repeat-with-delay
Skill545 starsChanged 9 months agoMITView on GitHub
Execute repeated shell commands as separate tool calls with a delay between each iteration. Use when a user asks to run something N times, wait between runs, increment a counter each cycle, and see each iteration result before the next run.
In this repository13 other files it gives its agents.
- ACPClient/AGENTS.mdAGENTS.md
- Agents.mdAGENTS.md
- Agmente/AGENTS.mdAGENTS.md
- AgmenteTests/AGENTS.mdAGENTS.md
- AgmenteUITests/AGENTS.mdAGENTS.md
- AppServerClient/AGENTS.mdAGENTS.md
- e2e/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- acp-local-runnerSkill
- codex-local-cli-e2eSkill
- upstream-protocol-drift-watchSkill
- run-agmente-codex-e2eSkill
- run-agmente-e2eSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Run one command at a time as individual tool calls so each iteration is visible in the transcript.
- Distinctive: line 26
If not on the final iteration and delay is greater than zero, run a separate sleep tool call:
- Distinctive: line 48
Keep loop execution sequential.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Repeat With Delay
Run one command at a time as individual tool calls so each iteration is visible in the transcript.
Required Execution Model
- Determine loop parameters from the request:
iterations(default10)delay-seconds(default2)start(default1)command(defaultecho "$LOOP_COUNTER")
- Execute iterations sequentially using separate tool calls:
- For each iteration, run one command tool call.
- Export the loop counter to that single call:
LOOP_COUNTER=<value> bash -lc '<command using $LOOP_COUNTER>'- Show that tool call result before continuing.
- If not on the final iteration and delay is greater than zero, run a separate sleep tool call:
sleep <delay-seconds>- Continue until iteration
Nis done. Do not batch iterations into one shell loop when the user wants per-iteration visibility.
Example Mapping
For "run 10 times and delay for 2 seconds between each", execute:
- 10 separate command tool calls (
LOOP_COUNTER=1toLOOP_COUNTER=10) - 9 separate sleep tool calls (
sleep 2) between runs
For "echo a number starting at 1 and increment each time":
LOOP_COUNTER=1 bash -lc 'echo "$LOOP_COUNTER"'
LOOP_COUNTER=2 bash -lc 'echo "$LOOP_COUNTER"'
...Notes
- Keep loop execution sequential; do not parallelize iterations unless explicitly requested.
- Preserve command failures; if one iteration fails, stop and report the failing iteration.
- Optional fallback script exists at
scripts/run_repeat_with_delay.sh, but use it only if the user explicitly asks for one single wrapper command.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

