@jenga-ai/agent 1.0.0 → 1.0.1

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.
Files changed (2) hide show
  1. package/README.md +25 -6
  2. package/package.json +6 -2
package/README.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # JengaAgent
2
2
 
3
- **A structured multi-agent development workflow built on [Claude Code](https://docs.anthropic.com/en/docs/claude-code).** Three specialised AI agents — Scrum Master, Developer, and Tester — collaborate through a shared scrum board, an event-driven trigger queue, and 28 slash-command skills to take a project from idea to verified, committed code — across as many sessions as it takes.
3
+ **A structured multi-agent development workflow that works with any AI agent or AI-native IDE.** Three specialised AI agents — Scrum Master, Developer, and Tester — collaborate through a shared scrum board, an event-driven trigger queue, and 28 slash-command skills to take a project from idea to verified, committed code — across as many sessions as it takes.
4
4
 
5
5
  > 📖 **Full reference:** [project/.wiki/documentation.md](project/.wiki/documentation.md) | [Intro Guide](project/.wiki/intro-guide.md)
6
6
 
@@ -12,7 +12,7 @@ Without a framework like JengaAgent, AI-assisted development has serious structu
12
12
 
13
13
  | Problem | Reality |
14
14
  |---|---|
15
- | **AI has no session memory** | Each Claude Code session starts from scratch — no awareness of open tasks, past decisions, or what was already tested |
15
+ | **AI has no session memory** | Every AI agent session starts from scratch — no awareness of open tasks, past decisions, or what was already tested |
16
16
  | **No role separation** | The AI writes *and* "tests" code in the same context, leading to hallucinated test results and self-affirming bugs |
17
17
  | **No structured planning** | Work happens ad-hoc — no Epic → Story → Task hierarchy to organise or track progress |
18
18
  | **No handoff protocol** | Switching from implementing to testing means manually re-explaining context every time |
@@ -30,11 +30,11 @@ JengaAgent solves each of these with structure: persistent board state, strict a
30
30
  **Without JengaAgent:**
31
31
  ```
32
32
  You: "Add user authentication"
33
- Claude: [writes auth code, declares it works, session ends]
33
+ AI agent: [writes auth code, declares it works, session ends]
34
34
 
35
35
  Next session:
36
36
  You: "What's the status of auth?"
37
- Claude: "I don't have context from the previous session."
37
+ AI agent: "I don't have context from the previous session."
38
38
  ```
39
39
 
40
40
  **With JengaAgent:**
@@ -136,7 +136,11 @@ Each agent is defined in `.agents/agents/`. They communicate exclusively through
136
136
 
137
137
  ## Getting Started
138
138
 
139
- **Prerequisites:** [Claude Code](https://docs.anthropic.com/en/docs/claude-code) installed and configured.
139
+ **Prerequisites:** An AI agent or AI-native IDE. Supported platforms include:
140
+ - [Claude Code](https://docs.anthropic.com/en/docs/claude-code)
141
+ - GitHub Copilot (VS Code extension or CLI)
142
+ - [Warp](https://www.warp.dev/)
143
+ - Codex CLI
140
144
 
141
145
  **Install from npm:**
142
146
  ```sh
@@ -155,9 +159,24 @@ Run `/status` at any time to see where the project stands.
155
159
 
156
160
  ---
157
161
 
162
+ ## Supported Platforms
163
+
164
+ JengaAgent has been tested with:
165
+
166
+ | Platform | Type |
167
+ |---|---|
168
+ | [Claude Code](https://docs.anthropic.com/en/docs/claude-code) | AI coding agent |
169
+ | [GitHub Copilot](https://github.com/features/copilot) | AI coding assistant |
170
+ | [Warp](https://www.warp.dev/) | AI-native terminal |
171
+ | Codex CLI | AI coding agent |
172
+
173
+ The framework is platform-agnostic by design — any AI agent that can read Markdown files and execute slash commands can use it.
174
+
175
+ ---
176
+
158
177
  ## Skills (Slash Commands)
159
178
 
160
- Skills live in `.agents/skills/<name>/SKILL.md`. Invoke with `/<name>` in any Claude Code session.
179
+ Skills live in `.agents/skills/<name>/SKILL.md`. Invoke with `/<name>` in your AI agent or IDE's command interface.
161
180
 
162
181
  ### Setup & Planning
163
182
 
package/package.json CHANGED
@@ -1,13 +1,17 @@
1
1
  {
2
2
  "name": "@jenga-ai/agent",
3
- "version": "1.0.0",
3
+ "version": "1.0.1",
4
4
  "description": "JengaAgent — agentic project management CLI",
5
5
  "type": "module",
6
+ "repository": {
7
+ "type": "git",
8
+ "url": "https://github.com/samwelmunga/jenga-npm.git"
9
+ },
6
10
  "publishConfig": {
7
11
  "access": "public"
8
12
  },
9
13
  "bin": {
10
- "jenga": "./bin/jenga.js"
14
+ "jenga": "bin/jenga.js"
11
15
  },
12
16
  "scripts": {
13
17
  "postinstall": "node scripts/postinstall.js",