Agent Scripts is a repository of shared instructions, reusable skills, helper scripts, and local safeguards for coding-agent workflows across multiple workspaces. It is for maintaining common agent behavior and portable development utilities between repositories.
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 steipete/agent-scripts --skill remindersgit clone --depth 1 https://github.com/steipete/agent-scriptsWrote 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/steipete/agent-scripts/reminders)<a href="https://agentmods.dev/skills/steipete/agent-scripts/reminders"><img src="https://agentmods.dev/badge/skills/steipete/agent-scripts/reminders/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/steipete/agent-scripts/reminders"><img src="https://agentmods.dev/badge/skills/steipete/agent-scripts/reminders.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 | $0.00022 | $0.00708 |
| Opus 5.5 | $0.00009 | $0.00283 |
| Sonnet 5.5 | $0.00004 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
reminders 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- reminders — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reminders
Use this for Apple Reminders tasks. Prefer rem over Things/AppleScript when
the user wants an AI-friendly personal todo backend on macOS.
Tool
- CLI:
rem - Repo:
https://github.com/BRO3886/rem - Install:
GOBIN=/opt/homebrew/bin go install github.com/BRO3886/rem/cmd/rem@latest
rem uses EventKit for normal reads/writes. It may need Reminders permission for
the calling app in System Settings > Privacy & Security.
Start
Check access:
rem lists -o json
rem today -o json
Use JSON for anything scripted or verified:
rem list --incomplete -o json
rem search "flight" -o json
rem show <id> -o json
Add Tasks
Default: add directly, then verify by search/show.
rem add "Book LHR-SFO nonstop business flight" --due "tomorrow 9am" --priority high --notes "Nonstop only." -o json
rem search "LHR-SFO" -o json
Useful flags:
--list "Name": target list--due "tomorrow 9am": due date/time; natural language is supported--priority high|medium|low|none--notes "text"--url https://...--silent: due date without notification--remind-me 15m: alarm before due time--repeat daily|weekly|monthly|yearly
Update / Complete / Delete
Find the UUID first, then mutate by id or unique short id:
rem search "flight" -o json
rem update <id> --name "New title" --due "friday 2pm" --notes "..." -o json
rem complete <id> -o json
rem delete <id> --force
Always read back after writes; do not trust exit status alone.
Lists
rem lists --count -o json
rem list-mgmt create "Travel"
rem list-mgmt rename "Old" "New"
rem list-mgmt delete "Name" --force
Conventions
- Use executable task titles. Rewrite vague notes into the next concrete action.
- Preserve user wording when they clearly want verbatim capture.
- Split multiple unrelated actions into separate reminders.
- Use the default list unless the user names a list or the category is obvious.
- Do not add calendar events here; use calendar tooling instead.
- For current date math, run
date; do not guess.
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 · 102 lines · 22 tokens per session scan A 99274f991fc7
reminders is a skill published in the GitHub repository steipete/agent-scripts (7,379 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 708 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…