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/onebrain-ai/onebrain/schedule-oncenpx skills add onebrain-ai/onebrain --skill schedule-oncegit clone --depth 1 https://github.com/onebrain-ai/onebrainWrote 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/onebrain-ai/onebrain/schedule-once)<a href="https://agentmods.dev/skills/onebrain-ai/onebrain/schedule-once"><img src="https://agentmods.dev/badge/skills/onebrain-ai/onebrain/schedule-once.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.01886 |
| Opus 5 | $0.00021 | $0.00943 |
| Sonnet 5 | $0.00008 | $0.00377 |
| Haiku 4.5 | $0.00004 | $0.00189 |
Grade A, and why
schedule-once 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 6d ago.
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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/schedule-once — One-shot scheduler wizard
Purpose
For users who want a reminder or task to fire ONCE at a specific date and time, then disappear cleanly. Walks through:
- Which skill to fire
- What date (YYYY-MM-DD)
- What time (HH:MM, 24-hour)
- Any required args (if the skill is
schedulable_with_args) - Confirms preview
- Writes one-shot entry to onebrain.yml + runs
onebrain schedule register
After the scheduled time, the OS scheduler runs the skill once and the entry deletes itself (launchd self-removal block · Task Scheduler DeleteExpiredTaskAfter · systemd ExecStopPost cleanup).
Skill flow
Step 1: Pick skill
List all schedulable skills by reading each SKILL.md frontmatter under .claude/plugins/onebrain/skills/. Filter for entries where schedulable: true OR schedulable_with_args: true.
Show via AskUserQuestion:
- question: "Which skill would you like to schedule for a one-time run?"
- header: "Schedule a One-Shot Run"
- multiSelect: false
- options (two groups):
- Skills with
schedulable: true(no args required): e.g./daily,/weekly,/recap,/doctor,/tasks,/moc - Skills with
schedulable_with_args: true(args required — wizard will prompt): e.g./distill,/research,/summarize,/search
- Skills with
Store: chosen_skill (the slash-command name, e.g. /daily).
Step 1b: Pick harness
Ask which harness should execute the skill: Claude (default/backward compatible), Gemini, or Codex. Store chosen_harness. Codex entries keep the shared YAML skill name (/daily); the scheduler translates it to $onebrain:daily.
Step 2: Pick date
Prompt for YYYY-MM-DD via plain conversational text:
What date should
{chosen_skill}run? Enter a date in YYYY-MM-DD format.
Validate:
- Format must match
YYYY-MM-DD(4-digit year, 2-digit month 01–12, 2-digit day 01–31). - Date must be strictly in the future relative to current datetime.
- If invalid or in the past, reject with a clear message and re-prompt:
- Malformed:
Invalid date format. Please use YYYY-MM-DD (e.g. 2026-05-15). - Past:
Date must be in the future. Current time: <now>.
- Malformed:
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.
- 6d ago First seen · 180 lines · 42 tokens per session scan A d46c00ca46d8
schedule-once is a skill published in the GitHub repository onebrain-ai/onebrain (26 stars, last pushed 8d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,886 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 2026-08-30.
Other skills, from other repositories
priority-dashboard
Use this to rebuild, inspect, or temporarily steer {{username}}'s current PersonalOS priority dashboard from canonical Actions, Attention Triggers, and owner context. Do NOT use it to create, complete, or independently manage tasks; use task-manager for Action and Trigger lifecycle changes.
wrap-session-up
End-of-session review for a Claude Code conversation. Replays what was discussed, checks for open action items, documents relevant outcomes in the brain vault, and creates Todoist tasks for anything untracked. Use at the end of a work session to ensure nothing falls through the cracks.
task-manager
Use this when {{username}} or an agent wants to add, review, prioritize, complete, defer, park, or inspect todos, open loops, confirmed actions, waiting states, or attention triggers. Maintains atomic records under operations/actions/ and operations/attention-triggers/ as the only local action truth. Do NOT use for…
gws-obsidian-prep
Cross-skill recipe: fetch today's (or tomorrow's) Google Calendar events via gws CLI and create meeting prep notes in the Obsidian vault.
resume
Восстановление контекста припаркованной задачи для продолжения работы. Агент сканирует plan.md §Blockers, log.md и delegations/-файлы активных проектов, находит активные блокеры, записи PAUSED и открытые делегирования, показывает пользователю список припаркованных задач с типами и триггерами, и после выбора загружает…
vault-onboarding-guide
Интерактивный проводник по первому запуску файлового хранилища с агентом. Используй, когда пользователь просит: «проведи онбординг», «помоги начать с хранилищем», «покажи методологию на практике», «хочу пощупать на реальной задаче», «научи работать с 00inbox, проектами, plan.md, tasks.md, parking/resume», «проведи по…