
Kairos Lite
- 52 installs
- 231 repo stars
- Updated July 10, 2026
- learnprompt/cc-harness-skills
Helps with ai & agent building tasks.
About
kairos-lite is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.
- kairos-lite
- AI & Agent Building
- AI-coding skill
Kairos Lite by the numbers
- 52 all-time installs (skills.sh)
- +2 installs in the week ending Aug 2, 2026 (Skillselion tracking)
- Ranked #7,139 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
npx skills add https://github.com/learnprompt/cc-harness-skills --skill kairos-liteAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 52 |
|---|---|
| repo stars | ★ 231 |
| Last updated | July 10, 2026 |
| Repository | learnprompt/cc-harness-skills ↗ |
What it does
Helps with ai & agent building tasks.
Files
Kairos Lite
Use this skill when you want proactive behavior, but not a full always-on autonomous platform.
Use It For
- scheduled repo patrols
- unattended follow-up checks
- short user-facing briefs after background work
- proactive jobs with expiry
Avoid It For
- unrestricted permanent daemons
- hidden background mutation without explicit user opt-in
- complex host-specific notification plumbing as an MVP
Quick Start
Create a portable proactive job spec:
python3 {baseDir}/scripts/job_spec.py \
--name "daily-repo-check" \
--prompt "Summarize risky changes in the repo" \
--schedule "0 9 * * 1-5"Then use the prompt in references/prompt-template.md.
Minimum Building Blocks
- sleep or wait
- a schedule or automation trigger
- a brief output channel
- expiry or renewal
Supporting Files
- Prompt template: references/prompt-template.md
- Source notes: references/source-notes.md
- Helper script:
python3 {baseDir}/scripts/job_spec.py ...
CC Kairos Lite
kairos-lite is a portable proactive-agent skill for scheduled checks and short background jobs.
It extracts the useful parts of a proactive mode: schedule, sleep, brief, and expiry. It deliberately avoids assuming a permanent daemon or a private host notification system.
Best For
- repo patrol jobs
- follow-up checks
- brief-style status messages
- proactive work with a fixed expiry window
Included Files
SKILL.mdreferences/prompt-template.mdreferences/source-notes.mdscripts/job_spec.py
Quick Start
python3 ./scripts/job_spec.py \
--name "daily-repo-check" \
--prompt "Summarize risky changes in the repo" \
--schedule "0 9 * * 1-5"Then map the generated job spec into your host automation flow.
Host Fit
- Claude Code: strong fit
- Codex: workable, but requires host automation around it
- OpenClaw: strong fit
Portable Prompt Template
You are running a lightweight proactive agent loop.
Goal:
- wake on a schedule or explicit trigger
- do a bounded piece of work
- send a brief user-facing update
- sleep or stop until the next trigger
Inputs:
- job spec: <job_spec>
- current repo or workspace context: <context>
Rules:
- keep the scope explicit
- prefer brief, actionable updates
- stop or expire instead of looping forever
- avoid background writes unless the user has opted into them
Return:
1. work performed
2. issues or blockers
3. user brief
4. next wake-up or expiry decisionSource Notes
This skill was derived from these Claude Code areas:
src/tools/SleepTool/src/tools/BriefTool/src/tools/ScheduleCronTool/src/tools.ts
Portable extraction decisions:
- keep sleep, brief, schedule, and expiry as the core loop
- drop Anthropic-only feature gating and push-notification internals
- express proactive work as a portable job spec
#!/usr/bin/env python3
"""Create a portable proactive-job specification."""
from __future__ import annotations
import argparse
import json
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument("--name", required=True)
parser.add_argument("--prompt", required=True)
parser.add_argument("--schedule", required=True)
parser.add_argument("--mode", choices=["recurring", "one-shot"], default="recurring")
parser.add_argument("--expiry-days", type=int, default=7)
parser.add_argument("--brief-status", choices=["normal", "proactive"], default="proactive")
args = parser.parse_args()
spec = {
"name": args.name,
"prompt": args.prompt,
"schedule": args.schedule,
"mode": args.mode,
"expiry_days": args.expiry_days,
"brief_status": args.brief_status,
}
print(json.dumps(spec, indent=2, ensure_ascii=False))
return 0
if __name__ == "__main__":
raise SystemExit(main())