at
Skill17 starsChanged 8 months agoMITView on GitHub
Manage one-shot scheduled jobs via OS-native schedulers (launchd on macOS, atd on Linux/WSL)
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- release-cekernelSkill
- cronSkill
- dispatchSkill
- orchctlSkill
- orchestrateSkill
- postmortemSkill
- probeSkill
- setupSkill
- unix-architectSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Read skills/references/namespace-detection.md from the repository root ($(git rev-parse …
- Very specific: line 35
If the user provides all required options (--schedule and one of --label/--prompt), pass them directly.
- Distinctive: line 37
If any required option is missing, interactively ask the user for the missing values before executing:
- Very specific: line 42
If both given, --prompt takes precedence.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/at
Manage one-shot scheduled execution of cekernel dispatch. Uses OS-native schedulers (launchd on macOS, atd on Linux/WSL).
Usage
/at register --schedule "<datetime>" [--label <label>] [--prompt <prompt>] [--repo <path>]
/at list
/at cancel <id>Note: In plugin mode, /cekernel:at also works.
Workflow
Step 1: Detect Namespace and Determine Script Location
- Read
skills/references/namespace-detection.mdfrom the repository root ($(git rev-parse --show-toplevel)/skills/references/namespace-detection.md). If the Read fails (file not found), you are in plugin mode. - Execute the detection Bash snippet from the reference file.
- Set the script path based on the result:
- If
CEKERNEL_NS=local:AT_SH="$(git rev-parse --show-toplevel)/scripts/scheduler/at.sh" - If
CEKERNEL_NS=plugin:AT_SH="$(dirname "$(dirname "$(which spawn-worker.sh 2>/dev/null)")")/scripts/scheduler/at.sh"
- If
Step 2: Execute Command
register — Interactive Option Builder
If the user provides all required options (--schedule and one of --label/--prompt), pass them directly.
If any required option is missing, interactively ask the user for the missing values before executing:
--labelor--prompt(one required): Ask whether to use a dispatch label or a custom prompt.--label <label>— Shorthand: generates prompt"/dispatch --env headless --label <label>"for theclaude --bgsession--prompt <prompt>— Arbitrary prompt string passed directly to theclaude --bgsession- If both given,
--prompttakes precedence.
--schedule(required): Ask for an ISO 8601 datetime. Show format examples:2026-03-15T09:00— March 15, 2026 at 9:00 AM2026-12-31T23:59— December 31, 2026 at 11:59 PM- Format:
YYYY-MM-DDThh:mm
--repo(optional): Ask if the target repository is the current directory. If not, ask for the path.
Once all values are gathered, confirm the full command with the user, then execute.
list / cancel
Pass directly to at.sh:
bash "$AT_SH" register --label "ready" --schedule "2026-03-15T09:00"
bash "$AT_SH" list
bash "$AT_SH" cancel cekernel-at-a1b2c3Step 3: Present Results
- For
register: The script outputs registration details. Confirm to the user. - For
list: The script outputs a formatted table. Show it directly. Entries marked[drifted]were removed from the OS scheduler externally — suggest re-registering or cancelling. Completed entries (withlast_run_status) remain for diagnostics — suggest cancelling to clean up. - For
cancel: The script confirms cancellation. Relay to the user. - On errors: Show the error message and suggest corrective action.
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.

