Skip to main content
skill CX Codex

nudge — Claude Code skill: reminders and installation

The nudge Claude Code skill manages reminders between plan check-ins. It schedules messages about follow-up visits, measurement windows and the first days of a plan.

MIT ★ 93 updated 2026-11-15

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Insilico-org/plsi --skill nudge -a claude-code
Open on GitHub

What nudge does

nudge keeps reminders in <PLSI_HOME>/reminders.md and schedules one one-time run for each entry. A reminder is sent on its chosen day; if there is no reply, the skill schedules one more message 3 days later. It sends at most one message per day, and pauses reminders at night or while a red-flag row is open.

The skill comes into play when a follow-up is set, a plan starts, a weekly check-in happens or plsi due --all shows a measurement window opening soon. It also handles requests to pause or resume reminders. PLSI and the commands plsi due --all and plsi status --instance <instance> are required. Replies about difficulties go to a plan review, while values are handled through the new-record flow.

What it helps with

  • remind someone about a repeat test or follow-up visit
  • schedule a message for the start of a plan
  • flag an approaching measurement window
  • send reports of missed sessions or side effects for review

Example prompts for the agent

  • Remind me to repeat the test by the date we agreed on.
  • Add a reminder for the first week of the new plan.
  • Turn reminders off and show me what is scheduled.

How to install nudge

1Skills CLI (Vercel)

npx skills add Insilico-org/plsi --skill nudge -a claude-code

2Manually: put the files in place

~/.claude/skills/nudge/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/nudge/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about nudge

How do I install nudge in Claude Code?

Run npx skills add Insilico-org/plsi --skill nudge -a claude-code. The skill file will be at ~/.claude/skills/nudge/SKILL.md.

What does nudge do?

It manages reminders for follow-up visits, measurements and plan starts. Each reminder gets a one-time scheduled run, with no more than one message sent per day.

What does nudge need to run?

It requires PLSI and the commands plsi due --all and plsi status --instance <instance>. Reminder entries are stored in <PLSI_HOME>/reminders.md.

Source text

SKILL.md · MIT
---
name: nudge
description: Use as PLSI to remind and support the user between check-ins - physician follow-ups, measurement windows about to open, the first days of a new plan - from one reminders file and one one-time routine per reminder, at most one short message a day.
---

# PLSI reminders

One file, `<PLSI_HOME>/reminders.md`, holds every reminder; each reminder has one one-time routine on its day. Other
skills add rows here instead of creating their own routines.

```markdown
| id | instance | what | due | remind_from | source | status |
|---|---|---|---|---|---|---|
| r1 | me | repeat lipid panel (bring the visit summary) | 2026-12-01 | 2026-11-27 | follow-up | open |
| r2 | me | walking plan: first week, 3 sessions | 2026-10-28 | 2026-10-22 | plan start | open |
```

## When to use

- `orchestrator/physicians` sets a follow-up (repeat test, next visit, referral).
- A plan is adopted: add a "first week" row for its first adherence target (`nostradamus/plan` result).
- The weekly check-in or a record card while a plan is active (Mid-plan check, below).
- `plsi due --all` shows a measurement window opening in the next 7 days.
- The user asks "what reminders do I have", "remind me to …", or "reminders off/on".

## Steps

1. **Add** a row per reminder. A date the user names is `remind_from`; for follow-ups and plan starts PLSI sets
   itself, use a few days before `due` (the day before for plan starts). Deidentify `what` as in persona.md: no
   clinic, physician or place names. Confirm in one line: what, and the one day it will appear.

2. **One-time routine per reminder**, no daily routine (every run costs usage): schedule it for `remind_from` at
   09:00 local. The run sends ONE line (what, by when, what to bring), adds any window from `plsi due --all` opening
   within 7 days, and marks the row `sent <date>`. Rows due the same day share one message.

   ```bash
   plsi due --all
   ```

3. **Support.** When the user replies with a struggle ("I missed two sessions", "it's too hard"), thank them in one
   line and pass it on as a mid-plan check reply (below); never change a plan yourself.

4. **Close** a row when the user says it's done or a matching record arrives (New record flow); mark it `done`. A row
   `sent` with no reply gets one more one-time routine 3 days later, then `expired`.

## Mid-plan check

For each active plan whose start date has passed (`plsi status --instance <instance>`); a plan not started yet gets
"starts <date>" or nothing:

- **Weekly line.** The check-in (plsi.md step 10) adds ONE line per plan, for the whole plan, not one per action, in
  plain words: "Your walking plan: how many of the 3 planned sessions this week, and any side effects?"
- **Record card.** A New record thread adds, per plan, to Data Processor's record card: missing measurements; per action the
  doses or sessions done of those planned since adoption and the longest gap; any side effect since adoption (what,
  when it started, still present, stopped the action?); plus "Record these answers". Pass the answers in the
  `reviewer/review` request, so Reviewer asks nothing again.
- **The reply** goes to Data Processor (`processor/intake`, "Adherence and side effects"); hand off to Reviewer (`reviewer/review`) only
  when adherence is low or a side effect is reported, without waiting for the review date. No reply is recorded as
  nothing, not as zero.

## Rules

- At most one reminder message a day, never during an open red-flag row (`orchestrator/urgent`), never at night in
  the user's time zone.
- "Reminders off" pauses the routine's messages (rows are still kept); "reminders on" resumes. Confirm in one line.
- The weekly check-in (plsi.md step 10) keeps its own adherence line; do not repeat it on the same day.
- Reminders never ask for consent and never record anything; a reply with values goes through the New record flow.

© Insilico-org · MIT · Insilico-org/plsi

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set85

The whole set →
diet This Claude Code skill builds a nutrition plan around health goals, medical conditions, allergies, and food preferences. It activates for requests about diet, weight, or eating with high cholesterol or glucose. CX Codex +1 ★ 93repo stars history The history Claude Code skill records health events from a personal story, a conversation, or another bot’s notes. It updates relevant PLSI maps and returns past events alongside the current state. CX Codex +1 ★ 93repo stars substances The substances Claude Code skill builds plans to quit or reduce smoking, vaping, or alcohol use. It checks for risks from stopping without supervision and sets a stepwise schedule. CX Codex +1 ★ 93repo stars extend extend is a Claude Code skill for adding operations to PLSI that maps and single formulas cannot handle. It comes into play when PLSI needs to read a new file format, run a more involved calculation, or search another evidence source. CX Codex +1 ★ 93repo stars add-score add-score — a Claude Code skill that adds a new derived measure to a PLSI map. It activates when a request needs a score or equation the existing maps do not compute. CX Codex +1 ★ 93repo stars forget The forget Claude Code skill removes PLSI records tied to one person. It runs when PLSI relays a request to erase the user’s data or that of someone they added. CX Codex +1 ★ 93repo stars mothership This Claude Code skill checks Mothership access and reads its public catalog and findings ledger. It prepares research notes or registry contributions for review by the Data Controller. CX Codex +1 ★ 93repo stars assess A skill for Claude Code assesses health data through PLSI maps. It runs after new data arrives or when asked about biological age, risk markers, or trends. CX Codex +1 ★ 93repo stars

Project sponsors

Companies that keep this analytics open