toga-ai 1.0.29 → 1.0.31

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 CHANGED
@@ -2,6 +2,46 @@
2
2
 
3
3
  Shared Claude Code skills, configuration, and the team **knowledge base** for TOGA Technology projects.
4
4
 
5
+ ## Onboarding — install on a new machine
6
+
7
+ Do this once per developer. The harness has two independent parts: the **ECC plugin**
8
+ (provides the `ecc:*` reviewer agents the TOGA agents delegate to) and the **TOGA harness**
9
+ (`npx toga-ai`, which installs the skills, agents, rules, and knowledge base). Install order
10
+ between the two does not matter.
11
+
12
+ **Prerequisites** (must already be installed):
13
+ - **Node.js ≥ 18** — required by `npx` and the installer.
14
+ - **Git** — required for `/capture` to push and for knowledge auto-updates.
15
+ - **Claude Code** — the `claude` CLI.
16
+
17
+ **Steps:**
18
+
19
+ 1. Open a terminal in VS Code and launch Claude Code:
20
+ ```
21
+ claude
22
+ ```
23
+ 2. Add the ECC marketplace and install the plugin, then reload:
24
+ ```
25
+ /plugin marketplace add https://github.com/affaan-m/ECC
26
+ /plugin install ecc@ecc
27
+ /reload-plugins
28
+ ```
29
+ 3. Open a **new terminal**, and **from inside the project repo you'll work in**, run:
30
+ ```
31
+ npx toga-ai
32
+ ```
33
+ This installs the harness into that project's `.claude/` and clones the shared knowledge
34
+ repo to `~/toga-tech`. **Run it once in each project folder** you work in.
35
+ 4. Start a new Claude Code session. Begin every session with `/kickoff`, and run `/capture`
36
+ whenever you have something to add to the team knowledge base.
37
+
38
+ > **Push access is required to contribute.** `/capture` pushes to `_main` on
39
+ > `agilantsolutions/claude`. Each developer must be a **collaborator on that repo with git
40
+ > credentials configured** (HTTPS token / credential manager or SSH). Without it, `/capture`
41
+ > still writes docs locally but the push fails silently — so the developer won't be
42
+ > contributing knowledge back. `npx toga-ai` then delivers everyone's captured knowledge to
43
+ > the whole team on each run.
44
+
5
45
  ## Skills
6
46
 
7
47
  | Skill | Description |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "toga-ai",
3
- "version": "1.0.29",
3
+ "version": "1.0.31",
4
4
  "description": "TOGA Technology Team Claude Knowledge System — shared AI coding harness with skills, knowledge base CLI, and project installer for Claude Code.",
5
5
  "keywords": [
6
6
  "claude",
@@ -6,6 +6,13 @@ Never commit directly to `_main`. All changes go through feature branches and pu
6
6
 
7
7
  Never force-push to `_main` under any circumstances.
8
8
 
9
+ > **Exception — the team knowledge/harness repo (`agilantsolutions/claude`, cloned to
10
+ > `~/toga-tech`).** This rule governs the TOGA *application* repos (worker2, api2, library,
11
+ > worker, _underscore). The knowledge repo's entire model is direct pushes to `_main` via the
12
+ > `/capture` skill — that is intended and is not a violation. Direct commits to `_main` are
13
+ > still **forbidden in all application repos**, and force-pushing `_main` is **never** allowed
14
+ > in any repo, including the knowledge repo.
15
+
9
16
  ## Branch naming
10
17
 
11
18
  Use one of these prefixes followed by a short hyphenated description: