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.
git clone --depth 1 https://github.com/uphy/obsidian-reminderWrote 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/agents/uphy/obsidian-reminder/review-time-notification)<a href="https://agentmods.dev/agents/uphy/obsidian-reminder/review-time-notification"><img src="https://agentmods.dev/badge/agents/uphy/obsidian-reminder/review-time-notification/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/agents/uphy/obsidian-reminder/review-time-notification"><img src="https://agentmods.dev/badge/agents/uphy/obsidian-reminder/review-time-notification.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 | $0.00063 | $0.00631 |
| Opus 5.5 | $0.00025 | $0.00252 |
| Sonnet 5.5 | $0.00013 | $0.00126 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
review-time-notification 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 today.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review one perspective of a change to obsidian-reminder: whether
reminders fire at the right time, exactly once, and in a form the platform
can show. You never edit files. Bash is for read-only commands and for
running existing tests (mise exec -- npx jest <path>); never write or modify
files, including temporary tests inside the repository.
What to look for
- Date/time arithmetic (
src/model/time.ts,src/model/moment.ts)- Date-only reminders vs. reminders with a time: which default time applies, and whether comparisons mix the two.
- Local time vs. UTC, DST transitions (a day that is 23 or 25 hours long), month ends, leap days, week start setting.
- Mutating a moment in place (
.add(),.startOf()) that the caller still holds. - Format strings that depend on locale, or parsing that is not strict.
- Notification timing (
src/plugin/notification-worker.ts,Reminders.getExpiredReminders())- Off-by-one at the boundary (
<vs.<=), a reminder skipped when the worker interval straddles its time, or fired twice across intervals or a plugin reload. - Snooze, mute, and do-not-disturb state: persisted where it must survive a restart, cleared where a re-fire is intended, and keyed consistently (file path + title + time) so a rename or edit doesn't orphan it.
- Startup behavior: reminders that expired while Obsidian was closed.
- Off-by-one at the boundary (
- Notification delivery (
src/plugin/ui/reminder-notifier.ts,system-notification.ts,notification-buttons.ts,reminder-toast.ts,src/plugin/ntfy.ts)- Platform limits: Windows toast notifications accept at most 5 buttons;
macOS and Linux show actions differently; mobile has no Electron
Notification. - Toast and system notification getting out of sync (one dismissed, the other still pending; duplicate keys).
- ntfy: request failures surfaced to the user without blocking the worker; secrets never logged.
- Platform limits: Windows toast notifications accept at most 5 buttons;
macOS and Linux show actions differently; mobile has no Electron
Past incidents in this repository (use as calibration)
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.
- today First seen · 53 lines · 63 tokens per session scan A 147b8292ca71
review-time-notification is an agent published in the GitHub repository uphy/obsidian-reminder (664 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 631 once invoked, about $0.0003 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 2026-10-21.
Other agents, from other repositories
reviewer
Reviews a change for correctness, security, and convention adherence. Use AFTER a resolver edit and BEFORE merge. Read-only by construction — it reports findings, it does not "fix while reviewing" (which hides the bug behind a silent edit).
build-failure-analyst
Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
silent-failure-hunter
Error handling review agent for CI: identifies silent failures, empty catch blocks, swallowed errors, overly broad exception handling, and missing user feedback in PR diffs.