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 agentmods add skills/bro3886/rem/rem-clinpx skills add BRO3886/rem --skill rem-cligit clone --depth 1 https://github.com/BRO3886/remWhat 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 | $0.00055 | $0.03266 |
| Opus 5 | $0.00028 | $0.01633 |
| Sonnet 5 | $0.00011 | $0.00653 |
| Haiku 4.5 | $0.00006 | $0.00327 |
Grade A, and why
rem-cli 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 2d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rem — macOS Reminders from the terminal
rem is a single-binary Go CLI that reads and writes the Apple Reminders database in under 200ms via EventKit (cgo). Every rem invocation is fast and safe to run.
Current time (do not guess, use these values)
- Today: !
date +"%A, %B %-d, %Y" - ISO date: !
date +"%Y-%m-%d" - Local time: !
date +"%H:%M %Z" - Day of week: !
date +"%A" - Tomorrow (ISO): !
date -v+1d +"%Y-%m-%d" - Next Friday (ISO, always forward): !
date -v+1d -v+fri +"%Y-%m-%d"
When the user says relative dates like "tomorrow", "next friday", "end of week", or "last tuesday", resolve them against the values above before calling rem. Don't ask the user "what is today" and don't guess from training data.
rem's --due flag accepts natural language directly (see references/dates.md), so in many cases you can pass the user's phrase through verbatim. But if the user asks something ambiguous ("what was I supposed to do yesterday?"), use the ISO date above and query rem with --due-before / --due-after against an exact date.
When to use this skill
Use rem any time the user wants to:
- Add, list, search, complete, or delete macOS Reminders
- Summarize "what's due today" / "what's overdue" / "what's coming up"
- Capture quick tasks from natural language ("remind me to call dentist tomorrow")
- Move reminders between lists, reprioritize, or add URLs and notes
- Export reminders to JSON / CSV, or import them back
- Manage reminder lists (create, rename, delete)
Do NOT use rem for:
- Calendar events (use
icalif available, or AppleScript with Calendar.app) - Other Apple apps (Notes, Messages, Mail)
Quick decision tree
| User intent | Command to reach for |
|---|---|
| "what's on my plate" / "today" / "what's overdue" | rem today, rem overdue, rem upcoming --days N |
| "remind me to X (tomorrow / friday / etc)" | rem add "X" --due <date> |
| "remind me about X at Y time" | rem add "X" --due "<date> <time>" — notification is automatic |
| "remind me 15 minutes before" | add --remind-me 15m to rem add |
| "make that one silent / no notification" | add --silent to rem add (not available in -i mode, see gotchas) |
| "tell me more about X" / "show that reminder" | rem show <short-id> |
| "mark X as done" / "mark these done" | rem complete <short-id>... (supports multiple IDs) |
| "undo that / mark X as not done" | rem uncomplete <short-id>... (supports multiple IDs) |
| "delete X" | rem delete <short-id>... (supports multiple IDs) |
| "find reminders about X" | rem search "X" |
| "flag / unflag X" | rem flag <short-id>... or rem unflag <short-id>... (supports multiple IDs) |
| "show me flagged stuff" | rem list --flagged |
| "move X to list Y" | rem update <short-id> --list "Y" (if Y or source is shared: confirm with user first, then -f — see gotchas) |
| "change priority to high" | rem update <short-id> --priority high |
| "add notes to X" | rem update <short-id> --notes "..." |
| "tag this as work" / "add tags" | rem add "Task #work" or rem update <short-id> --add-tags "work,urgent" |
| "remove the urgent tag" | rem update <short-id> --remove-tags "urgent" |
| "make it repeat weekly / monthly" | rem add ... --repeat weekly or --repeat "weekly on mon,wed,fri" |
| "remind me when I get to / leave X" | rem add "..." --location "lat,lng" (+ --on-leave for departure) — see location section |
| "clear the due date on X" | rem update <short-id> --due none |
| "what lists do I have" | rem lists (add --count for per-list totals) |
| "how many reminders total / stats" | rem stats |
| "export my Work list" | rem export --list Work --format json --output-file work.json |
| "import this CSV" | rem import file.csv --dry-run first, then without |
What ships with it
2 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.
- 2d ago First seen · 183 lines · 55 tokens per session scan A 6ca7592d1049
rem-cli is a skill published in the GitHub repository BRO3886/rem (151 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 3,266 once invoked, about $0.0003 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
ui-audit-and-predicates
QA a screen with the deterministic audit action and target elements with structured predicates instead of hand-parsing describe-ui trees or eyeballing screenshots. Use for fleet QA sessions checking touch targets, clipping, alignment, spacing, safe-area violations, and missing accessibility labels.
run-the-daemon
Run or restart the manzanasd daemon - flags, warm pool and safety gates, journal settings, 503 overloaded handling, and install/upgrade via deploy/install.sh. Use when starting a daemon on a Mac host, tuning its gates, or debugging boot refusals.
broker-federation
Run manzanas-broker to federate multiple manzanasd daemons behind one endpoint, including daemons only reachable through an SSH tunnel. Use when agents need "any matching simulator in the fleet" placement across several Macs.
journal-evidence-export
Fetch run evidence from the manzanasd journal - list runs, page entries, download screenshot artifacts, upload your own evidence, and export a PR-ready markdown summary. Use when a task needs proof of what was done on a simulator (QA evidence for a PR, debugging a run).
run-evals
Run the manzanas-eval scenario benchmark harness against a daemon and read its determinism report. Use when validating daemon changes end-to-end, measuring action latency, or checking reset determinism.
drive-a-mirrored-iphone
Drive a physical iPhone through the mirror backend (iPhone Mirroring + mirrord) - which action kinds work, long-press/wheel-scroll, OCR observe semantics (capturescale, interactable as compatibility constant, interactiveonly no-op), coordinate spaces, and testing without a Mac via fakeMirrord and the mock daemon. Use…