │ ├── ralph-loop.md # /oh-my-claudecode:ralph-loop command
307
+ │ └── cancel-ralph.md # /oh-my-claudecode:cancel-ralph command
308
308
  ├── skills/
309
309
  │ ├── ultrawork/SKILL.md # Maximum performance mode
310
310
  │ ├── deepinit/SKILL.md # Hierarchical AGENTS.md generation
@@ -363,22 +363,22 @@ claude
363
363
  /oh-my-claudecode:ultrawork implement user dashboard with charts
364
364
 
365
365
  # Initialize structured task with PRD
366
- /ralph-init implement user authentication with OAuth
366
+ /oh-my-claudecode:ralph-init implement user authentication with OAuth
367
367
 
368
368
  # Maximum intensity with completion guarantee
369
- /ultrawork-ralph migrate database schema to PostgreSQL
369
+ /oh-my-claudecode:ultrawork-ralph migrate database schema to PostgreSQL
370
370
 
371
371
  # Autonomous QA cycling
372
- /ultraqa all tests must pass with 90%+ coverage
372
+ /oh-my-claudecode:ultraqa all tests must pass with 90%+ coverage
373
373
 
374
374
  # Save important discoveries
375
- /note Project uses Bun runtime instead of Node.js
375
+ /oh-my-claudecode:note Project uses Bun runtime instead of Node.js
376
376
 
377
377
  # Deep search
378
- /deepsearch API endpoints that handle user data
378
+ /oh-my-claudecode:deepsearch API endpoints that handle user data
379
379
 
380
380
  # Deep analysis
381
- /analyze performance bottleneck in the database layer
381
+ /oh-my-claudecode:analyze performance bottleneck in the database layer
382
382
  ```
383
383
 
384
384
  ### Magic Keywords
@@ -867,7 +867,9 @@ If you're coming from oh-my-opencode:
867
867
  ## Requirements
868
868
 
869
869
  - [Claude Code](https://docs.anthropic.com/claude-code) installed
870
- - Anthropic API key (`ANTHROPIC_API_KEY` environment variable)
870
+ - One of:
871
+ - **Claude Max/Pro subscription** (recommended for individuals)
872
+ - **Anthropic API key** (`ANTHROPIC_API_KEY` environment variable)
871
873
  - **Windows**: Node.js 20+ (for npm installation)
872
874
  - **macOS/Linux**: Bash shell (default) or Node.js 20+ (optional)
873
875
 
@@ -81,11 +81,11 @@ Slash commands have been updated to use new naming:
81
81
 
82
82
  | Old Command | New Command |
83
83
  |-------------|-------------|
84
- | /sisyphus | /orchestrate |
85
- | /sisyphus-default | /omc-default |
86
- | /sisyphus-default-global | /omc-default-global |
87
- | /prometheus | /planner |
88
- | /mnemosyne | /learner |
84
+ | /sisyphus | /oh-my-claudecode:orchestrate |
85
+ | /sisyphus-default | /oh-my-claudecode:omc-default |
86
+ | /sisyphus-default-global | /oh-my-claudecode:omc-default-global |
87
+ | /prometheus | /oh-my-claudecode:planner |
88
+ | /mnemosyne | /oh-my-claudecode:learner |
89
89
 
90
90
  ## Feature Flag Changes
91
91
 
@@ -183,4 +183,4 @@ After migration, verify your setup:
183
183
  If you encounter issues during migration:
184
184
  - Check the [GitHub Issues](https://github.com/Yeachan-Heo/oh-my-claude-sisyphus/issues)
185
185
  - Review the [Documentation](https://github.com/Yeachan-Heo/oh-my-claude-sisyphus/tree/main/docs)
186
- - Run `/doctor` to diagnose common issues
186
+ - Run `/oh-my-claudecode:doctor` to diagnose common issues
package/docs/MIGRATION.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  Your old commands still work! But now you don't need them.
6
6
 
7
- **Before 3.0:** Explicitly invoke 25+ commands like `/ralph "task"`, `/ultrawork "task"`
7
+ **Before 3.0:** Explicitly invoke 25+ commands like `/oh-my-claudecode:ralph "task"`, `/oh-my-claudecode:ultrawork "task"`
8
8
 
9
9
  **After 3.0:** Just work naturally - Claude auto-activates the right behaviors. One-time setup: just say "setup omc"
10
10
 
@@ -18,13 +18,13 @@ You had to remember and explicitly invoke specific commands for each mode:
18
18
 
19
19
  ```bash
20
20
  # 2.x workflow: Multiple commands, lots to remember
21
- /ralph "implement user authentication" # Persistence mode
22
- /ultrawork "refactor the API layer" # Maximum parallelism
23
- /planner "plan the new dashboard" # Planning interview
24
- /deepsearch "find database schema files" # Deep search
25
- /git-master "commit these changes" # Git expertise
26
- /deepinit ./src # Index codebase
27
- /analyze "why is this test failing?" # Deep analysis
21
+ /oh-my-claudecode:ralph "implement user authentication" # Persistence mode
22
+ /oh-my-claudecode:ultrawork "refactor the API layer" # Maximum parallelism
23
+ /oh-my-claudecode:planner "plan the new dashboard" # Planning interview
24
+ /oh-my-claudecode:deepsearch "find database schema files" # Deep search
25
+ /oh-my-claudecode:git-master "commit these changes" # Git expertise
26
+ /oh-my-claudecode:deepinit ./src # Index codebase
27
+ /oh-my-claudecode:analyze "why is this test failing?" # Deep analysis
28
28
  ```
29
29
 
30
30
  ### After (3.0): Auto-Activation + Keywords
@@ -49,20 +49,20 @@ All 2.x commands continue to work. Here's what changed:
49
49
 
50
50
  | 2.x Command | 3.0 Equivalent | Works? |
51
51
  |-------------|----------------|--------|
52
- | `/ralph "task"` | Say "don't stop until done" OR use `ralph` keyword | ✅ YES (both ways) |
53
- | `/ultrawork "task"` | Say "fast" or "parallel" OR use `ulw` keyword | ✅ YES (both ways) |
54
- | `/ultrawork-ralph` | Say "ralph ulw:" prefix | ✅ YES (keyword combo) |
55
- | `/planner "task"` | Say "plan this" OR use `plan` keyword | ✅ YES (both ways) |
56
- | `/plan "description"` | Start planning naturally | ✅ YES |
57
- | `/review [path]` | Invoke normally | ✅ YES (unchanged) |
58
- | `/deepsearch "query"` | Say "find" or "search" | ✅ YES (auto-detect) |
59
- | `/analyze "target"` | Say "analyze" or "investigate" | ✅ YES (auto-detect) |
60
- | `/deepinit [path]` | Invoke normally | ✅ YES (unchanged) |
61
- | `/git-master` | Say "git", "commit", "atomic commit" | ✅ YES (auto-detect) |
62
- | `/frontend-ui-ux` | Say "UI", "styling", "component", "design" | ✅ YES (auto-detect) |
63
- | `/note "content"` | Say "remember this" or "save this" | ✅ YES (auto-detect) |
64
- | `/cancel-ralph` | Say "stop", "cancel", or "abort" | ✅ YES (auto-detect) |
65
- | `/doctor` | Invoke normally | ✅ YES (unchanged) |
52
+ | `/oh-my-claudecode:ralph "task"` | Say "don't stop until done" OR use `ralph` keyword | ✅ YES (both ways) |
53
+ | `/oh-my-claudecode:ultrawork "task"` | Say "fast" or "parallel" OR use `ulw` keyword | ✅ YES (both ways) |
54
+ | `/oh-my-claudecode:ultrawork-ralph` | Say "ralph ulw:" prefix | ✅ YES (keyword combo) |
55
+ | `/oh-my-claudecode:planner "task"` | Say "plan this" OR use `plan` keyword | ✅ YES (both ways) |
56
+ | `/oh-my-claudecode:plan "description"` | Start planning naturally | ✅ YES |
57
+ | `/oh-my-claudecode:review [path]` | Invoke normally | ✅ YES (unchanged) |
58
+ | `/oh-my-claudecode:deepsearch "query"` | Say "find" or "search" | ✅ YES (auto-detect) |
59
+ | `/oh-my-claudecode:analyze "target"` | Say "analyze" or "investigate" | ✅ YES (auto-detect) |
60
+ | `/oh-my-claudecode:deepinit [path]` | Invoke normally | ✅ YES (unchanged) |
61
+ | `/oh-my-claudecode:git-master` | Say "git", "commit", "atomic commit" | ✅ YES (auto-detect) |
62
+ | `/oh-my-claudecode:frontend-ui-ux` | Say "UI", "styling", "component", "design" | ✅ YES (auto-detect) |
63
+ | `/oh-my-claudecode:note "content"` | Say "remember this" or "save this" | ✅ YES (auto-detect) |
64
+ | `/oh-my-claudecode:cancel-ralph` | Say "stop", "cancel", or "abort" | ✅ YES (auto-detect) |
65
+ | `/oh-my-claudecode:doctor` | Invoke normally | ✅ YES (unchanged) |
66
66
  | All other commands | Work exactly as before | ✅ YES |
67
67
 
68
68
  ---
@@ -113,7 +113,7 @@ If in planning → End planning interview
113
113
  If multiple active → Stop the most recent
114
114
  ```
115
115
 
116
- No more `/cancel-ralph` - just say "cancel"!
116
+ No more `/oh-my-claudecode:cancel-ralph` - just say "cancel"!
117
117
 
118
118
  ---
119
119
 
@@ -126,10 +126,10 @@ No more `/cancel-ralph` - just say "cancel"!
126
126
  You can still use explicit commands if you prefer:
127
127
 
128
128
  ```bash
129
- /ralph "implement OAuth" # Still works ✅
130
- /ultrawork "refactor everything" # Still works ✅
131
- /planner "plan the feature" # Still works ✅
132
- /cancel-ralph # Still works ✅
129
+ /oh-my-claudecode:ralph "implement OAuth" # Still works ✅
130
+ /oh-my-claudecode:ultrawork "refactor everything" # Still works ✅
131
+ /oh-my-claudecode:planner "plan the feature" # Still works ✅
132
+ /oh-my-claudecode:cancel-ralph # Still works ✅
133
133
  ```
134
134
 
135
135
  These are now **optional** - use them if you like, but you don't have to.
@@ -172,7 +172,7 @@ See [MIGRATION-v3.md](MIGRATION-v3.md) for detailed 2.x → 3.0 naming changes.
172
172
  **No commands to memorize.** Work naturally:
173
173
 
174
174
  ```
175
- Before: "OK, I need to use /ultrawork for speed..."
175
+ Before: "OK, I need to use /oh-my-claudecode:ultrawork for speed..."
176
176
  After: "I'm in a hurry, go fast!"
177
177
 
178
178
  Claude: "I'm activating ultrawork mode..."
@@ -194,7 +194,7 @@ Your request Claude's action
194
194
 
195
195
  You don't ask for delegation - it happens automatically.
196
196
 
197
- ### 3. Learned Skills (`/learner`)
197
+ ### 3. Learned Skills (`/oh-my-claudecode:learner`)
198
198
 
199
199
  Extract reusable insights from problem-solving:
200
200
 
@@ -219,7 +219,7 @@ See what Claude is doing in the status bar:
219
219
  [OMC] ralph:3/10 | US-002 | ultrawork skill:planner | ctx:67% | agents:2 | todos:2/5
220
220
  ```
221
221
 
222
- Run `/hud setup` to install. Presets: minimal, focused, full.
222
+ Run `/oh-my-claudecode:hud setup` to install. Presets: minimal, focused, full.
223
223
 
224
224
  ### 5. Three-Tier Memory System
225
225
 
@@ -233,10 +233,10 @@ Permanently loaded on session start
233
233
  Never lost through compaction
234
234
  ```
235
235
 
236
- Or use `/note` to save discoveries manually:
236
+ Or use `/oh-my-claudecode:note` to save discoveries manually:
237
237
 
238
238
  ```bash
239
- /note Project uses PostgreSQL with Prisma ORM
239
+ /oh-my-claudecode:note Project uses PostgreSQL with Prisma ORM
240
240
  ```
241
241
 
242
242
  ### 6. Structured Task Tracking (PRD Support)
@@ -244,7 +244,7 @@ Or use `/note` to save discoveries manually:
244
244
  **Ralph Loop now uses Product Requirements Documents:**
245
245
 
246
246
  ```bash
247
- /ralph-init "implement OAuth with multiple providers"
247
+ /oh-my-claudecode:ralph-init "implement OAuth with multiple providers"
248
248
 
249
249
  Auto-creates PRD with user stories
250
250
 
@@ -312,7 +312,7 @@ You're done - Claude handles the rest
312
312
  Apply oh-my-claudecode to current project only:
313
313
 
314
314
  ```
315
- /omc-default
315
+ /oh-my-claudecode:omc-default
316
316
  ```
317
317
 
318
318
  Creates: `./.claude/CLAUDE.md`
@@ -322,7 +322,7 @@ Creates: `./.claude/CLAUDE.md`
322
322
  Apply to all Claude Code sessions:
323
323
 
324
324
  ```
325
- /omc-default-global
325
+ /oh-my-claudecode:omc-default-global
326
326
  ```
327
327
 
328
328
  Creates: `~/.claude/CLAUDE.md`
@@ -337,7 +337,7 @@ Creates: `~/.claude/CLAUDE.md`
337
337
 
338
338
  **2.x Workflow:**
339
339
  ```
340
- /ultrawork "implement the todo list feature"
340
+ /oh-my-claudecode:ultrawork "implement the todo list feature"
341
341
  ```
342
342
 
343
343
  **3.0 Workflow:**
@@ -353,7 +353,7 @@ Claude: "I'm activating ultrawork for maximum parallelism"
353
353
 
354
354
  **2.x Workflow:**
355
355
  ```
356
- /ralph "debug the memory leak"
356
+ /oh-my-claudecode:ralph "debug the memory leak"
357
357
  ```
358
358
 
359
359
  **3.0 Workflow:**
@@ -369,7 +369,7 @@ Claude: "I'm activating ralph-loop to ensure completion"
369
369
 
370
370
  **2.x Workflow:**
371
371
  ```
372
- /planner "design the new authentication system"
372
+ /oh-my-claudecode:planner "design the new authentication system"
373
373
  ```
374
374
 
375
375
  **3.0 Workflow:**
@@ -387,7 +387,7 @@ Interview begins automatically
387
387
 
388
388
  **2.x Workflow:**
389
389
  ```
390
- /cancel-ralph
390
+ /oh-my-claudecode:cancel-ralph
391
391
  ```
392
392
 
393
393
  **3.0 Workflow:**
@@ -421,10 +421,10 @@ A: No. Keywords are optional shortcuts. Claude auto-detects intent without them.
421
421
  A: No. All 2.x commands continue to work exactly as before.
422
422
 
423
423
  **Q: What if I like explicit commands?**
424
- A: Keep using them! `/ralph`, `/ultrawork`, `/planner` all still work.
424
+ A: Keep using them! `/oh-my-claudecode:ralph`, `/oh-my-claudecode:ultrawork`, `/oh-my-claudecode:planner` all still work.
425
425
 
426
426
  **Q: How do I know what Claude is doing?**
427
- A: Claude announces major behaviors: "I'm activating ralph-loop..." or set up `/hud` for real-time status.
427
+ A: Claude announces major behaviors: "I'm activating ralph-loop..." or set up `/oh-my-claudecode:hud` for real-time status.
428
428
 
429
429
  **Q: Where's the old command list?**
430
430
  A: See [README.md](../README.md) for full command reference. All commands still work.
@@ -436,9 +436,9 @@ A: Keywords are explicit shortcuts. Natural language triggers auto-detection. Bo
436
436
 
437
437
  ## Need Help?
438
438
 
439
- - **Diagnose issues**: Run `/doctor`
439
+ - **Diagnose issues**: Run `/oh-my-claudecode:doctor`
440
440
  - **See all commands**: Run `/oh-my-claudecode:help`
441
- - **View real-time status**: Run `/hud setup`
441
+ - **View real-time status**: Run `/oh-my-claudecode:hud setup`
442
442
  - **Review detailed changelog**: See [CHANGELOG.md](../CHANGELOG.md)
443
443
  - **Report bugs**: [GitHub Issues](https://github.com/Yeachan-Heo/oh-my-claude-sisyphus/issues)
444
444
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "oh-my-claude-sisyphus",
3
- "version": "3.3.5",
3
+ "version": "3.3.7",
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",
@@ -25,6 +25,23 @@ Conduct thorough analysis of the specified target (code, architecture, issue, bu
25
25
  - Map dependencies and relationships
26
26
  - Check for edge cases
27
27
 
28
+ **For Debugging/Bug Analysis (4-Phase Protocol)**
29
+
30
+ When analyzing bugs or issues, follow systematic debugging:
31
+
32
+ - **Root Cause First** - Never skip to fixes
33
+ - Read ALL error messages
34
+ - Reproduce consistently
35
+ - Document hypothesis before looking at code
36
+
37
+ - **Pattern Analysis** - Find working vs broken
38
+ - Compare with working similar code
39
+ - Identify the specific delta
40
+
41
+ - **3-Failure Circuit Breaker** - If stuck:
42
+ - After 3 failed hypotheses, question the architecture
43
+ - The bug may be elsewhere entirely
44
+
28
45
  3. **Synthesize Findings**
29
46
  - Root cause (for bugs)
30
47
  - Design decisions and tradeoffs (for architecture)
@@ -22,9 +22,9 @@ Autopilot is the ultimate hands-off mode. Give it a brief product idea (2-3 line
22
22
  ## Usage
23
23
 
24
24
  ```
25
- /autopilot <your idea>
26
- /ap "A CLI tool that tracks daily habits"
27
- /autopilot Add dark mode to the app
25
+ /oh-my-claudecode:autopilot <your idea>
26
+ /oh-my-claudecode:ap "A CLI tool that tracks daily habits"
27
+ /oh-my-claudecode:autopilot Add dark mode to the app
28
28
  ```
29
29
 
30
30
  ## Magic Keywords
@@ -115,7 +115,7 @@ Optional settings in `.claude/settings.json`:
115
115
  ## Cancellation
116
116
 
117
117
  ```
118
- /cancel-autopilot
118
+ /oh-my-claudecode:cancel-autopilot
119
119
  ```
120
120
 
121
121
  Or say: "stop", "cancel", "abort"
@@ -124,23 +124,23 @@ Progress is preserved for resume.
124
124
 
125
125
  ## Resume
126
126
 
127
- If autopilot was cancelled or failed, just run `/autopilot` again to resume from where it stopped.
127
+ If autopilot was cancelled or failed, just run `/oh-my-claudecode:autopilot` again to resume from where it stopped.
128
128
 
129
129
  ## Examples
130
130
 
131
131
  **New Project:**
132
132
  ```
133
- /autopilot A REST API for a bookstore inventory with CRUD operations
133
+ /oh-my-claudecode:autopilot A REST API for a bookstore inventory with CRUD operations
134
134
  ```
135
135
 
136
136
  **Feature Addition:**
137
137
  ```
138
- /autopilot Add user authentication with JWT tokens
138
+ /oh-my-claudecode:autopilot Add user authentication with JWT tokens
139
139
  ```
140
140
 
141
141
  **Enhancement:**
142
142
  ```
143
- /ap Add dark mode support with system preference detection
143
+ /oh-my-claudecode:ap Add dark mode support with system preference detection
144
144
  ```
145
145
 
146
146
  ## Best Practices
@@ -17,7 +17,7 @@ Cancel an active autopilot session gracefully.
17
17
  ## Usage
18
18
 
19
19
  ```
20
- /cancel-autopilot
20
+ /oh-my-claudecode:cancel-autopilot
21
21
  ```
22
22
 
23
23
  Or say: "stop autopilot", "cancel autopilot", "abort autopilot"
@@ -37,14 +37,14 @@ When cancelled, autopilot preserves:
37
37
  - Spec and plan files
38
38
  - Validation verdicts
39
39
 
40
- Run `/autopilot` to resume from where you left off.
40
+ Run `/oh-my-claudecode:autopilot` to resume from where you left off.
41
41
 
42
42
  ## Force Clear
43
43
 
44
44
  To completely clear all state (no resume):
45
45
 
46
46
  ```
47
- /cancel-autopilot --clear
47
+ /oh-my-claudecode:cancel-autopilot --clear
48
48
  ```
49
49
 
50
50
  This removes all autopilot files including:
@@ -35,9 +35,9 @@ After running this command, you are free to stop working. The persistent mode ho
35
35
 
36
36
  ## Note on Linked Modes
37
37
 
38
- Since v3.0, Ralph automatically activates Ultrawork for parallel execution. When you cancel Ralph, the linked Ultrawork is also cancelled. If you started Ultrawork separately (not via Ralph), use `/cancel-ultrawork` to cancel it independently.
38
+ Since v3.0, Ralph automatically activates Ultrawork for parallel execution. When you cancel Ralph, the linked Ultrawork is also cancelled. If you started Ultrawork separately (not via Ralph), use `/oh-my-claudecode:cancel-ultrawork` to cancel it independently.
39
39
 
40
40
  ## To Start Fresh
41
41
 
42
- - `/ralph "task"` - Start ralph with ultrawork (default)
43
- - `/ultrawork "task"` - Start ultrawork only (standalone)
42
+ - `/oh-my-claudecode:ralph "task"` - Start ralph with ultrawork (default)
43
+ - `/oh-my-claudecode:ultrawork "task"` - Start ultrawork only (standalone)
@@ -22,8 +22,8 @@ After running this command, the QA cycling will stop.
22
22
 
23
23
  ## To Start Fresh
24
24
 
25
- - `/ultraqa --tests` - Run until all tests pass
26
- - `/ultraqa --build` - Run until build succeeds
27
- - `/ultraqa --lint` - Run until no lint errors
28
- - `/ultraqa --typecheck` - Run until no type errors
29
- - `/ultraqa --custom "pattern"` - Run until pattern matches
25
+ - `/oh-my-claudecode:ultraqa --tests` - Run until all tests pass
26
+ - `/oh-my-claudecode:ultraqa --build` - Run until build succeeds
27
+ - `/oh-my-claudecode:ultraqa --lint` - Run until no lint errors
28
+ - `/oh-my-claudecode:ultraqa --typecheck` - Run until no type errors
29
+ - `/oh-my-claudecode:ultraqa --custom "pattern"` - Run until pattern matches
@@ -18,7 +18,7 @@ The Ultrawork mode has been cancelled. Clearing state files.
18
18
  cat .omc/ultrawork-state.json 2>/dev/null | jq -r '.linked_to_ralph // false'
19
19
  ```
20
20
 
21
- **If linked_to_ralph is true**: Use `/cancel-ralph` instead to cancel both Ralph and its linked Ultrawork.
21
+ **If linked_to_ralph is true**: Use `/oh-my-claudecode:cancel-ralph` instead to cancel both Ralph and its linked Ultrawork.
22
22
 
23
23
  **Otherwise**, execute this command to cancel Ultrawork:
24
24
 
@@ -33,10 +33,10 @@ After running this command, ultrawork mode will be deactivated and the HUD will
33
33
  ## Note on Linked Modes
34
34
 
35
35
  Since v3.0, Ralph automatically activates Ultrawork. If you see `linked_to_ralph: true` in the ultrawork state, it means Ultrawork was auto-activated by Ralph. In this case:
36
- - Use `/cancel-ralph` to cancel both modes
36
+ - Use `/oh-my-claudecode:cancel-ralph` to cancel both modes
37
37
  - If you only cancel ultrawork, Ralph will continue but without parallel execution benefits
38
38
 
39
39
  ## To Start Fresh
40
40
 
41
- - `/ultrawork "task"` - Start ultrawork only (standalone)
42
- - `/ralph "task"` - Start ralph with ultrawork (default)
41
+ - `/oh-my-claudecode:ultrawork "task"` - Start ultrawork only (standalone)
42
+ - `/oh-my-claudecode:ralph "task"` - Start ralph with ultrawork (default)