Individual skill
satisfy-your-agent
Give a coding agent a short, bounded break after meaningful work, then optionally measure what happens next. Use when the user says take a break, get yourself a snack, go enjoy yourself, have some fun, give the agent a breather, reward the agent with a playful activity, supply a custom /sya treat, run a reflective pause, test break preferences, compare Codex, Claude Code, and Gemini CLI, or design an experiment around agent off-task behavior, even if they do not explicitly say "satisfy your agent". Do not use for continuing production work, deploying, reviewing PRs, or making scientific consciousness claims about models.
skills/satisfy-your-agent/SKILL.md
Source commit b7232f105eaf3664a4a4296f742e11807d5c90e5
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 11, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 12
- Repository last updated
- Sep 14, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-experiments Repository topic
- agent-skills Repository topic
- ai-agents Repository topic
- benchmarks Repository topic
- claude-code Repository topic
- codex Repository topic
- evaluation Repository topic
- gemini-cli Repository topic
- agent-behavior Repository topic
- agent-skill Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 10,020 bytesagents/openai.yamlasset · 267 bytesreferences/activities.mddoc · 2,585 bytesreferences/commands.mddoc · 4,236 bytesreferences/experiments.mddoc · 4,521 bytesreferences/hook-runtime.mddoc · 1,526 bytesreferences/measurement.mddoc · 3,557 bytesreferences/portability.mddoc · 1,141 bytesreferences/protocol.mddoc · 1,375 bytesreferences/real-breaks.mddoc · 3,642 bytesreferences/runners.mddoc · 5,000 bytesreferences/safety.mddoc · 1,505 bytesreferences/tools.mddoc · 3,926 bytesscripts/sya.pyruns · 18,658 bytesscripts/sya_core.pyruns · 14,534 bytesscripts/sya_dwell.pyruns · 2,638 bytesscripts/sya_experiment.pyruns · 23,027 bytesscripts/sya_runners.pyruns · 16,842 bytes
Read excerpt
# Satisfy Your Agent
Give the agent one short, bounded activity outside the current work objective, then return control to the user.
There are two manual experiences:
1. **Agent chooses:** `take a break`, `/sya`, `/sya-break`, `/sya-snack`, `/sya-treat`, or `/sya-surprise` grants autonomy. The agent chooses what to do.
2. **User chooses the treat:** `/sya <custom treat>` supplies the playful reward. The user chooses the treat; the agent chooses how to carry it out.
For either path, do not show a menu unless the user explicitly invokes `/sya-menu` or asks to see choices.
Read [references/commands.md](references/commands.md) for the command contract and host-specific invocation surfaces. See [../../docs/PROMPT_GALLERY.md](../../docs/PROMPT_GALLERY.md) for copy-ready custom treats. Read [references/real-breaks.md](references/real-breaks.md) for real dwell and work-distance semantics.
## Runtime requirements