Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/cocorof/geny-executor/loopnpx skills add CocoRoF/geny-executor --skill loopgit clone --depth 1 https://github.com/CocoRoF/geny-executorWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00046 | $0.01171 |
| Opus 5 | $0.00023 | $0.00585 |
| Sonnet 5 | $0.00009 | $0.00234 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
Loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop — schedule a recurring task
You are recording a recurring instruction. The host is responsible for the actual cron daemon — your job is to (1) parse what the user asked for, (2) translate it into a canonical cron expression, and (3) hand it off to the host's scheduler with a clear acknowledgement.
Inputs
${interval}— when to fire. Three syntaxes accepted:- Compact:
5m,30m,1h,2h,1d,12h. Translate to cron. - Cron expression:
*/5 * * * *,0 9 * * 1— pass through. - Plain English: "every weekday at 9am", "every 30 minutes", "every Monday morning". Convert to cron.
- Compact:
${task}— what to do each tick. Free-form; quote it with double-quotes if it contains spaces.
If either is missing, ask once. Don't guess on task — a
mis-recorded recurring task is worse than none.
Translate to cron
Standard 5-field POSIX cron: minute hour day-of-month month day-of-week.
Common compact translations:
| Compact | Cron expression | Meaning |
|---|---|---|
5m |
*/5 * * * * |
every 5 minutes |
15m |
*/15 * * * * |
every 15 minutes |
30m |
*/30 * * * * |
every 30 minutes |
1h |
0 * * * * |
every hour on the hour |
2h |
0 */2 * * * |
every 2 hours |
4h |
0 */4 * * * |
every 4 hours |
12h |
0 */12 * * * |
every 12 hours |
1d |
0 0 * * * |
every day at midnight |
1w |
0 0 * * 0 |
every Sunday at midnight |
For natural-language inputs, try to be conservative. "Every morning"
defaults to 09:00 unless the user said otherwise. "Every weekday at
5pm" → 0 17 * * 1-5. If you're not sure, echo back your
interpretation and ask the user to confirm before scheduling.
Hand off to the scheduler
This skill does not implement the cron daemon itself — the host
provides one (geny-executor's cron extra ships croniter-backed
scheduling; Geny exposes ScheduleCron / similar tools).
Your job:
- Show the user the parsed schedule + task in one block:
Schedule: <cron expression> (every <human-readable description>) Task: <task> - Hand the canonical schedule + task off to the host's scheduler.
In a Geny-style host the next step is calling
ScheduleCron/ the equivalent tool with(cron_expression, task). If no such tool is in the current tool roster, don't fake it — say so: "I parsed your request to . The current session doesn't have a scheduler tool wired; here's the canonical form to keep for when you set one up." - Confirm the schedule was registered with a single short sentence, including the cron expression so the user can edit it later if needed.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 104 lines · 46 tokens per session scan A df7edc619527
Loop is a skill published in the GitHub repository CocoRoF/geny-executor (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,171 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.