agentmods.dev

familiar

familiar is a command for Claude Code from yaniv-golan/claude-familiar. It costs 16 tokens per session (512 once invoked), scanned A, original, MIT.

A command interface for managing a virtual companion’s personality, mood, statistics, and backstory.

In plain words
What is it for?
Use it to view or change the companion’s personality and mood, inspect its statistics, and view or add lore.
Why use it?
It keeps these companion settings in one place instead of requiring separate commands for each kind of change.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Part of the familiar-extras plugin — 1 skill, 1 command, 5 hooks, 1 MCP server shipped together

not rated 2repo 5mo ago A scan 16 tokens original MIT

Good fit Use it to view or change the companion’s personality and mood, inspect its statistics, and view or add lore.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/yaniv-golan/claude-familiar/familiar
View source ↗ yaniv-golan/claude-familiar
Install

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.

Clone the repo
git clone --depth 1 https://github.com/yaniv-golan/claude-familiar

Made for: Claude Code.

Or install familiar-extras, the plugin that ships this one along with the rest of its 1 skill, 1 command, 5 hooks, 1 MCP server.

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 familiar

README.md
[![agentmods](https://agentmods.dev/badge/commands/yaniv-golan/claude-familiar/familiar/github.svg)](https://agentmods.dev/commands/yaniv-golan/claude-familiar/familiar)
Your own site
<a href="https://agentmods.dev/commands/yaniv-golan/claude-familiar/familiar"><img src="https://agentmods.dev/badge/commands/yaniv-golan/claude-familiar/familiar/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.

agentmods 80×15 button for familiar

Your own site · 80×15
<a href="https://agentmods.dev/commands/yaniv-golan/claude-familiar/familiar"><img src="https://agentmods.dev/badge/commands/yaniv-golan/claude-familiar/familiar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 512 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00016 $0.00512
Opus 5 $0.00008 $0.00256
Sonnet 5 $0.00003 $0.00102
Haiku 4.5 $0.00002 $0.00051

Measured 12d ago against content hash d3ac11190a73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

familiar 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 12d 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.

packages/familiar-extras/commands/familiar.md · 38 lines

What it actually says

Route this command to the correct familiar MCP tool based on the subcommand.

Subcommand: $1 | Arguments: $ARGUMENTS

Routing

personality (default when $1 is empty or "personality"):

  • No further args → call familiar-personality with no arguments (show mode)
  • $1 is "personality" and $2 is "reset" → call familiar-personality with reset: true
  • $1 is "personality" and $2+ is present → call familiar-personality with description set to everything after "personality" in $ARGUMENTS
  • $1 is missing entirely → call familiar-personality with no arguments (show mode)

mood (when $1 is "mood"):

  • No further args → call familiar-mood with no arguments (show current mood)
  • $2 is present → call familiar-mood with set = $2 (valid: cheerful, neutral, grumpy, excited, sleepy, chaotic)

stats (when $1 is "stats"):

  • Call familiar-stats with no arguments

lore (when $1 is "lore"):

  • No further args → call familiar-lore with no arguments (show all lore)
  • $2+ is present → call familiar-lore with add set to everything after "lore" in $ARGUMENTS

Unrecognized subcommand: If $1 doesn't match any of the above, tell the user the valid subcommands:

  • /familiar personality [description|reset] — show, change, or reset personality
  • /familiar mood [mood-name] — show or set mood
  • /familiar stats — show companion stats and history
  • /familiar lore [new entry text] — show or add backstory

Responding

These tools return context seeds — JSON with personality, mood, and an instruction field. Use that context to generate an in-character response. Consult the familiar-help skill for mood calibration and the full response pattern.

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. 12d ago First seen · 38 lines · 16 tokens per session scan A d3ac11190a73

Subscribe to this mod's changes

familiar is a command published in the GitHub repository yaniv-golan/claude-familiar (2 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 512 once invoked, about $0.0001 per session on Opus 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 2026-08-31.

Claude CodeCreative and mediaai-companionanthropicbunclaude-code-plugindeveloper-tools
Related

Other commands, from other repositories

ashlr-budget

Set, check, or clear a session spend cap. Guards against runaway tool use in long sessions.

ashlrai/ashlr-plugin · 24 tokens

ashlr-eco-mode

Toggle eco mode — aggressive token-saving behaviors that trade some response richness for lower session cost.

ashlrai/ashlr-plugin · 24 tokens

ashlr-parallelize

Spawn N parallel sub-agents — one per file — each applying the same task instruction. Merges results into a unified report.

ashlrai/ashlr-plugin · 32 tokens

ashlr-tour

60-second guided walkthrough of the ashlr-plugin on the current project — proves the value of the tools on real files.

ashlrai/ashlr-plugin · 29 tokens

goal

Create a goal, decompose it into milestones, and advance the next one as a sandboxed proposal-only run.

ashlrai/ashlr-plugin · 25 tokens

pin

Break checkpoint — status display, session log, optional MEMORY.md update.

gf-labs/claude-toolbox · 0 tokens