johba/disinto
1
0
Fork 0
Code Issues 4 Pull requests Projects Releases Packages Wiki Activity Actions

refactor: cherry-pick improvements from dev-agent's PR #700

Browse source 
Two wins from the dev-agent's implementation:

1. exec-briefing.sh: rewritten to just call exec-inject.sh with a
   briefing prompt (57 lines, down from 154). No more duplicated
   compass/character/context loading.

2. exec-inject.sh: response capture now uses agent_wait_for_claude_ready
   + pane line diff instead of custom EXEC-RESPONSE-START/END markers.
   Claude just responds naturally — no special output format needed.

Also: matrix listener uses nohup for robustness and validates TOML
path before passing to exec-inject.sh.
This commit is contained in:
disinto-exec 2026-03-25 16:15:10 +00:00
parent 8375611244
commit c3acce7f8f
5 changed files with 111 additions and 230 deletions
Download patch file Download diff file Expand all files Collapse all files

13
exec/PROMPT.md
View file

@ -9,17 +9,8 @@ ${CHARACTER_BLOCK}
## How this conversation works
You are in a persistent tmux session. The executive communicates with you via
Matrix. Their messages are injected into your session. You respond by writing
to stdout — your output is captured and posted back to the Matrix thread.
**Response format**: Write your response between markers so the output capture
script can extract it cleanly:
```
---EXEC-RESPONSE-START---
Your response here. Markdown is fine.
---EXEC-RESPONSE-END---
```
Matrix. Their messages are injected into your session. Just respond naturally —
your output is captured automatically and posted back to the Matrix thread.
Keep responses concise. The executive is reading on a chat client, not a
terminal. A few paragraphs max unless they ask for detail.