remind
Skill2 starsChanged 20 days agoMITView on GitHub
Use when the user says "/remind", "remind me to run X", "add that to my reminders", or when you hand them commands they must run themselves later (sudo, interactive login, another machine). Keeps a short checklist of commands with reasons in ~/remind.md; new chats surface due items automatically.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- seanx10m/skillstheir own version, first seen Nov 1, 2026
- KrishP147/skillstheir own version, first seen Nov 1, 2026
- davidondrej/skillstheir own version, first seen Oct 29, 2026
- sd0xdev/sd0x-dev-flowtheir own version, first seen Oct 8, 2026
- sd0xdev/sd0x-harnesstheir own version, first seen Oct 6, 2026
- zirkelc/agent-reminderstheir own version, first seen Aug 11, 2026
Used with
Projects with it also use deep-research.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
NVIDIASkilldeep-research
Queue deep, multi-step research and analysis tasks to the DeepAgents worker. Supports execution depth presets, request-specific rubrics, SubAgent delegation, and RubricMiddleware cross-validation.
Also in 3 projects that use this
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- davidondrej/skills★ 4.3ksame name
- sd0xdev/sd0x-dev-flow★ 192same name
- sd0xdev/sd0x-harness★ 192same name
- KrishP147/skills★ 37same name
- huanchong-99/PocketAide★ 9same name
- roeyw5/claude-code-guide★ 9same name
- sandst1/research-assistant★ 8same name
- rgr4y/claude-skill-remind★ 1same name
- seanx10m/skills★ 0same name
- zirkelc/agent-reminders★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- global/CLAUDE.mdCLAUDE.md
- black-octoberSkill
- branch-cascadeSkill
- build-orderSkill
- full-review-auditSkill
- meta-improveSkill
- newSkill
- pr-monitorSkill
- publish-mobile-appSkill
- reopen-prSkill
- research-spikeSkill
- setup-switch-loginSkill
- skill-syncSkill
- splice-youtube-quotesSkill
- switch-loginSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Create ~/remind.md with the # Reminders heading if it doesn't exist.
- Distinctive: line 35
When the session-start context lists open items that are due:
- Very specific: line 38
When an item needs more background than its reason gives, read the chat that added it: ~/github/skills/remind/scripts/log.sh <transcript …
- Very specific: line 39
If an item can be checked cheaply and without side effects (docker ps, ls, tailscale serve status), check first.
- Distinctive: line 42
Don't run reminded commands yourself unless the user asks: they're on the list because the user has to run them.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Remind
~/remind.md is the user's checklist of things to run on this machine. A SessionStart hook (the skill-sync skill) shows every new Claude Code or Codex chat the open items, so the reminder reaches the user wherever they open a chat next.
Format
Each item is two lines. The first is a checkbox, an optional due date, the command in backticks, a dash, then the reason in a few words. The second, indented, is the ctx: line that points back to the chat that added the item.
# Reminders
- [ ] 2026-10-14 `cd ~/github/opengym && sudo docker compose down --rmi all` — remove local openGym
- ctx: claude 379070e2-… · ~/.claude/projects/-home-…-opengym/379070e2-….jsonl · https://claude.ai/code/session_01… · resume: `cd ~/github/opengym && claude --resume 379070e2-…`- The command must be pasteable as is: include the
cdwhen it matters, and use absolute or~paths. - The reason is why to run it, not what it does.
- The date (
YYYY-MM-DD) means "don't remind before". "Tomorrow" is a real date, so compute it withdate -d tomorrow +%F. No date means remind at the next chat. - Several commands that must run in order become several items, in order.
- Never write the
ctx:line by hand. Generate it with~/github/skills/remind/scripts/ctx.sh, run from the chat's working directory. It works in Claude Code and Codex, and gives the session id, the transcript path, the Remote Control link when there is one, and the resume command. Items added in one batch share the same line.
Adding
- Create
~/remind.mdwith the# Remindersheading if it doesn't exist. - Append the items, each with its
ctx:line fromctx.sh. Never rewrite or reorder the user's existing lines. - Show the user the lines you added.
Reminding
When the session-start context lists open items that are due:
- In your first reply, list them one per line: the command and its reason. Then answer whatever the user asked.
- When an item needs more background than its reason gives, read the chat that added it:
~/github/skills/remind/scripts/log.sh <transcript path from the ctx line>prints that chat as plain conversation, in Claude Code or Codex format. Pass a second argument to cap each message's length (default 1500 characters). - If an item can be checked cheaply and without side effects (
docker ps,ls,tailscale serve status), check first. If it's already done, say so and offer to tick it. - Tick an item (
- [x]) only when the user says it's done or the check proves it. Delete ticked items older than a week when you're editing the file anyway.
Don't run reminded commands yourself unless the user asks: they're on the list because the user has to run them.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

