diff --git a/skills/coding-agent/SKILL.md b/skills/coding-agent/SKILL.md index d9216ebabb..cae7af0eee 100644 --- a/skills/coding-agent/SKILL.md +++ b/skills/coding-agent/SKILL.md @@ -76,7 +76,7 @@ bash pty:true workdir:~/project background:true command:"codex exec --full-auto # Monitor progress process action:log sessionId:XXX -# Check if done +# Check if done process action:poll sessionId:XXX # Send input (if agent asks a question) @@ -217,17 +217,17 @@ git worktree remove /tmp/issue-99 ## ⚠️ Rules -1. **Always use pty:true** — coding agents need a terminal! -2. **Respect tool choice** — if user asks for Codex, use Codex. +1. **Always use pty:true** - coding agents need a terminal! +2. **Respect tool choice** - if user asks for Codex, use Codex. - Orchestrator mode: do NOT hand-code patches yourself. - - If an agent fails/hangs, respawn it or ask the user for direction, but don’t silently take over. -3. **Be patient** — don't kill sessions because they're "slow" -4. **Monitor with process:log** — check progress without interfering -5. **--full-auto for building** — auto-approves changes -6. **vanilla for reviewing** — no special flags needed -7. **Parallel is OK** — run many Codex processes at once for batch work -8. **NEVER start Codex in ~/clawd/** — it'll read your soul docs and get weird ideas about the org chart! -9. **NEVER checkout branches in ~/Projects/clawdbot/** — that's the LIVE Clawdbot instance! + - If an agent fails/hangs, respawn it or ask the user for direction, but don't silently take over. +3. **Be patient** - don't kill sessions because they're "slow" +4. **Monitor with process:log** - check progress without interfering +5. **--full-auto for building** - auto-approves changes +6. **vanilla for reviewing** - no special flags needed +7. **Parallel is OK** - run many Codex processes at once for batch work +8. **NEVER start Codex in ~/clawd/** - it'll read your soul docs and get weird ideas about the org chart! +9. **NEVER checkout branches in ~/Projects/clawdbot/** - that's the LIVE Clawdbot instance! --- @@ -235,7 +235,7 @@ git worktree remove /tmp/issue-99 When you spawn coding agents in the background, keep the user in the loop. -- Send 1 short message when you start (what’s running + where). +- Send 1 short message when you start (what's running + where). - Then only update again when something changes: - a milestone completes (build finished, tests passed) - the agent asks a question / needs input @@ -247,6 +247,28 @@ This prevents the user from seeing only "Agent failed before reply" and having n --- +## Auto-Notify on Completion + +For long-running background tasks, append a wake trigger to your prompt so Clawdbot gets notified immediately when the agent finishes (instead of waiting for the next heartbeat): + +``` +... your task here. + +When completely finished, run this command to notify me: +clawdbot gateway wake --text "Done: [brief summary of what was built]" --mode now +``` + +**Example:** +```bash +bash pty:true workdir:~/project background:true command:"codex --yolo exec 'Build a REST API for todos. + +When completely finished, run: clawdbot gateway wake --text \"Done: Built todos REST API with CRUD endpoints\" --mode now'" +``` + +This triggers an immediate wake event — Skippy gets pinged in seconds, not 10 minutes. + +--- + ## Learnings (Jan 2026) - **PTY is essential:** Coding agents are interactive terminal apps. Without `pty:true`, output breaks or agent hangs.