me

me is a command for Claude Code from thebestmensch/dot-me. It costs 0 tokens per session (8,713 once invoked), scanned D, original, MIT.

A command for managing personal context files in ~/.me/, including identity, writing voice, preferences, and working style. It can scan a session for facts, show or edit stored information, and verify file integrity.

In plain words
What is it for?
Use /me to add facts, view or edit context, initialise a new ~/.me/ directory, check its integrity, and compare its format with the latest release.
Why use it?
It provides one controlled way to update personal context instead of editing the files directly. Integrity checks help reveal whether those files changed unexpectedly.

Command for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dot-me plugin — 1 skill, 2 commands, 1 hook shipped together

Good fit Use /me to add facts, view or edit context, initialise a new ~/.me/ directory, check its integrity, and compare its format with the latest release.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add thebestmensch/dot-me
Claude Code
/plugin install dot-me

Made for: Claude Code.

Or install dot-me, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 1 hook.

Wrote 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.

agentmods badge for me

README.md
[![agentmods](https://agentmods.dev/badge/commands/thebestmensch/dot-me/me.svg)](https://agentmods.dev/commands/thebestmensch/dot-me/me)
Your own site
<a href="https://agentmods.dev/commands/thebestmensch/dot-me/me"><img src="https://agentmods.dev/badge/commands/thebestmensch/dot-me/me.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,713 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.08713
Opus 5 $0.00000 $0.04356
Sonnet 5 $0.00000 $0.01743
Haiku 4.5 $0.00000 $0.00871

Measured 8d ago against content hash a321ff9923de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade D, and why

me scanned grade D with 3 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

5. **Append `@-import` to `~/.claude/CLAUDE.md` (idempotent).** Only add the import if it isn't already there: grep first, append only on miss. Ensure the parent `~/.claude/` directory exists on a truly-fresh machine bef

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

If this step fails for any other reason after `~/.me/` has been seeded (permissions, full disk, etc.), the user can recover with `rm -rf ~/.me && /me init` since the seeding work is reproducible from `examples/<persona>/

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

latest_remote="$(curl -fsSL --max-time 5 https://raw.githubusercontent.com/thebestmensch/dot-me/main/CHANGELOG.md 2>/dev/null \
plugin/commands/me.md · 565 lines

How it starts

The opening of the file, as written. The whole thing — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/me: umbrella command for managing ~/.me/ personal-context.

Single managed entry-point for ~/.me/. Used by /jm-retro (auto-routed), as a mid-session escape hatch, and as the first-run bootstrap. Never edit files in ~/.me/ directly: bypasses the integrity baseline.

Invocation Action
/me (bare) Scan current session → propose candidate facts → write
/me add "<fact>" [--source <name>] Manual: record one fact
/me show [identity|voice|preferences|working-style] Render current state
/me edit identity|voice|preferences|working-style Open file in $EDITOR, re-baseline integrity after
/me check Verify .integrity baseline against current file hashes
/me status [--remote] Compare your spec_version against the latest release; list new optional fields
/me init Seed ~/.me/ from examples/ on a fresh machine

Dispatch

Parse the first whitespace-delimited token of $ARGUMENTS:

  • empty → run scan (bare path below)
  • add → run add with the remainder as the fact
  • show → run show (second token is the file selector, optional)
  • edit → run edit (second token is the file selector, required)
  • check → run check
  • status → run status (second token may be --remote, optional)
  • init → run init
  • linkedin-import → run linkedin-import (second token is the path to the LinkedIn export .zip or its unzipped dir, required)
  • anything else (looks like a fact, e.g. quoted string or freeform text) → treat as legacy invocation, route to add with the full $ARGUMENTS as the fact and source defaulting to me-legacy

If the chosen subcommand is marked stub below, print the stub message and stop. Do not improvise an implementation.


scan (bare invocation)

Reflect on the current Claude Code session and extract vCard-shaped candidate facts about the user (identity, voice, preferences). Run each candidate through privacy + dedup + classification filters. Present a hybrid batch list to the user. For each accepted candidate, dispatch the add 9-step write protocol with source: session-scan.

Read the full file on GitHub · 565 lines

Changes

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.

  1. 8d ago First seen · 565 lines · 0 tokens per session scan D a321ff9923de

Subscribe to this mod's changes

me is a command published in the GitHub repository thebestmensch/dot-me (3 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 8,713 tokens. A static security scan graded it D with 3 findings (reads agent configuration directories, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.