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 adtn0810/truestack --skill truestack-task-schedulinggit clone --depth 1 https://github.com/adtn0810/truestackWrote 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/adtn0810/truestack/truestack-task-scheduling)<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-task-scheduling"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-task-scheduling/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/adtn0810/truestack/truestack-task-scheduling"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-task-scheduling.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 | $0.00140 | $0.01056 |
| Opus 5 | $0.00070 | $0.00528 |
| Sonnet 5 | $0.00028 | $0.00211 |
| Haiku 4.5 | $0.00014 | $0.00106 |
Grade A, and why
truestack-task-scheduling 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 10d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
truestack-task-scheduling
A scheduled run happens with no memory of this conversation — only the job spec you write and whatever lives in committed project memory. So the whole skill is about making the future run self-sufficient, grounded at run time, and safe to repeat. Get the spec right and it runs unattended for months; get it vague and it silently does the wrong thing every morning.
1. Is it actually a schedule?
- A cadence ("every morning", "each Monday", "hourly") → schedule it.
- A time phrase describing the subject, not the timing ("summarize yesterday's standup") → that's a one-off; just do it now.
- Ambiguous? Do it once now, then offer to make it recurring — don't assume.
2. Write the job spec
Capture four things, precisely:
- Trigger — a recurring cadence (cron, e.g.
0 6 * * *for 06:00 daily) or a one-time fire-at timestamp. Pin the timezone. - The run prompt — the exact, self-contained instruction the run will execute. It must name its own data sources and re-fetch them at run time; it cannot rely on anything from this chat.
- Delivery — what "done" produces and where it goes (a file, a message, a report, a memory update), so a silent run isn't a useless run.
- Failure policy — what to do on error or empty result: skip quietly, retry, or alert — and explicitly don't spam the user with "nothing to report" every day unless they asked.
3. Ground at run time (never bake in stale facts)
The single biggest scheduled-task bug: freezing today's data into the prompt. The run must read live sources and current memory when it fires — "yesterday" is computed at run time, prices and statuses are re-fetched, the repo is re-read. Author the prompt so it pulls fresh, not so it repeats a snapshot.
4. Make repeated runs safe
- Idempotent / bounded: a run must be safe to fire again; guard against overlap if one run can outlast its interval; cap the work so a busy day can't blow up.
- Side-effects stay gated: a scheduled job still obeys the boundaries — it may prepare a message, payment, or destructive change, but anything Ask-first needs human approval, not an automatic 6am execution. Schedule the draft, not the irreversible send, unless the user explicitly authorized the action itself.
What ships with it
1 file 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.
- 10d ago First seen · 74 lines · 140 tokens per session scan A 8589b32a7790
truestack-task-scheduling is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 140 tokens to every session and 1,056 once invoked, about $0.0007 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
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".
notifications
Send notifications through the unified notification router.
gmail-trigger
Beta. Act on new Gmail as it arrives: get pinged only for urgent mail, digest newsletters, forward invoices — any standing instruction, across one or several accounts.
offer-toolkit-skill
A set of job-search tools covering the path from finding a vacancy to accepting an offer. It includes separate tools for job searches, job-description analysis, tailored resumes, behavioral interviews, offer comparisons, and salary negotiation.
start-the-day
An on-demand personal daily briefing — weather, headlines, the shape of your day, and one thing worth your attention — in a sharp executive-assistant voice. The general-purpose morning brief; richer work or admin digests compose it as their general layer.