mozempk/redsen-lean-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: scaffold redsen-lean-harness v0.1.0

Browse Source 
Recovered from crashed session (Node OOM). Repo contains full P0-P6
scaffold: plugin.json/marketplace.json, AGENTS.md, ADRs 0001-0006,
lh CLI (init/index/graph/lane/run/memory/host/report/doctor), 10
.github/agents, 12 CLI skills, instructions, context7 mcp.json, and
unit/e2e test suite.

Fixed: run.mjs read --in-tokens/--out-tokens but tests and CLI docs
use --input-tokens/--output-tokens, so telemetry totals were always 0.
Now accepts both forms.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
mozempk
2026-09-09 22:44:15 +02:00
co-authored by Copilot
commit 383129f571
79 changed files with 7855 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/prompts/build.prompt.md
+12
View File
@@ -0,0 +1,12 @@
---
description: Run the lean harness build phase through the Conductor agent and Ralph lane loop.
---
# Build Prompt
Invoke the `build` skill or `Conductor` agent.
Run `lh host` first. Obey its strategy.
Use parallel lanes only when host supports them.
In VS Code, degrade to sequential lane execution.
Keep Ralph loop and journal intact.