create-byan-agent 2.47.0 → 2.47.1
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/CHANGELOG.md +16 -0
- package/install/templates/.claude/CLAUDE.md +2 -2
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -9,6 +9,22 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
|
|
9
9
|
|
|
10
10
|
## [Unreleased]
|
|
11
11
|
|
|
12
|
+
## [2.47.1] - 2026-07-16
|
|
13
|
+
|
|
14
|
+
### Fixed - Doctrine told users to invoke with `@byan`, which does not load the skill
|
|
15
|
+
|
|
16
|
+
- The docs said "tape `@byan` / `@hermes`" to invoke BYAN. In Claude Code, `@` is a
|
|
17
|
+
file mention, not a skill loader — so the byan-byan skill (which holds the agent
|
|
18
|
+
entry gate) was not loaded, and BYAN ran a task inline with no dispatch. Root
|
|
19
|
+
cause of the entry gate appearing "not to work" on a real machine.
|
|
20
|
+
- Corrected the entry guidance in `CLAUDE.md`: invoke BYAN with the **command**
|
|
21
|
+
`/byan-byan` (it loads the skill, the entry gate, and the rail) ; noted explicitly
|
|
22
|
+
that `@byan`/`@hermes` do not load the skill. Mirrored to install/templates.
|
|
23
|
+
- Note: the entry-gate code (2.47.0) is unchanged and correct ; it simply was not
|
|
24
|
+
reached because the skill was not loaded. Open question (does the loaded doctrine
|
|
25
|
+
reliably make BYAN propose an agent, or is a hard pre-write block needed) is to be
|
|
26
|
+
decided by testing `/byan-byan` with the rail actually loaded.
|
|
27
|
+
|
|
12
28
|
## [2.47.0] - 2026-07-16
|
|
13
29
|
|
|
14
30
|
### Added - Mandatory agent entry gate (match-or-create), the base of BYAN
|
|
@@ -11,7 +11,7 @@
|
|
|
11
11
|
Avant de chercher un agent specifique, demande a Hermes. Il connait tous les agents,
|
|
12
12
|
workflows et contextes, et te route vers le bon specialiste.
|
|
13
13
|
|
|
14
|
-
Pour
|
|
14
|
+
Pour lancer BYAN sur une tache, utilise la **commande** `/byan-byan` : c'est elle qui charge le skill (donc la porte d'entree et le rail de dispatch). Attention — `@byan` / `@hermes` NE chargent PAS le skill : cote Claude Code, `@` est une mention de fichier, pas un lanceur. Une fois dans `/byan-byan`, decris ta tache ou demande "quel agent pour [ta tache] ?".
|
|
15
15
|
|
|
16
16
|
Voir @.claude/rules/hermes-dispatcher.md pour les commandes Hermes.
|
|
17
17
|
|
|
@@ -68,7 +68,7 @@ Doctrine d'equipe complete (template role-in-team, analogie orchestre, principes
|
|
|
68
68
|
|
|
69
69
|
## Commandes Utiles
|
|
70
70
|
|
|
71
|
-
-
|
|
71
|
+
- `/byan-byan` → Entree BYAN + dispatcher universel (recommandations, routage, pipelines). Le `@` ne charge pas le skill.
|
|
72
72
|
- Agent disponibles: voir @.claude/rules/byan-agents.md
|
|
73
73
|
- Doctrine d'equipe: voir @.claude/rules/team-doctrine.md
|
|
74
74
|
- Methodologie: voir @.claude/rules/merise-agile.md
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "create-byan-agent",
|
|
3
|
-
"version": "2.47.
|
|
3
|
+
"version": "2.47.1",
|
|
4
4
|
"description": "BYAN v2.8 - Intelligent AI agent creator with ELO trust system + scientific fact-check + Hermes universal dispatcher + native Claude Code integration (hooks, skills, MCP server). Multi-platform (Claude Code, Codex). Merise Agile + TDD + 71 Mantras. ~54% LLM cost savings.",
|
|
5
5
|
"main": "src/index.js",
|
|
6
6
|
"bin": {
|