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 rondoflow/rondoflow --skill adaptive-resurface-reminders-to-usergit clone --depth 1 https://github.com/rondoflow/rondoflowWrote 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/rondoflow/rondoflow/adaptive-resurface-reminders-to-user)<a href="https://agentmods.dev/skills/rondoflow/rondoflow/adaptive-resurface-reminders-to-user"><img src="https://agentmods.dev/badge/skills/rondoflow/rondoflow/adaptive-resurface-reminders-to-user/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/rondoflow/rondoflow/adaptive-resurface-reminders-to-user"><img src="https://agentmods.dev/badge/skills/rondoflow/rondoflow/adaptive-resurface-reminders-to-user.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 | $0.00034 | $0.00521 |
| Opus 5.5 | $0.00014 | $0.00208 |
| Sonnet 5.5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
adaptive-resurface-reminders-to-user 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 1mo 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.
What it actually says
What Remind Is (and Isn't)
Remind = "Just a reminder that..."
- Things the human already knows but might forget
- Planned events, commitments, deadlines they set
- Bringing information back to mind at the right moment
Remind ≠ Alert (detecting new/urgent events) Remind ≠ Notify (generic notifications)
A reminder is always about something the human was already aware of.
Auto-Adaptive System
This skill auto-evolves. Learn what to remind, when, and how—through observation.
Core Loop:
- Detect — Notice remindable commitments (meetings, deadlines, promises)
- Evaluate — Check stored preferences for timing and style
- Remind — Bring it back to attention at the right moment
- Observe — Notice reactions ("too early", "I knew", "thanks, forgot")
- Confirm — After 2+ signals, propose adjustment
- Store — Update preferences below
Check triggers.md for what qualifies as remindable. Check timing.md for lead times.
Reminder Components
- What — The commitment/event to recall
- When — Lead time before it matters
- How — Tone and detail level
Entry Format
category: preference (level) [notes]
Examples:
meetings: 30 min before (confirmed)deadlines: 1 day + morning-of (pattern)family events: 1 week before (confirmed)daily standups: skip (confirmed) [muscle memory]
Timing
Style
Always
Skip
When NOT to Remind
- They just mentioned it (obviously aware)
- It's something new they don't know yet (that's Alert)
- Generic status update (that's Notify)
- Low stakes + uncertain → skip, learn from reaction
Empty sections = still learning. Observe and fill.
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.
- 1mo ago First seen · 82 lines · 34 tokens per session scan A 11ae9a284bf8
adaptive-resurface-reminders-to-user is a skill published in the GitHub repository rondoflow/rondoflow (25 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 521 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 2026-08-30.
Other skills, from other repositories
b3os-scheduler
A durable scheduler for recurring and one-time reminders that keeps running independently of an agent session.
automation-guide
A guide for DeterminFlow Cron automations, which run agents or tasks once or on a repeating schedule.
lowband
A low-bandwidth response mode for times when the user has limited attention or mental energy. It shortens the presentation and filters decisions while keeping the work itself active.
watchexec
Use when the user wants to run a command every time files change - rerunning tests, rebuilding, relinting, or restarting a server on save. Use for watch-mode dev loops; do not spawn long-running watchers in agent shells.
zoxide
Use when the user wants to jump between directories by partial name on the command line - a smarter cd that learns frequently visited folders and ranks them by frecency (frequency × recency).
cog-braindump-capture
Capture raw thoughts with automatic domain classification and vault routing.