agent-bober 0.4.1 → 0.4.3

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/.claude-plugin/plugin.json +1 -1
  2. package/LICENSE +1 -1
  3. package/README.md +49 -21
  4. package/package.json +2 -2
  5. package/skills/bober.run/SKILL.md +15 -8
package/.claude-plugin/plugin.json CHANGED
@@ -2,7 +2,7 @@
2
2
  "name": "bober",
3
3
  "description": "Generator-Evaluator multi-agent harness for building applications autonomously with Claude",
4
4
  "version": "0.1.0",
5
- "author": { "name": "bober4ik" },
5
+ "author": { "name": "BOBER3r" },
6
6
  "homepage": "https://github.com/BOBER3r/agent-bober",
7
7
  "repository": "https://github.com/BOBER3r/agent-bober",
8
8
  "license": "MIT"
package/LICENSE CHANGED
@@ -1,6 +1,6 @@
1
1
  MIT License
2
2
 
3
- Copyright (c) 2026 bober4ik
3
+ Copyright (c) 2026 BOBER3r
4
4
 
5
5
  Permission is hereby granted, free of charge, to any person obtaining a copy
6
6
  of this software and associated documentation files (the "Software"), to deal
package/README.md CHANGED
@@ -65,18 +65,19 @@ npx agent-bober init brownfield
65
65
 
66
66
  Then in Claude Code:
67
67
  ```
68
- /bober:plan # Describe your feature, get a structured plan
69
- /bober:sprint # Execute the next sprint
70
- /bober:eval # Evaluate the sprint output
71
- /bober:run # Full autonomous pipeline
68
+ /bober-principles # Define project standards (optional but recommended)
69
+ /bober-plan # Describe your feature, get a structured plan
70
+ /bober-sprint # Execute the next sprint
71
+ /bober-eval # Evaluate the sprint output
72
+ /bober-run # Full autonomous pipeline
72
73
  ```
73
74
 
74
75
  Specialized workflows:
75
76
  ```
76
- /bober:react # React web app workflow
77
- /bober:solidity # EVM smart contract workflow
78
- /bober:anchor # Solana program workflow
79
- /bober:brownfield # Existing codebase workflow
77
+ /bober-react # React web app workflow
78
+ /bober-solidity # EVM smart contract workflow
79
+ /bober-anchor # Solana program workflow
80
+ /bober-brownfield # Existing codebase workflow
80
81
  ```
81
82
 
82
83
  ---
@@ -87,26 +88,53 @@ Specialized workflows:
87
88
 
88
89
  | Command | Description |
89
90
  |---|---|
90
- | `/bober:plan` | Plan any feature -- stack-agnostic |
91
- | `/bober:sprint` | Execute the next sprint contract |
92
- | `/bober:eval` | Evaluate current sprint output |
93
- | `/bober:run` | Full autonomous pipeline |
94
- | `/bober:react` | React web application workflow |
95
- | `/bober:solidity` | EVM smart contract workflow |
96
- | `/bober:anchor` | Solana program workflow |
97
- | `/bober:brownfield` | Existing codebase workflow |
91
+ | `/bober-principles` | Define project principles — AI expands your rough notes into standards |
92
+ | `/bober-plan` | Plan any feature — stack-agnostic, sprint-decomposed |
93
+ | `/bober-sprint` | Execute the next sprint contract |
94
+ | `/bober-eval` | Evaluate current sprint output |
95
+ | `/bober-run` | Full autonomous pipeline (plan + sprint + eval loop) |
96
+ | `/bober-react` | React web application workflow |
97
+ | `/bober-solidity` | EVM smart contract workflow |
98
+ | `/bober-anchor` | Solana program workflow |
99
+ | `/bober-brownfield` | Existing codebase workflow |
98
100
 
99
101
  ### CLI
100
102
 
101
103
  ```bash
102
- npx agent-bober init [preset] # Initialize project (nextjs, react-vite, solidity, anchor, api-node, python-api, brownfield)
103
- npx agent-bober plan # Run the planner
104
+ npx agent-bober init [preset] # Initialize project
105
+ npx agent-bober plan "feature" # Run the planner
104
106
  npx agent-bober sprint # Execute next sprint
105
107
  npx agent-bober eval # Evaluate current sprint
106
- npx agent-bober run # Full autonomous loop
107
- npx agent-bober status # Show plan progress
108
+ npx agent-bober run "feature" # Full autonomous loop
108
109
  ```
109
110
 
111
+ ### Fully Autonomous Mode (no human in the loop)
112
+
113
+ **Option A: Claude Code (recommended)**
114
+
115
+ Launch Claude Code with auto-accept permissions, then run the pipeline:
116
+
117
+ ```bash
118
+ cd your-project
119
+ agent-bober init nextjs
120
+ claude --dangerously-skip-permissions
121
+ # Inside Claude Code:
122
+ /bober-run Build a complete dashboard with auth, CRUD, and charts
123
+ ```
124
+
125
+ Claude will plan, build, evaluate, rework, and iterate without asking you anything. Come back to a finished project.
126
+
127
+ **Option B: CLI with API key**
128
+
129
+ ```bash
130
+ export ANTHROPIC_API_KEY=sk-ant-...
131
+ cd your-project
132
+ agent-bober init nextjs
133
+ agent-bober run "Build a complete dashboard with auth, CRUD, and charts"
134
+ ```
135
+
136
+ The CLI uses the Anthropic SDK directly — no approval prompts at all.
137
+
110
138
  ---
111
139
 
112
140
  ## Configuration
@@ -492,4 +520,4 @@ This project is inspired by and implements the patterns from Anthropic's [**"Har
492
520
 
493
521
  ## License
494
522
 
495
- [MIT](LICENSE) -- Copyright (c) 2026 bober4ik
523
+ [MIT](LICENSE) -- Copyright (c) 2026 BOBER3r
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agent-bober",
3
- "version": "0.4.1",
3
+ "version": "0.4.3",
4
4
  "description": "Generator-Evaluator multi-agent harness for building applications autonomously with Claude. Implements planner, sprint, and evaluator patterns.",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
@@ -26,7 +26,7 @@
26
26
  "claude-code",
27
27
  "plugin"
28
28
  ],
29
- "author": "bober4ik",
29
+ "author": "BOBER3r",
30
30
  "license": "MIT",
31
31
  "repository": {
32
32
  "type": "git",
package/skills/bober.run/SKILL.md CHANGED
@@ -8,6 +8,18 @@ argument-hint: <task-description>
8
8
 
9
9
  You are running the **bober.run** skill. This is the top-level orchestrator that runs the entire Generator-Evaluator pipeline from start to finish: planning, sprint execution, evaluation, and iteration. The user provides a task description and you deliver a working implementation.
10
10
 
11
+ ## Autonomous Mode
12
+
13
+ This command is designed to run **fully autonomously** — do NOT stop to ask the user for confirmation between phases unless something is genuinely ambiguous or blocked. Specifically:
14
+
15
+ - **Do NOT ask** "should I continue to the next sprint?" — just continue.
16
+ - **Do NOT ask** "should I start building?" after planning — just start.
17
+ - **Do NOT ask** "should I rework?" after a failed evaluation — just rework (up to maxIterations).
18
+ - **Do NOT ask** for approval on file writes, commits, or evaluation runs — just do them.
19
+ - **DO stop** only if: you hit maxIterations on a sprint and cannot progress, or the task description is genuinely unclear and you cannot infer intent.
20
+
21
+ The user launched this command to walk away and come back to a finished product. Respect that intent.
22
+
11
23
  ## Overview
12
24
 
13
25
  The pipeline follows this flow:
@@ -53,14 +65,9 @@ If `bober.config.json` exists, read the configuration.
53
65
 
54
66
  Read `.bober/specs/` and `.bober/progress.md`. If there is an existing plan with incomplete sprints:
55
67
 
56
- Ask the user:
57
- ```
58
- I found an existing plan: "<plan title>" with <N> sprints (<M> completed, <K> remaining).
59
-
60
- A) Continue with the existing plan (resume from sprint <next>)
61
- B) Create a new plan for your task (the existing plan stays but won't be executed)
62
- C) Archive the existing plan and start fresh
63
- ```
68
+ - If the user provided a new task description that clearly differs from the existing plan → create a new plan (option B)
69
+ - If the user provided no task or a task that matches the existing plan → resume from the next incomplete sprint (option A)
70
+ - Log your decision but do NOT ask the user — autonomous mode means you decide and move forward
64
71
 
65
72
  ### 1c. Run the Planning Phase
66
73