Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Kairos Lite — measured AI agent skill | DecimalAI

kentunderage549/kairos-lite

SkillScore91Maintained

Build a lightweight proactive mode with scheduled checks, sleep intervals, concise user briefs, and expiry safeguards so an agent can work in the background without becoming an uncontrolled daemon.

by kentunderage549

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

DevOps & SRE pack

decimalai skills pull kentunderage549-kairos-lite

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/kentunderage549-kairos-lite/SKILL.md

Raw file: /s/kentunderage549-kairos-lite/SKILL.md ↗ · machine-readable summary at /s/kentunderage549-kairos-lite.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

—-47% tokens0% turns91% of whole cases pass with skill (20/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-19	✗→✓	▲ Improved	-51%	0%
case-01	✗→✓	▲ Improved	-50%	0%
case-03	✗→✓	▲ Improved	-58%	0%
case-08	✗→✓	▲ Improved	-38%	0%
case-04	✗→✓	▲ Improved	-60%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

kentunderage549 / cc-harness-skills

skills/kairos-lite/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1Bundled 3 files · scripts

Skill contents

scripts/

references/

SKILL.md

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:

bash
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 ...

Want to see if kentunderage549/kairos-lite would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.