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 metraton/gaia --skill scheduled-taskgit clone --depth 1 https://github.com/metraton/gaiaWrote 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/metraton/gaia/scheduled-task)<a href="https://agentmods.dev/skills/metraton/gaia/scheduled-task"><img src="https://agentmods.dev/badge/skills/metraton/gaia/scheduled-task.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 | $0.00086 | $0.02745 |
| Opus 5 | $0.00043 | $0.01373 |
| Sonnet 5 | $0.00017 | $0.00549 |
| Haiku 4.5 | $0.00009 | $0.00275 |
Grade A, and why
scheduled-task 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 8d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scheduled Task
A scheduled task is a Gaia task that runs unattended on a recurring schedule
via the OS crontab, executes claude -p headless, and leaves the user a report
in the notifications inbox instead of asking anything mid-run. This skill covers
the three flows of its lifecycle: creating one, executing it headless, and
consuming what it reports. Work the user wants done once, now, in this session
is an ordinary dispatch, not a scheduled task.
The load-bearing constraint that shapes everything below: a headless run has no
user to answer a prompt. So a scheduled task must complete everything it can
WITHOUT a T3 mutation, and when a T3 is unavoidable it must NOT try to ask --
it accumulates the approval_id, finishes the rest, and reports back so the
user can resume and grant later. Gaia's T3 layer gates independently of Claude
Code's permission dialog: --dangerously-skip-permissions removes the TUI
prompt, but Gaia still blocks/accumulates T3 mutations exactly the same.
When to use
Trigger when the user asks for routine/scheduled execution: "cada noche corre X", "rutinariamente revisa Y", "cada 6 horas", "prográmame Z". If they want it run once now, this is the wrong skill -- that is an ordinary one-shot dispatch.
Flow A -- Creation (mount the task)
Build three artifacts, in order. Heavy mechanics and the full wrapper rationale
are in reference.md; the runnable templates are in scripts/.
- Write the task as a read-only-first atomic prompt. State the task's job as a self-contained prompt that opens with the headless preamble (Flow B). Front-load everything read-only; isolate any mutation as an explicit, clearly-labeled step so the headless run can skip-and-accumulate it cleanly. Store the prompt in its own file (one task = one prompt file).
- Copy the wrapper
scripts/run-scheduled-task.shto a per-task file (e.g.~/ws/me/scheduled-tasks/<task>.sh) and edit its==CONFIG==block:TASK_NAME,PROJECT_DIR,PROMPT_FILE. The wrapper exports credentials and PATH explicitly (cron has almost no environment), runs the validated headless invocation, persists the session, and parses out thesession_id. Do not drop--output-format jsonor add--no-session-persistence-- the session MUST stay resumable. - Add a staggered crontab entry from
scripts/crontab.template. Give the wrapper an ABSOLUTE path, redirect to a per-task log, and offset the minute so no two tasks start in the same minute.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 197 lines · 86 tokens per session scan A 6a7d1c2fcdaf
scheduled-task is a skill published in the GitHub repository metraton/gaia (3 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 2,745 once invoked, about $0.0004 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
review-team
A multi-reviewer code review process that checks a change from several specialist viewpoints and combines the results into one report. It can cover bugs, security, tests, dependencies, frontend behavior, and continuous-integration workflows.
ultra
Fans the work out as a fleet of parallel Grok and Codex agents billed to their own subscriptions, then synthesizes one result. The peer engine equivalent of ultracode, adding intensity without spending Claude quota on the fleet. Use it for genuinely broad goals, not only explicit asks for intensity.
grok-prompting
Brief writing guidance for composing self contained Grok briefs for coding, review, diagnosis, and second opinion tasks.
smoke
Runs a three probe live smoke wave after a plugin update and reports gate chain health before real work rides it.
codex-result-handling
Internal contract for returning Codex companion output without alteration.
shipwrights-loop
Drive multiple Jira tickets sequentially through the /shipwrights-epic pipeline. Auto-picks the next ticket, watches the PR until merged, transitions Jira to shipped, repeats. Resumable across Claude Code sessions via .shipwrights/loop-state.json. Invoked as /shipwrights-loop [N] | --status | --abort.