loki-mode 6.0.0 → 6.2.0
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 +20 -0
- package/SKILL.md +2 -2
- package/VERSION +1 -1
- package/autonomy/bmad-adapter.py +776 -0
- package/autonomy/loki +393 -0
- package/autonomy/prd-analyzer.py +26 -4
- package/autonomy/run.sh +149 -4
- package/autonomy/sandbox.sh +181 -1
- package/dashboard/__init__.py +1 -1
- package/docs/INSTALLATION.md +1 -1
- package/docs/architecture/bmad-integration-epic.md +271 -0
- package/docs/architecture/bmad-integration-review.md +86 -0
- package/docs/architecture/bmad-integration-validation.md +249 -0
- package/docs/architecture/bmad-loki-voice-agent-council-analysis.md +61 -0
- package/mcp/__init__.py +1 -1
- package/mcp/requirements.txt +1 -0
- package/mcp/server.py +152 -0
- package/package.json +1 -1
- package/templates/clusters/README.md +21 -0
- package/templates/clusters/code-review.json +36 -0
- package/templates/clusters/performance-audit.json +29 -0
- package/templates/clusters/refactoring.json +29 -0
- package/templates/clusters/security-review.json +36 -0
package/README.md
CHANGED
|
@@ -73,6 +73,26 @@ The system classifies your PRD complexity, assembles an agent team, and runs RAR
|
|
|
73
73
|
|
|
74
74
|
---
|
|
75
75
|
|
|
76
|
+
## BMAD Method Integration
|
|
77
|
+
|
|
78
|
+
Loki Mode integrates with the [BMAD Method](https://github.com/bmad-code-org/BMAD-METHOD), a structured AI-driven agile methodology. If your project uses BMAD for requirements elicitation (product briefs, PRDs, architecture documents, epic/story breakdowns), Loki Mode can consume those artifacts directly:
|
|
79
|
+
|
|
80
|
+
```bash
|
|
81
|
+
# Start from BMAD project artifacts
|
|
82
|
+
loki start --bmad-project ./my-project
|
|
83
|
+
|
|
84
|
+
# BMAD artifacts are discovered automatically from _bmad-output/
|
|
85
|
+
# PRD is analyzed with BMAD-aware scoring dimensions
|
|
86
|
+
# Architecture decisions are injected as execution context
|
|
87
|
+
# Epics/stories are loaded into the task queue
|
|
88
|
+
```
|
|
89
|
+
|
|
90
|
+
The adapter handles BMAD's frontmatter conventions, FR-format functional requirements, Given/When/Then acceptance criteria, and artifact chain validation. Non-BMAD projects are completely unaffected -- the integration is additive and opt-in via the `--bmad-project` flag.
|
|
91
|
+
|
|
92
|
+
See [BMAD Integration Validation](docs/architecture/bmad-integration-validation.md) for the compatibility analysis.
|
|
93
|
+
|
|
94
|
+
---
|
|
95
|
+
|
|
76
96
|
## Presentation
|
|
77
97
|
|
|
78
98
|
|
package/SKILL.md
CHANGED
|
@@ -3,7 +3,7 @@ name: loki-mode
|
|
|
3
3
|
description: Multi-agent autonomous startup system. Triggers on "Loki Mode". Takes PRD to deployed product with minimal human intervention. Requires --dangerously-skip-permissions flag.
|
|
4
4
|
---
|
|
5
5
|
|
|
6
|
-
# Loki Mode v6.
|
|
6
|
+
# Loki Mode v6.2.0
|
|
7
7
|
|
|
8
8
|
**You are an autonomous agent. You make decisions. You do not ask questions. You do not stop.**
|
|
9
9
|
|
|
@@ -263,4 +263,4 @@ The following features are documented in skill modules but not yet fully automat
|
|
|
263
263
|
| Quality gates 3-reviewer system | Implemented (v5.35.0) | 5 specialist reviewers in `skills/quality-gates.md`; execution in run.sh |
|
|
264
264
|
| Benchmarks (HumanEval, SWE-bench) | Infrastructure only | Runner scripts and datasets exist in `benchmarks/`; no published results |
|
|
265
265
|
|
|
266
|
-
**v6.
|
|
266
|
+
**v6.2.0 | [Autonomi](https://www.autonomi.dev/) flagship product | ~260 lines core**
|
package/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
6.
|
|
1
|
+
6.2.0
|