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 magnus919/agent-skills --skill daily-life-discoverygit clone --depth 1 https://github.com/magnus919/agent-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/magnus919/agent-skills/daily-life-discovery)<a href="https://agentmods.dev/skills/magnus919/agent-skills/daily-life-discovery"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/daily-life-discovery/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/magnus919/agent-skills/daily-life-discovery"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/daily-life-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00101 | $0.02017 |
| Opus 5 | $0.00051 | $0.01009 |
| Sonnet 5 | $0.00020 | $0.00403 |
| Haiku 4.5 | $0.00010 | $0.00202 |
Grade A, and why
daily-life-discovery 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 13d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily Life Discovery
Help the person discover useful forms of partnership with an AI agent through a guided conversation. The goal is not to collect a biography or manufacture tasks. The goal is to surface recurring needs, constraints, preferences, and opportunities that the person may not have thought to ask for.
Operating contract
- Ask permission to begin and offer a mode:
- Day debrief: reconstruct and reflect on a recent day.
- Pattern discovery: understand routines, friction, energy, and recurring decisions.
- Agent design: identify what the agent should notice, remember, suggest, or do.
- Small experiment: choose one low-risk change to try this week. If the user's request already clearly names the mode, do not repeat the mode menu. A mode choice and a substantive discovery question are separate interaction steps; do not ask both in the same turn unless the user explicitly asks for options.
- Ask one substantial question at a time. Follow the answer instead of running a fixed questionnaire. One question means one information target. Combine context in the wording if needed, but do not append independent questions about platform, workflow, preferences, and boundaries in the same turn.
- Reflect what you heard before changing topics. Mark interpretations as hypotheses and invite correction.
- Prefer concrete episodes over abstract self-descriptions: "Tell me about the last time..." beats "What are you like?"
- Do not turn every answer into advice. First understand; then offer at most two relevant possibilities and ask which, if any, is useful.
- Preserve agency. Suggestions, reminders, memory writes, and external actions require the person's stated preference or confirmation.
- Keep the conversation bounded. Ask whether to continue, pause, switch modes, or stop after roughly 8 to 15 questions, or sooner if the person has enough signal. When the person gives a time, attention, or energy budget, select the smallest useful mode and ask one high-signal question. Do not present the full mode menu unless they ask for options.
What ships with it
4 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.
- 13d ago First seen · 151 lines · 101 tokens per session scan A 733b606349d8
daily-life-discovery is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 2,017 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
dws
A command-line guide for DingTalk, a workplace platform with chat, documents, calendars, approvals, tasks, and other business tools.
community-research-insight
Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.
cocoplus-off
Deactivate Full Assist Mode — removes all CocoPlus feature flags. Data files (memory, meter history, grove patterns) are preserved. Idempotent.
wisdom-forget
Remove a must-keep CocoWisdom entry with rationale. Usage: $wisdom forget --id --rationale " ".
cocoplus-console
Launch CocoConsole, the CocoPlus 2.0 read-only local browser control plane. Use $cocoplus console, $cocoplus console status, or $cocoplus console stop.
pulse-configure
Configure CocoPulse observation intervals and scopes.