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 kriscard/Skills --skill todays-focusgit clone --depth 1 https://github.com/kriscard/SkillsWrote 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/kriscard/skills/todays-focus)<a href="https://agentmods.dev/skills/kriscard/skills/todays-focus"><img src="https://agentmods.dev/badge/skills/kriscard/skills/todays-focus/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/kriscard/skills/todays-focus"><img src="https://agentmods.dev/badge/skills/kriscard/skills/todays-focus.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 | $0.00036 | $0.02036 |
| Opus 5.5 | $0.00014 | $0.00814 |
| Sonnet 5.5 | $0.00007 | $0.00407 |
| Haiku 4.5 | $0.00004 | $0.00204 |
Grade A, and why
todays-focus 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 6d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Today's Focus
Three focus areas, an honest check-in, three questions to sit with. Help Chris judge what deserves attention, not assemble another backlog. Tools show what is happening; the vault explains what matters. Keep tasks in their existing trackers. Keep judgment human.
1. Establish scope and context
Read ../vault/SKILL.md, then the live vault-root AGENTS.md and its required personal context.
Resolve today's date and timezone from the user or environment; use the vault's stated timezone when
no override is given. Apply the live schema rather than the original author's vault layout.
Accept all, work, or personal from the invocation or an explicit request. Otherwise use
AskUserQuestionTool (or the runtime's structured question tool) to ask:
What should today's focus cover?
- All: work and personal priorities sharing one realistic day.
- Work: Roofr commitments, communication, and professional growth.
- Personal: personal projects, learning, health, and life outside work.
If no structured question tool is available, ask the same question in text. All means three focus areas total, not three per domain. Work mode still respects sleep and presence without turning private concerns into a work briefing. Personal mode does not query work trackers or work messages.
Completion: scope, local date, timezone, vault contract, and required decision context are known.
2. Gather relevant evidence
Use the connected MCP tools directly. Discover available capabilities and their actual schemas; MCP access is session-specific. Use authenticated identity and supported current-user filters. Resolve IDs through the connector only when required, rather than maintaining user IDs, emails, or team IDs in this skill. Ask when several accounts, workspaces, or calendars make the intended source ambiguous.
| Role | Source | Scope and retrieval |
|---|---|---|
| Decision context | Obsidian | Principles, current Top of Mind, relevant goals, and active project notes for the selected scope |
| Recent reflection | Obsidian | Existing daily notes from the last 14 days, including today; relevant current weekly note |
| Work tasks | Jira MCP | Work/All: active assigned issues, deadlines, blockers, and relevant sprint context |
| Personal tasks | Linear MCP | Personal/All: active personal-project issues and relevant milestones |
| Messaging | Slack MCP | Work/All: actionable mentions, accessible DMs, and relevant threads from the last 48 hours |
| Schedule | Google Calendar MCP | Remaining events today; tomorrow only when preparation matters today |
| Meeting commitments | Granola MCP | Relevant meetings from the last seven days: explicit commitments by Chris and unresolved decisions |
| Local meeting context | Obsidian | Relevant existing meeting snapshots when Granola is unavailable or local context is needed |
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.
- 6d ago Changed · +124 lines · +13 tokens per session fceeedeb5db1
- 19d ago First seen · 61 lines · 23 tokens per session scan A 9a2712e2927f
todays-focus is a skill published in the GitHub repository kriscard/Skills (15 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 2,036 once invoked, about $0.0001 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 2026-10-09.
Other skills, from other repositories
tfw-daily-task
Complete a bounded everyday request after project and purpose checks, preserving selected Trace and a checked result without a second planning approval.
world-time-get-{timezone}
Returns the current time for the given IANA timezone identifier. The timezone is supplied as a path parameter (e.g. America/NewYork, Europe/London, UTC).
skillsmith
Discover, install, compare, and manage Claude Code skills. Search the registry, get recommendations, validate skill quality, and manage your installed skills.
done
Summarize the current agent session, create an Obsidian note for it, and link it from today's daily note. Use when the user is finished with a session and wants to log what was accomplished.
weekly-review
Summarize the past week's daily notes, extracting key findings, links, action items, and potential atomic notes, and write the summary into the matching weekly note.
organize-inbox
Move notes from the Inbox to their respective folders based on their frontmatter category.