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/paultyng/skill-issue/start-daynpx skills add paultyng/skill-issue --skill start-daygit clone --depth 1 https://github.com/paultyng/skill-issueWrote 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/paultyng/skill-issue/start-day)<a href="https://agentmods.dev/skills/paultyng/skill-issue/start-day"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/start-day.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 | $0.00069 | $0.00927 |
| Opus 5 | $0.00034 | $0.00464 |
| Sonnet 5 | $0.00014 | $0.00185 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
start-day 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 5d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start Day
Produce a short morning brief: what happened since the user was last active, and 2–8 ranked things to do today. Discovery-driven — no hardcoded sources. Read-only; never posts, commits, or mutates anything.
1. Compute the lookback window
A since:<date|weekday> argument overrides everything below.
Two inputs, combined:
- fixed_floor — the minimum lookback. The last business day at 15:00 local (17:00 assumed end-of-day, minus 2h). Last business day: Mon → previous Fri; Sat/Sun → previous Fri; else → yesterday.
- empirical — extends the window earlier only. The end of the user's last genuinely active day: the later of (a) the newest local session under
~/.claude/projects/*/*.jsonldated before today, and (b) the user's last Slack message (from:me sort:timestamp).
window_start = the earlier of fixed_floor and empirical. Empirical can only push earlier — a low-focus weekend glance cannot shrink the window below fixed_floor, and a vacation gap extends it. window_end = now.
Compute fixed_floor (macOS date):
case $(date +%u) in 1) back=3;; 7) back=2;; *) back=1;; esac # Mon→Fri, Sun→Fri, else yesterday (Sat→Fri via back=1)
floor=$(date -v-${back}d -v15H -v0M -v0S +%s) # last business day @ 15:00 local
Holidays need no special handling: if the last business day was a holiday, the user's empirical last-active day predates it and extends the window automatically.
2. Discover and run summarization skills
Scan the available skills. Run every skill whose name matches summarize-* OR whose description declares summary / recap / status intent. Do not hardcode which ones — discover them so newly added ones are picked up. Pass the window when a skill accepts a range. If none exist, skip this step.
3. Run local extensions
Run every available skill whose name matches start-day-* (there may be several). Machine- and context-specific morning setup lives there, outside this portable skill. Fold each extension's output into the brief as bullets.
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.
- 5d ago First seen · 57 lines · 69 tokens per session scan A b0cbbfe539df
start-day is a skill published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 24d ago), licensed MIT. It adds 69 tokens to every session and 927 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
collection
Choose which SkillNote skill collection is active for this Codex project. Use when the user says "change collection", "switch skills", "use frontend skills", or "show collections".
confluence-search
Search Confluence using CQL queries, validate syntax, export results, and manage search history. ALWAYS use when user wants to find, search, or query for content.
confluence-ops
Cache management, API diagnostics, and operational utilities. Use when optimizing performance, managing cache, diagnosing API issues, or troubleshooting Confluence connectivity.
confluence-property
Manage content properties (custom metadata) on Confluence pages and blog posts. ALWAYS use for custom metadata, key-value data, or application-specific fields.
confluence-comment
Manage comments on Confluence pages - add, get, update, delete, and resolve comments. ALWAYS use for feedback, discussions, and inline annotations.
confluence-hierarchy
Navigate and manage Confluence page hierarchies, ancestors, descendants, and trees. ALWAYS use for parent/child relationships and page tree navigation.