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 skills add Cloudgeni-ai/opengeni --skill schedulesgit clone --depth 1 https://github.com/Cloudgeni-ai/opengeniWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cloudgeni-ai/opengeni/schedules)<a href="https://agentmods.dev/skills/cloudgeni-ai/opengeni/schedules"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/schedules/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cloudgeni-ai/opengeni/schedules"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/schedules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00055 | $0.01233 |
| Opus 5.5 | $0.00022 | $0.00493 |
| Sonnet 5.5 | $0.00011 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
schedules 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a schedule
Turn the user's description into scheduled work in the current workspace. Research what is available before asking questions. Ask only for essential details you cannot discover or reasonably decide from the request.
Choose the destination
By default, schedule a message in this conversation. “Remind me”, “check later”,
“keep watching” and “schedule yourself” mean continue this chat. Supply name,
schedule and prompt; the tool resolves the current chat from its signed
context. Choose another existing chat with targetSessionId only when requested.
Its model, tools, machine and attachments apply at run time, so do not copy those
settings into the schedule.
Use reusable_session or new_session_per_run with agentConfig only when the
user requests separate-agent work. Sessionless calls require an explicit
destination or a separate-agent mode.
For separate-agent work, use agentConfig.executionTarget: "workspace_default"
unless the user chose a specific machine or backend. Each new run chat resolves
the current workspace default; a reusable chat keeps its first machine. Explicit
machineTarget or sandboxBackend pins placement and cannot be combined with
executionTarget. An unavailable machine is a blocker, never permission to
switch computers.
Discover what the task needs
- Use
scheduled_tasks_listto avoid duplicating an existing schedule. Follow pagination when needed and usescheduled_tasks_getfor a relevant task's details. A list summary is not its complete configuration. - If the work needs a repository, use
github_repositories_listto find the authorized repository and select the required resources. - If the scheduled agent needs credentials, use
secret_searchto find the saved item and write its reference (for example{{secret:GitHub/token}}) in the prompt. Save it to the workspace withsecret_saveorsecret_movewhen the schedule runs without you; never copy secret values into prompts. - If it needs an integration such as Slack or Sentry, use
capability_catalog_searchand the available tool discovery to find the capability and exact operations. Follow returned connection/setup and approval requirements. Do not claim that discovery means the integration is ready. - For posting as the workspace Slack bot, verify the available bot and channel through its tools. Record the exact Slack workspace and channel in the task instructions; use an explicit connection ID when multiple bots are available. Scheduled and interactive work use the same bot capability. No separate schedule-specific posting setting is required. Never substitute a personal account when the user requested the bot.
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 · 107 lines · 55 tokens per session scan A cd7929fdb263
schedules is a skill published in the GitHub repository Cloudgeni-ai/opengeni (205 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,233 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-21.
Other skills, from other repositories
output-meta-project-context
Comprehensive guide to Output.ai Framework for building durable, LLM-powered workflows orchestrated by Temporal. Covers project structure, workflow patterns, steps, LLM integration, HTTP clients, CLI commands, and the full inventory of available agents and skills.
output-dev-eval-testing
Create offline evaluation tests for Output SDK workflows using @outputai/evals. Use when implementing test evaluators with verify(), creating dataset YAML files, building eval workflows, or running workflow tests via CLI.
output-eval-error-analysis
Systematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval project, after significant pipeline changes, or when production quality drops.
output-build-workflow
Implement an Output SDK workflow from a plan document. Use when the user asks to build, implement, or code a workflow from an existing plan, or after output-plan-workflow has produced a plan and the user is ready to build.
output-dev-create-skeleton
Generate workflow skeleton files using the Output SDK CLI. Use when starting a new workflow, scaffolding project structure, or understanding the generated file layout.
output-dev-folder-structure
Workflow folder structure conventions for Output SDK. Use when creating new workflows, organizing workflow files, or understanding the standard project layout.