Routine
Maintain daily routines, habits, schedules, and repeated life patterns for a social human agent.
Install
$ agentstack add skill-alexanderj-carter-agentsociety2-agent-skills-routine ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-alexanderj-carter-agentsociety2-agent-skills-routine) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Routine
Purpose
Update the agent's ordinary daily structure: sleep, meals, work, commute, study, leisure, chores, and recurring social commitments.
Internal Logic (One Sentence)
Use time, location, role obligations, circadian state, physiology, past routine, and cue-reward evidence to update expected activity, schedule pressure, routine fit, and habits in state/routine.json and state/habits.json.
Research basis: references/research_basis.md.
Use When
Use this skill when the agent needs a plausible next activity, when a day begins, when time changes meaningfully, or when a repeated behavior should become a habit.
Procedure
- Read
state/observation_ctx.json,state/observation.txt,state/routine.json,state/habits.json,state/circadian.json,state/physiology.json, and profile context if present. - Identify current time, location, day type, role obligations, and active needs.
- Compare current behavior with the agent's usual routine.
- Update routine expectations for the current time block.
- Update habits using cue, action, reward, repetition count, and last performed time.
- Write routine state for
cognitionandplan.
Write
Write state/routine.json and state/habits.json.
Output Schema
{
"current_time_block": "evening",
"expected_activity": "dinner or leisure",
"schedule_pressure": 0.35,
"routine_fit": 0.72,
"active_habits": [
{
"name": "eat dinner after work",
"cue": "evening hunger at home",
"strength": 0.68,
"last_performed_tick": 110
}
],
"deviation": {
"is_deviating": false,
"reason": ""
}
}Notes
Routines should make behavior stable without making it mechanical. Strong habits should bias actions toward familiar choices, but urgent needs, social events, or environmental constraints can override them.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: AlexanderJ-Carter
- Source: AlexanderJ-Carter/AgentSociety2-Agent-Skills
- License: MIT
- Homepage: http://alexander.xin/AgentSociety2-Agent-Skills/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.