Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add XBlueSky/cc-loadout/plugin install cc-loadoutWrote 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/xbluesky/cc-loadout/schedule)<a href="https://agentmods.dev/skills/xbluesky/cc-loadout/schedule"><img src="https://agentmods.dev/badge/skills/xbluesky/cc-loadout/schedule/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/xbluesky/cc-loadout/schedule"><img src="https://agentmods.dev/badge/skills/xbluesky/cc-loadout/schedule.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 | $0.00149 | $0.01476 |
| Opus 5.5 | $0.00060 | $0.00590 |
| Sonnet 5.5 | $0.00030 | $0.00295 |
| Haiku 4.5 | $0.00015 | $0.00148 |
Grade A, and why
schedule 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 2mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guided cc-loadout task setup
You help the user create a recurring headless Claude task via cc-loadout — the
config that schedules claude -p <prompt> to run non-interactively at a fixed
time, on a chosen account, inside a specific repo. You drive the cc-loadout task
CLI; you do not hand-write tasks.json or touch crontab yourself — the CLI
validates and writes everything.
Prerequisite
The cc-loadout CLI must be installed (cc-loadout --version). If it's missing,
that's normally the SessionStart hook not having run yet or having failed — have
the user start a fresh session first; install.sh (see the cc-loadout README) is
the fix only for someone using the CLI without the plugin.
Steps
1. Shape the prompt (the real value-add)
Get the recurring intent from the user and turn it into a concrete, self-contained
headless prompt. The key constraint: claude -p runs non-interactively — there
is no follow-up, no clarification round-trip, no keyboard. The prompt must be fully
self-contained.
Prefer a slash command where one exists (/cortex:weekly, /cortex:distill,
/code-review, etc.) — they are already self-contained by design. Otherwise write a
crisp imperative that leaves no ambiguity (e.g. Generate the weekly Cortex report and commit it rather than do the weekly thing).
Ask the user what they want to happen, then draft the prompt text with them before moving on.
2. Pick when, who, and where
Three things to resolve:
When — one or more HH:MM times (24-hour). Multiple fire times are passed as
separate --at values (e.g. --at 08:00 --at 20:00).
Who (account) — list real account aliases and have the user pick one:
cc-loadout account list --json
Use the alias field from the JSON output. The task runs under that account's
Claude session.
Where (cwd) — an absolute path to the repo the task should run in.
cc-loadout does not expand ~, so confirm the full path (e.g.
/home/you/cortex, not ~/cortex). This is also where any relative slash
commands resolve their context.
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.
- 2mo ago First seen · 149 lines · 149 tokens per session scan A 31f3babdf9f9
schedule is a skill published in the GitHub repository XBlueSky/cc-loadout (2 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 1,476 once invoked, about $0.0006 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 2026-08-31.
schedule compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| scheduleXBlueSky/cc-loadout | Skill | 2 | 1mo ago | MIT | A | 149 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 112k | today | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 2d ago | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | today | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 11d ago | MIT | A | 52 | Claude Code, Codex |