Agent skill · AI & Agents

mode-creator

Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram alerts, bot setup, worker restart, and startup-context verification. Use this whenever someone asks to customize what claude-mem remembers, create or change a mode, track domain-specific notes, add observation types or tags, or send Telegram notifications for particular memories—even if they do not use the word "mode.

Alex Newman88,857★ · +719/wk · 1 repos on radarProfile →
claude-codeships scriptsApache-2.0
Install
npx skills add thedotmack/claude-mem --skill mode-creator --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 6
SKILL.md size: 9 KB
Bundled scripts: yes
Requires: Requires a local claude-mem worker installation, an interactive question tool, filesystem access, and Node.js 20+.…
Path: plugin/skills/mode-creator/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 89,517 · +660 this week
Language: JavaScript
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Mode Creator Create a useful note-taking system, not merely a valid JSON file. Interview the user, propose a small taxonomy, obtain approval, install it durably, configure optional alerts, restart the worker, and prove the active mode appears in startup context. ## Ground rules - Use the available interactive question tool (`AskUserQuestion`, `request_user_input`, or equivalent) for the interview. Ask in small batches and wait for each response. - Explain observation types as mutually exclusive kinds of notes and concepts as reusable tags. Avoid jargon unless the user uses it first. - Inspect existing bundled and user modes before inventing a new one. Reuse or remix a close match when that serves the user better. - Do not edit a plugin cache or bundled mode. Install custom files under the resolved claude-mem data directory's `modes/` folder. - Do not expose a Telegram token in chat, command arguments, logs, or tool output. Treat it like a password. - Preserve unrelated settings and existing Telegram triggers. The helpers make timestamped backups and merge requested triggers. - Custom modes are supported by the local worker runtime. If `CLAUDE_MEM_RUNTIME` is `server`, explain tha

What's inside
Steps it walks through
  1. Ground rules
  2. 1. Open with the purpose
  3. 2. Discover what is worth remembering
  4. 3. Propose the mode
  5. 4. Ask about Telegram alerts
  6. 5. Draft, validate, and install
  7. 6. Connect Telegram when needed
  8. 7. Restart and prove the result
  9. 8. Hand off clearly
Ships with 5 files
  • evals/evals.json
  • references/mode-authoring.md
  • references/telegram.md
  • scripts/configure-telegram.mjs
  • scripts/install-mode.mjs
Commands it runs
node <skill-directory>/scripts/install-mode.mjs \
node <skill-directory>/scripts/configure-telegram.mjs \
npx claude-mem restart
npx claude-mem status
More from claude-mem
All skills →
About this skill
What does the mode-creator skill do?

Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram alerts, bot setup, worker restart, and startup-context verification. Use this whenever someone asks to customize what claude-mem remembers, create or change a mode, track domain-specific notes, add observation types or tags, or send Telegram notifications for particular memories—even if they do not use the word "mode.

How do I install it?

Run `npx skills add thedotmack/claude-mem --skill mode-creator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From thedotmack/claude-mem, a repository with 89,517 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going