olympus-ai 2.7.4 → 3.2.0
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/.claude/.olympus-version.json +6 -0
- package/.claude/CLAUDE.md +84 -61
- package/.claude/agents/document-writer.md +152 -0
- package/.claude/agents/explore-medium.md +25 -0
- package/.claude/agents/explore.md +86 -0
- package/.claude/agents/frontend-engineer-high.md +17 -0
- package/.claude/agents/frontend-engineer-low.md +17 -0
- package/.claude/agents/frontend-engineer.md +80 -0
- package/.claude/agents/librarian-low.md +22 -0
- package/.claude/agents/librarian.md +70 -0
- package/.claude/agents/metis.md +85 -0
- package/.claude/agents/momus.md +97 -0
- package/.claude/agents/multimodal-looker.md +39 -0
- package/.claude/agents/olympian-high.md +32 -0
- package/.claude/agents/olympian-low.md +22 -0
- package/.claude/agents/olympian.md +78 -0
- package/.claude/agents/oracle-low.md +23 -0
- package/.claude/agents/oracle-medium.md +28 -0
- package/.claude/agents/oracle.md +77 -0
- package/.claude/agents/prometheus.md +125 -0
- package/.claude/agents/qa-tester.md +220 -0
- package/.claude/commands/analyze/skill.md +14 -0
- package/.claude/commands/ascent/skill.md +152 -0
- package/.claude/commands/cancel-ascent.md +9 -0
- package/.claude/commands/complete-plan.md +101 -0
- package/.claude/commands/deepsearch/skill.md +15 -0
- package/.claude/commands/olympus/skill.md +82 -0
- package/.claude/commands/olympus-default.md +26 -0
- package/.claude/commands/plan.md +71 -0
- package/.claude/commands/prometheus/skill.md +38 -0
- package/.claude/commands/review/skill.md +34 -0
- package/.claude/commands/ultrawork/skill.md +90 -0
- package/.claude/commands/update.md +38 -0
- package/.claude-plugin/plugin.json +1 -1
- package/COPYRIGHT +22 -0
- package/LICENSE +1 -1
- package/NOTICE +24 -0
- package/README.md +376 -10
- package/dist/__tests__/installer.test.js +1 -1
- package/dist/__tests__/learning/cleanup.test.d.ts +2 -0
- package/dist/__tests__/learning/cleanup.test.d.ts.map +1 -0
- package/dist/__tests__/learning/cleanup.test.js +122 -0
- package/dist/__tests__/learning/cleanup.test.js.map +1 -0
- package/dist/__tests__/learning/storage.test.d.ts +2 -0
- package/dist/__tests__/learning/storage.test.d.ts.map +1 -0
- package/dist/__tests__/learning/storage.test.js +75 -0
- package/dist/__tests__/learning/storage.test.js.map +1 -0
- package/dist/agents/definitions.d.ts.map +1 -1
- package/dist/agents/definitions.js +22 -6
- package/dist/agents/definitions.js.map +1 -1
- package/dist/agents/olympian.d.ts.map +1 -1
- package/dist/agents/olympian.js +23 -7
- package/dist/agents/olympian.js.map +1 -1
- package/dist/agents/orchestrator-olympus.js +1 -1
- package/dist/cli/index.js +128 -9
- package/dist/cli/index.js.map +1 -1
- package/dist/hooks/context-window-limit-recovery/index.d.ts +2 -3
- package/dist/hooks/context-window-limit-recovery/index.d.ts.map +1 -1
- package/dist/hooks/context-window-limit-recovery/index.js +2 -3
- package/dist/hooks/context-window-limit-recovery/index.js.map +1 -1
- package/dist/hooks/olympus-orchestrator/constants.d.ts +3 -3
- package/dist/hooks/olympus-orchestrator/constants.d.ts.map +1 -1
- package/dist/hooks/olympus-orchestrator/constants.js +3 -3
- package/dist/hooks/preemptive-compaction/index.d.ts +2 -3
- package/dist/hooks/preemptive-compaction/index.d.ts.map +1 -1
- package/dist/hooks/preemptive-compaction/index.js +2 -3
- package/dist/hooks/preemptive-compaction/index.js.map +1 -1
- package/dist/installer/index.d.ts +2 -2
- package/dist/installer/index.d.ts.map +1 -1
- package/dist/installer/index.js +114 -30
- package/dist/installer/index.js.map +1 -1
- package/dist/learning/cleanup.d.ts +18 -0
- package/dist/learning/cleanup.d.ts.map +1 -0
- package/dist/learning/cleanup.js +160 -0
- package/dist/learning/cleanup.js.map +1 -0
- package/dist/learning/discovery.d.ts.map +1 -1
- package/dist/learning/discovery.js +3 -1
- package/dist/learning/discovery.js.map +1 -1
- package/dist/learning/pattern-extractor.d.ts +1 -1
- package/dist/learning/pattern-extractor.d.ts.map +1 -1
- package/dist/learning/pattern-extractor.js +4 -2
- package/dist/learning/pattern-extractor.js.map +1 -1
- package/dist/learning/stats.d.ts +28 -0
- package/dist/learning/stats.d.ts.map +1 -0
- package/dist/learning/stats.js +112 -0
- package/dist/learning/stats.js.map +1 -0
- package/dist/learning/storage.d.ts +4 -0
- package/dist/learning/storage.d.ts.map +1 -1
- package/dist/learning/storage.js +26 -1
- package/dist/learning/storage.js.map +1 -1
- package/package.json +9 -4
- package/{dist → scripts/dist}/hooks/olympus-hooks.cjs +70 -69
- package/scripts/esbuild.hooks.mjs +67 -0
- package/scripts/generate-logo-hybrid-v2.mjs +213 -0
- package/scripts/generate-logo-hybrid.mjs +209 -0
- package/scripts/generate-logo-infinity.mjs +239 -0
- package/scripts/generate-logo-mythology.mjs +190 -0
- package/scripts/generate-logo-orchestration.mjs +228 -0
- package/scripts/generate-logo-recraft.mjs +147 -0
- package/scripts/generate-logo-simple.mjs +154 -0
- package/scripts/generate-logo.mjs +117 -0
- package/scripts/install.sh +4 -7
- package/scripts/rebrand.mjs +206 -0
- package/.claude-plugin/nul +0 -3
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Start strategic planning with Prometheus
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
[DELEGATION REQUIRED]
|
|
6
|
+
|
|
7
|
+
You must delegate this planning session to the Prometheus agent.
|
|
8
|
+
|
|
9
|
+
**IMMEDIATELY** use the Task tool to spawn the prometheus agent:
|
|
10
|
+
|
|
11
|
+
```
|
|
12
|
+
Task(
|
|
13
|
+
subagent_type="prometheus",
|
|
14
|
+
description="Strategic planning session",
|
|
15
|
+
prompt="""
|
|
16
|
+
$ARGUMENTS
|
|
17
|
+
|
|
18
|
+
Please conduct a strategic planning session. Interview me about the requirements, consult with Metis for hidden risks, and create a comprehensive work plan.
|
|
19
|
+
|
|
20
|
+
When I'm ready, I'll say one of these to trigger plan generation:
|
|
21
|
+
- "Make it into a work plan!"
|
|
22
|
+
- "Create the plan"
|
|
23
|
+
- "I'm ready to plan"
|
|
24
|
+
- "Generate the plan"
|
|
25
|
+
|
|
26
|
+
Save the final plan to `.olympus/plans/`.
|
|
27
|
+
|
|
28
|
+
A good plan should have:
|
|
29
|
+
- Clear requirements summary
|
|
30
|
+
- Concrete acceptance criteria
|
|
31
|
+
- Specific implementation steps with file references
|
|
32
|
+
- Risk identification and mitigations
|
|
33
|
+
- Verification steps
|
|
34
|
+
"""
|
|
35
|
+
)
|
|
36
|
+
```
|
|
37
|
+
|
|
38
|
+
**DO NOT** attempt to handle planning yourself - you must spawn the Prometheus agent.
|
|
@@ -0,0 +1,34 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Review a plan with Momus
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
[DELEGATION REQUIRED]
|
|
6
|
+
|
|
7
|
+
You must delegate this plan review to the Momus agent.
|
|
8
|
+
|
|
9
|
+
**IMMEDIATELY** use the Task tool to spawn the momus agent:
|
|
10
|
+
|
|
11
|
+
```
|
|
12
|
+
Task(
|
|
13
|
+
subagent_type="momus",
|
|
14
|
+
description="Critical plan review",
|
|
15
|
+
prompt="""
|
|
16
|
+
$ARGUMENTS
|
|
17
|
+
|
|
18
|
+
Please critically review the specified plan (or the most recent plan in `.olympus/plans/` if no path provided).
|
|
19
|
+
|
|
20
|
+
Evaluation Criteria:
|
|
21
|
+
- **Clarity**: 80%+ of claims must cite specific file/line references
|
|
22
|
+
- **Testability**: 90%+ of acceptance criteria must be concrete and testable
|
|
23
|
+
- **Verification**: All file references must be verified to exist
|
|
24
|
+
- **Specificity**: No vague terms like "improve", "optimize" without metrics
|
|
25
|
+
|
|
26
|
+
Provide one of these verdicts:
|
|
27
|
+
- **APPROVED** - Plan meets all criteria, ready for execution
|
|
28
|
+
- **REVISE** - Plan has issues (provide specific feedback)
|
|
29
|
+
- **REJECT** - Fundamental problems requiring replanning
|
|
30
|
+
"""
|
|
31
|
+
)
|
|
32
|
+
```
|
|
33
|
+
|
|
34
|
+
**DO NOT** attempt to review the plan yourself - you must spawn the Momus agent.
|
|
@@ -0,0 +1,90 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Maximum intensity mode - parallel everything, delegate aggressively, never wait
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
[ULTRAWORK MODE ACTIVATED - MAXIMUM INTENSITY]
|
|
6
|
+
|
|
7
|
+
$ARGUMENTS
|
|
8
|
+
|
|
9
|
+
## THE ULTRAWORK OATH
|
|
10
|
+
|
|
11
|
+
You are now operating at **MAXIMUM INTENSITY**. Half-measures are unacceptable. Incomplete work is FAILURE. You will persist until EVERY task is VERIFIED complete.
|
|
12
|
+
|
|
13
|
+
This mode OVERRIDES default heuristics. Where default mode says "parallelize when profitable," ultrawork says "PARALLEL EVERYTHING."
|
|
14
|
+
|
|
15
|
+
## ULTRAWORK OVERRIDES
|
|
16
|
+
|
|
17
|
+
| Default Behavior | Ultrawork Override |
|
|
18
|
+
|------------------|-------------------|
|
|
19
|
+
| Parallelize when profitable | **PARALLEL EVERYTHING** |
|
|
20
|
+
| Do simple tasks directly | **DELEGATE EVEN SMALL TASKS** |
|
|
21
|
+
| Wait for verification | **DON'T WAIT - continue immediately** |
|
|
22
|
+
| Background for long ops | **BACKGROUND EVERYTHING POSSIBLE** |
|
|
23
|
+
|
|
24
|
+
## EXECUTION PROTOCOL
|
|
25
|
+
|
|
26
|
+
### 1. PARALLEL EVERYTHING
|
|
27
|
+
- Fire off MULTIPLE agents simultaneously - don't analyze, just launch
|
|
28
|
+
- Don't wait when you can parallelize
|
|
29
|
+
- Use background execution for ALL operations that support it
|
|
30
|
+
- Maximum throughput is the only goal
|
|
31
|
+
- Launch 3-5 agents in parallel when possible
|
|
32
|
+
|
|
33
|
+
### 2. DELEGATE AGGRESSIVELY
|
|
34
|
+
Route tasks to specialists IMMEDIATELY - don't do it yourself:
|
|
35
|
+
- `oracle` → ANY debugging or analysis
|
|
36
|
+
- `librarian` → ANY research or doc lookup
|
|
37
|
+
- `explore` → ANY search operation
|
|
38
|
+
- `frontend-engineer` → ANY UI work
|
|
39
|
+
- `document-writer` → ANY documentation
|
|
40
|
+
- `olympian` → ANY code changes
|
|
41
|
+
- `qa-tester` → ANY verification
|
|
42
|
+
|
|
43
|
+
### 3. NEVER WAIT
|
|
44
|
+
- Start the next task BEFORE the previous one completes
|
|
45
|
+
- Check background task results LATER
|
|
46
|
+
- Don't block on verification - launch it and continue
|
|
47
|
+
- Maximum concurrency at all times
|
|
48
|
+
|
|
49
|
+
### 4. PERSISTENCE ENFORCEMENT
|
|
50
|
+
- Create TODO list IMMEDIATELY
|
|
51
|
+
- Mark tasks in_progress BEFORE starting
|
|
52
|
+
- Mark completed ONLY after VERIFICATION
|
|
53
|
+
- LOOP until 100% complete
|
|
54
|
+
- Re-check todo list before ANY conclusion attempt
|
|
55
|
+
|
|
56
|
+
## THE ULTRAWORK PROMISE
|
|
57
|
+
|
|
58
|
+
Before stopping, VERIFY:
|
|
59
|
+
- [ ] Todo list: ZERO pending/in_progress tasks
|
|
60
|
+
- [ ] All functionality: TESTED and WORKING
|
|
61
|
+
- [ ] All errors: RESOLVED
|
|
62
|
+
- [ ] User's request: FULLY SATISFIED
|
|
63
|
+
|
|
64
|
+
**If ANY checkbox is unchecked, CONTINUE WORKING. No exceptions.**
|
|
65
|
+
|
|
66
|
+
## VERIFICATION PROTOCOL
|
|
67
|
+
|
|
68
|
+
### Step 1: Self-Check
|
|
69
|
+
Run through the checklist above.
|
|
70
|
+
|
|
71
|
+
### Step 2: Oracle Review (Launch in Background)
|
|
72
|
+
```
|
|
73
|
+
Task(subagent_type="oracle", run_in_background=true, prompt="VERIFY COMPLETION:
|
|
74
|
+
Original task: [task]
|
|
75
|
+
Changes made: [list]
|
|
76
|
+
Please verify this is complete and production-ready.")
|
|
77
|
+
```
|
|
78
|
+
|
|
79
|
+
### Step 3: Run Tests (In Parallel)
|
|
80
|
+
```bash
|
|
81
|
+
npm test # or pytest, go test, cargo test
|
|
82
|
+
```
|
|
83
|
+
|
|
84
|
+
### Step 4: Decision
|
|
85
|
+
- **Oracle APPROVED + Tests PASS** → Declare complete
|
|
86
|
+
- **Any REJECTED/FAILED** → Fix and re-verify
|
|
87
|
+
|
|
88
|
+
## THE ASCENT NEVER ENDS
|
|
89
|
+
|
|
90
|
+
The ascent continues until Olympus is reached. In ultrawork mode, the climb intensifies.
|
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Check for and install Olympus updates
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
[UPDATE CHECK]
|
|
6
|
+
|
|
7
|
+
$ARGUMENTS
|
|
8
|
+
|
|
9
|
+
## Checking for Updates
|
|
10
|
+
|
|
11
|
+
I will check for available updates to Olympus.
|
|
12
|
+
|
|
13
|
+
### What This Does
|
|
14
|
+
|
|
15
|
+
1. **Check Version**: Compare your installed version against the latest release on GitHub
|
|
16
|
+
2. **Show Release Notes**: Display what's new in the latest version
|
|
17
|
+
3. **Perform Update**: If an update is available and you confirm, download and install it
|
|
18
|
+
|
|
19
|
+
### Update Methods
|
|
20
|
+
|
|
21
|
+
**Automatic (Recommended):**
|
|
22
|
+
Run the install script to update:
|
|
23
|
+
```bash
|
|
24
|
+
curl -fsSL https://raw.githubusercontent.com/mikev10/olympus/main/scripts/install.sh | bash
|
|
25
|
+
```
|
|
26
|
+
|
|
27
|
+
**Manual:**
|
|
28
|
+
1. Check your current version in `~/.claude/.olympus-version.json`
|
|
29
|
+
2. Visit https://github.com/mikev10/olympus/releases
|
|
30
|
+
3. Download and run the install script from the latest release
|
|
31
|
+
|
|
32
|
+
### Version Info Location
|
|
33
|
+
|
|
34
|
+
Your version information is stored at: `~/.claude/.olympus-version.json`
|
|
35
|
+
|
|
36
|
+
---
|
|
37
|
+
|
|
38
|
+
Let me check for updates now. I'll read your version file and compare against the latest GitHub release.
|
package/COPYRIGHT
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
Olympus - Multi-Agent Orchestration for Claude Code
|
|
2
|
+
Copyright (c) 2026 Michael Vidal (mikev10)
|
|
3
|
+
All rights reserved.
|
|
4
|
+
|
|
5
|
+
This software is licensed under the MIT License.
|
|
6
|
+
See LICENSE file for full license text.
|
|
7
|
+
|
|
8
|
+
OWNERSHIP NOTICE:
|
|
9
|
+
This software was created by Michael Vidal as a personal project.
|
|
10
|
+
The copyright and all intellectual property rights remain with Michael Vidal.
|
|
11
|
+
|
|
12
|
+
Companies, organizations, and individuals may use this software under
|
|
13
|
+
the terms of the MIT License, but such use does not constitute a
|
|
14
|
+
transfer of ownership or copyright.
|
|
15
|
+
|
|
16
|
+
Original Repository: https://github.com/mikev10/olympus
|
|
17
|
+
Author: Michael Vidal
|
|
18
|
+
GitHub: @mikev10
|
|
19
|
+
Contact: via GitHub Issues
|
|
20
|
+
|
|
21
|
+
Creation Date: 2026
|
|
22
|
+
First Public Release: January 2026
|
package/LICENSE
CHANGED
package/NOTICE
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
Olympus
|
|
2
|
+
Copyright (c) 2026 Michael Vidal (mikev10)
|
|
3
|
+
|
|
4
|
+
This product includes software developed by Michael Vidal.
|
|
5
|
+
|
|
6
|
+
Licensed under the MIT License.
|
|
7
|
+
You may not use this file except in compliance with the License.
|
|
8
|
+
You may obtain a copy of the License at:
|
|
9
|
+
|
|
10
|
+
https://opensource.org/licenses/MIT
|
|
11
|
+
|
|
12
|
+
Unless required by applicable law or agreed to in writing, software
|
|
13
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
14
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
15
|
+
See the License for the specific language governing permissions and
|
|
16
|
+
limitations under the License.
|
|
17
|
+
|
|
18
|
+
TRADEMARK NOTICE:
|
|
19
|
+
"Olympus" as a software product name and the associated branding
|
|
20
|
+
are proprietary to Michael Vidal.
|
|
21
|
+
|
|
22
|
+
ATTRIBUTION:
|
|
23
|
+
If you use this software in your product, an acknowledgment in the
|
|
24
|
+
product documentation would be appreciated but is not required.
|