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 SHAHARYAR1255/sunrise --skill setgit clone --depth 1 https://github.com/SHAHARYAR1255/sunriseWrote 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/shaharyar1255/sunrise/set)<a href="https://agentmods.dev/skills/shaharyar1255/sunrise/set"><img src="https://agentmods.dev/badge/skills/shaharyar1255/sunrise/set.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 | $0.00058 | $0.01012 |
| Opus 5 | $0.00029 | $0.00506 |
| Sonnet 5 | $0.00012 | $0.00202 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
set 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sunrise: set your session start time
The user wants their Claude 5-hour usage window to start at a chosen local time each day, so resets land predictably. You achieve this by creating a cloud routine (the same thing the built-in /schedule creates) that sends one tiny no-op message four times a day, five hours apart. Each message starts or refreshes the 5-hour window, keeping it primed.
A plugin cannot run on a timer itself — only a cloud routine runs 24/7 (even with the user's machine off). So your job here is to compute the schedule and create that routine.
Requested start time (may be empty): $ARGUMENTS
Follow these steps in order.
1. Parse the start hour
From "$ARGUMENTS", determine the start hour in 24-hour local time.
- Accept forms like
9am,9,09:00,9:00am,21,6am,18:30. - Default the minute to :07 unless the user specified one. (An off-:00 minute avoids the top-of-hour rush and reliably lands just after each window boundary.)
- If "$ARGUMENTS" is empty or genuinely ambiguous, ask the user: "What local time should your Claude window start each day?" Then continue once they answer.
2. Compute the four daily ping times (local)
The window lasts 5 hours, so prime four times a day:
- T1 = start hour
- T2 = (start + 5) mod 24
- T3 = (start + 10) mod 24
- T4 = (start + 15) mod 24
All four use the same minute. This keeps a window primed for ~20 hours a day; the one unavoidable ~4-hour gap (because 24 is not divisible by 5) lands overnight when the start hour is the user's wake time.
3. Confirm before creating anything
Show the user, in their local time:
- The four ping times T1–T4.
- That their window will then reset at (start+5), (start+10), (start+15), (start+20) mod 24.
- That this uses ~4 of their 15 daily routine runs and needs a Claude Pro or Max plan with Claude Code routines.
Ask them to confirm. If they decline, stop and change nothing.
4. Create (or update) the routine
Invoke the built-in schedule skill (the /schedule routine creator) to make a recurring cloud routine with exactly these parameters:
- name:
sunrise - schedule: every day at T1, T2, T3, T4 local time. (The routine system converts local to a UTC cron. A single cron
MINUTE H1,H2,H3,H4 * * *in UTC works, since all four pings share one minute.) - model:
claude-opus-4-8— must be a heavy model. Lighter models like Haiku do NOT anchor the 5-hour usage window (the window silently never starts); Opus does. The prompt is trivial, so the cost is ~one token regardless of model. - git repositories / sources: none. This routine performs no work and needs no repo.
- prompt:
Output exactly: ok. Do not read files, run commands, use tools, or change anything. Then stop.
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 · 58 lines · 58 tokens per session scan A 84e2193e824d
set is a skill published in the GitHub repository SHAHARYAR1255/sunrise (4 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 1,012 once invoked, about $0.0003 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
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
sys-configure
Configure Claude Octopus — redirects to /octo:setup interactive wizard.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
recipe-reverse-engineer
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow.
37signals-way
Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…