@e0ipso/ai-task-manager 1.6.0 β 1.6.1
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/README.md +5 -67
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -3,84 +3,22 @@
|
|
|
3
3
|
[](https://www.npmjs.com/package/@e0ipso/ai-task-manager)
|
|
4
4
|
[](LICENSE)
|
|
5
5
|
|
|
6
|
-
|
|
6
|
+
AI-powered task management that creates structured workflows within your existing AI subscriptions. Supports Claude Code, Gemini CLI, and Open Code through custom slash commands.
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
π° Unlike projects such as **Plandex**, **Claude Task Master**, and **Conductor Tasks** that require API keys with pay-per-token pricing, **AI Task Manager** works within your existing AI subscription interface. Simply log in to your Claude or Gemini account and use the slash commands - **no API keys or additional costs required**.
|
|
9
9
|
|
|
10
|
-
|
|
10
|
+
## How It Works
|
|
11
11
|
|
|
12
|
-
This tool creates
|
|
12
|
+
This tool creates custom slash commands (like `/tasks:create-plan`, `/tasks:generate-tasks`) that integrate directly into:
|
|
13
13
|
- **Claude Code**: Works with your Claude Pro/Max subscription via [claude.ai/code](https://claude.ai/code)
|
|
14
|
-
- **Gemini CLI**: Uses your existing Gemini subscription
|
|
14
|
+
- **Gemini CLI**: Uses your existing Gemini subscription
|
|
15
15
|
- **Open Code**: Leverages your preferred open-source setup
|
|
16
16
|
|
|
17
|
-
### π° **Billing Model Comparison**
|
|
18
|
-
|
|
19
|
-
| Tool | Additional API Costs | Total for Subscription Users |
|
|
20
|
-
|------|---------------------|------------------------------|
|
|
21
|
-
| **AI Task Manager** | **$0** | **$0** (uses existing subscription) |
|
|
22
|
-
| **Plandex Cloud** | Included credits | *$45/month* |
|
|
23
|
-
| **Plandex (BYOK)** | Unpredictable (API usage) | *Unpredictable costs* |
|
|
24
|
-
| **Claude Task Master** | Unpredictable (API usage) | *Unpredictable costs* |
|
|
25
|
-
| **Conductor Tasks** | Unpredictable (API usage) | *Unpredictable costs* |
|
|
26
|
-
| **Shrimp Task Manager** | Unpredictable (API usage) | *Unpredictable costs* |
|
|
27
|
-
|
|
28
|
-
<details>
|
|
29
|
-
<summary>π More Details</summary>
|
|
30
|
-
|
|
31
|
-
| Tool | Stars | Type | Key Features | Documentation |
|
|
32
|
-
|------|-------|------|--------------|---------------|
|
|
33
|
-
| **AI Task Manager** | New | Task Management System | β
PlansβTasksβExecution workflow<br>β
Native slash commands<br>β
No API keys needed | This README |
|
|
34
|
-
| **[Plandex](https://github.com/plandex-ai/plandex)** | 14k+ | AI Coding Agent | β
Handles 2M token context<br>β
Multi-file editing<br>β οΈ Terminal-based (not in IDE) | [Docs](https://docs.plandex.ai/) |
|
|
35
|
-
| **[Claude Task Master](https://github.com/eyaltoledano/claude-task-master)** | 4.2k+ | Task Management | β
PRDβTasks workflow<br>β
MCP integration<br>β οΈ Requires API keys | [Tutorial](https://github.com/eyaltoledano/claude-task-master/blob/main/docs/tutorial.md) |
|
|
36
|
-
| **[Conductor Tasks](https://github.com/hridaya423/conductor-tasks)** | 38 | Visual Task Manager | β
Kanban boards<br>β
Dependency trees<br>β οΈ Requires API keys | [GitHub](https://github.com/hridaya423/conductor-tasks) |
|
|
37
|
-
| **[Shrimp Task Manager](https://github.com/cjo4m06/mcp-shrimp-task-manager)** | 70+ | Chain-of-Thought Tasks | β
Chain-of-thought focus<br>β
Persistent memory<br>β οΈ Requires API keys | [Docs](https://github.com/cjo4m06/mcp-shrimp-task-manager/tree/main/docs) |
|
|
38
|
-
|
|
39
|
-
</details>
|
|
40
|
-
|
|
41
|
-
### β‘ **Predictable Costs**
|
|
42
|
-
|
|
43
|
-
Because this works within your existing AI interface:
|
|
44
|
-
- **No surprise API bills** - you already know what your AI subscription costs
|
|
45
|
-
- **No rate limiting issues** - uses your subscription's limits
|
|
46
|
-
- **No API key management** - just type slash commands
|
|
47
|
-
- **Full model access** - get the latest models as soon as they're available in your subscription
|
|
48
|
-
|
|
49
|
-
AI-powered task management that creates structured workflows within your existing AI subscriptions. Supports Claude Code, Gemini CLI, and Open Code through custom slash commands.
|
|
50
|
-
|
|
51
|
-
### π― Key Differentiators
|
|
52
|
-
|
|
53
|
-
**1. Zero Additional Costs**: AI Task Manager is the **only tool** that works within your existing AI subscriptions (Claude Pro/Max, Gemini, etc.) without any API fees or additional subscriptions.
|
|
54
|
-
|
|
55
|
-
**2. Native Integration**: Unlike terminal-based tools (Plandex) or MCP servers requiring complex setup, AI Task Manager creates simple slash commands that work directly in your AI interface (claude.ai/code, Gemini CLI, etc.).
|
|
56
|
-
|
|
57
|
-
**3. Complete Workflow**: Full planning β task generation β execution workflow, matching enterprise tools like Claude Task Master but without the API key requirement.
|
|
58
|
-
|
|
59
|
-
**4. Predictable Costs**: No surprise API bills. You already know what your AI subscription costs - there's nothing extra to pay.
|
|
60
|
-
|
|
61
17
|
## β¨ Features
|
|
62
18
|
|
|
63
19
|
- π€ **Multi-Assistant Support**: Configure support for Claude, Gemini, and Open Code
|
|
64
20
|
- π **Template System**: Built-in templates for different project types (basic, development, research)
|
|
65
21
|
|
|
66
|
-
## π° Intelligent Token Usage
|
|
67
|
-
|
|
68
|
-
**One of the key benefits of this project is dramatically reducing AI costs by using the right model for the right task.**
|
|
69
|
-
|
|
70
|
-
The AI Task Manager leverages a **staged refinement approach** that maximizes the value of expensive, high-capability models while delegating execution to faster, cheaper models:
|
|
71
|
-
|
|
72
|
-
### π§ Use Premium Models for Complex Analysis
|
|
73
|
-
- **Planning Phase** (`/tasks:create-plan`): Deploy your most capable models (Claude Opus, GPT-5, etc.) for deep requirement analysis, architecture decisions, and strategic planning
|
|
74
|
-
- **Task Generation** (`/tasks:generate-tasks`): Leverage advanced reasoning for complex decomposition, dependency mapping, and scope optimization
|
|
75
|
-
|
|
76
|
-
### β‘ Use Fast Models for Execution
|
|
77
|
-
- **Blueprint Execution** (`/tasks:execute-blueprint`): Switch to faster, cost-effective models (Gemini 2.0 Flash, Claude Haiku) for task execution
|
|
78
|
-
- **Individual Tasks**: Sub-agents can also choose to use simpler models since most complexity is resolved during planning
|
|
79
|
-
|
|
80
|
-
### π‘ Why This Works
|
|
81
|
-
The heavy cognitive lifting happens during plan creation and task generation. By the time you reach execution, the blueprint documents are detailed and specific enough that simpler models can reliably implement them. This approach can **reduce your AI costs** and be **significantly faster** compared to using premium models for all phases.
|
|
82
|
-
|
|
83
|
-
_The more complex your project, the greater the savings._
|
|
84
22
|
|
|
85
23
|
## π Quick Start
|
|
86
24
|
|