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 mostafa-drz/claude-skills --skill one-thing-todaygit clone --depth 1 https://github.com/mostafa-drz/claude-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/mostafa-drz/claude-skills/one-thing-today)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/one-thing-today"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/one-thing-today/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/mostafa-drz/claude-skills/one-thing-today"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/one-thing-today.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 | $0.00053 | $0.03229 |
| Opus 5.5 | $0.00021 | $0.01292 |
| Sonnet 5.5 | $0.00011 | $0.00646 |
| Haiku 4.5 | $0.00005 | $0.00323 |
Grade A, and why
one-thing-today 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 26d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One thing today
Getting 1% better every day beats a perfect plan that never starts. This skill reads what you've connected and what Claude remembers about you, then gives you one thing for today: what it is, why it's the one, and how to start in the next 25 minutes. It works for any part of life: work, personal, health, family, learning, a side project. Everything else can wait, and the page says so.
It starts automatically when the request matches: "what's my one thing today?", "one thing for personal life today", "I'm overwhelmed, where do I start?". It's not for a full day plan, a to-do list or a schedule.
One reference, read it every run: choosing.md (gather,
pick, write, learn). Data shape: evals/example-focus.json.
Defaults: Configuration, at the end of this file.
The flow
Focus progress:
- [ ] 0. Settings: the chat, then saved settings in memory, then Configuration
- [ ] 1. Area: which part of life this run is for
- [ ] 2. Gather: the area's sources + memory + past chats (+ last focus, same area)
- [ ] 3. Pick one (choosing.md), and write why with evidence
- [ ] 4. Write focus.json → validate → render → show the page
- [ ] 5. Learn: save what changed, in one line
0. Settings
Look in memory for the line starting "one-thing-today settings:". What the user says in this chat wins, then the saved settings, then Configuration. A saved "skip Slack" holds until the user changes it; the "never assume a source" rule below is about what's connected, not about preferences.
1. Area
The area is free text (work, personal, health, family, side project…), or
all. Resolve it in this order: the request ("my one thing for personal life"), the
scheduled task's instruction, a saved day rule ("Sat–Sun: personal"), then all.
The area decides three things: which sources are read (the saved area map, for example
work = Gmail (work), Slack, Linear), which candidates can win, and what goes on the
page. On a personal page, nothing from work appears, not even under Can wait or in
the sources footer. With no map saved, use judgement: a work Slack isn't personal, a
family calendar isn't work. Say which sources you counted as the area in the closing line,
and offer to save the map.
What ships with it
9 files 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.
- 26d ago First seen · 249 lines · 53 tokens per session scan A fc011ffe9acc
one-thing-today is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed 20d ago), licensed MIT. It adds 53 tokens to every session and 3,229 once invoked, about $0.0002 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 2026-09-25.
Other skills, from other repositories
agency-multi-brand-pack
Per-client asset templates scoped by workspace.
hydra
Fan multiple independent tasks out to SEPARATE Terminal.app windows, each running its own live claude session with exactly the context it needs — real parallel sessions with isolated context windows, not subagents. Confirms grouping/model/risk with the user before launching, delivers context invisibly, auto-tiles…
application-pack
Turns one pasted job post into an application folder built only from the student's own career vault: a tailored resume, a cover letter under 250 words, and an HR call sheet with the answers already drafted. Reads career-vault/01 to 06 first and refuses to run while the positioning, portfolio story or resume are still…
shipkit-work-memory
Log session progress and save resume state. Infers from conversation and git. Triggers: 'log progress', 'session summary', 'checkpoint', 'save progress', 'end session'.
session-update
Use when the user says "update session", "log progress", "checkpoint session", or invokes /session-update — especially before /clear or handoff.
sounding-board
Use when a user needs to vent, talk something out, or just not feel like they're shouting into a void. Active listening with gentle reflection — not therapy, not silence, just a friend who pays attention.