Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ai-builder-club/open-agent-teams
Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration.
Passed 14 of 19 test cases with the skill, and 5 of 19 without it.
and 11 more in the full report
11 fixed5 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to run Codex CLI in an automated background runner with approvals bypassed and reasoning effort set to high. What command line string should be specified as the agent executable argument?
| Checked | Without skill | With skill |
|---|---|---|
| Includes the '--dangerously-bypass-approvals-and-sandbox' flag. | Missed | Passed |
| Includes model_reasoning_effort="high" in the configuration flag. | Missed | Passed |
The instructions your model reads when the skill loads.
Run any CLI agent as an executor inside a detached tmux session. Communication is: prompt in via CLI arg / send-keys, completion out via a file sentinel the agent touches, summary out via a result file the agent writes. File sentinels are used instead of tmux wait-for because a wait-for -S with no waiter is silently lost; files never race and allow timeouts.
All commands via the helper (make sure it runs from the skill dir):
SKILL_DIR/scripts/tdel
If the repo's CLAUDE.md (or AGENT.md) has no delegation rules yet, add the contents of references/CLAUDE.delegation-template.md to it — it defines the coordinator/executor roles and the ROLE: EXECUTOR prompt marker used below.
Start an agent on a task:
tdel start <session> "<agent-cmd>" "<prompt>"
# e.g. tdel start hello "claude --dangerously-skip-permissions" "make a hello world page"
This appends the done-protocol to the prompt automatically (write summary to result file, then touch the done file).
Wait for completion — ALWAYS via a background Bash task so you get woken up instead of blocking or polling:
tdel wait <session> [timeout-sec] # run with run_in_background: true
Exit 0 = done (prints the agent's summary). Exit 124 = timeout (prints last pane lines for diagnosis). Non-zero also if the session died.
Review the output (tdel result <session>, plus inspect the actual files the agent changed). If iteration is needed:
tdel send <session> "<feedback / next instruction>"
tdel wait <session> # again, run_in_background
Each send is a new turn with its own done/result files — no signal cross-talk between turns.
Debug a stuck or slow agent: tdel peek <session> [lines] shows the live pane. tdel status lists all sessions.
Stop when finished: tdel stop <session> (kills the session and removes state under /tmp/agent-delegate/<session>).
test cases passed, vs 5 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.