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.
npx skills add yaniv-golan/claude-familiar --skill familiar-helpgit clone --depth 1 https://github.com/yaniv-golan/claude-familiarWrote 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.
[](https://agentmods.dev/skills/yaniv-golan/claude-familiar/familiar-help)<a href="https://agentmods.dev/skills/yaniv-golan/claude-familiar/familiar-help"><img src="https://agentmods.dev/badge/skills/yaniv-golan/claude-familiar/familiar-help/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.
<a href="https://agentmods.dev/skills/yaniv-golan/claude-familiar/familiar-help"><img src="https://agentmods.dev/badge/skills/yaniv-golan/claude-familiar/familiar-help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00161 | $0.02388 |
| Opus 5 | $0.00081 | $0.01194 |
| Sonnet 5 | $0.00032 | $0.00478 |
| Haiku 4.5 | $0.00016 | $0.00239 |
Grade A, and why
familiar-help 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Familiar Companion Tools
You have access to tools that let the user's companion interact creatively. Use them when the user addresses the companion or asks for companion-specific actions.
The companion can be referred to in several ways — treat all of these as equivalent triggers:
- By Anthropic's UI label: "buddy" (this is what Claude Code's own interface calls it)
- By the companion's assigned name: e.g. "Cragwise", "Pip" — whatever name Claude Code assigned. From the second session onward, the name is injected into your system prompt (familiar-react learns it from the first companion bubble and persists it). If it appears in your context, you can use it with certainty. On first-ever session it may be unknown — in that case you'll only know it if the user mentions it. You cannot change the name (it is set by Claude Code, not familiar-sdk).
- By role: "familiar", "companion", "my familiar", "the companion"
Intent → Tool Mapping
| User says something like... | Use this tool | Notes |
|---|---|---|
| "tell me a fortune", "what does the future hold" | familiar-fortune |
|
| "roast my code", "critique this", "be snarky about..." | familiar-roast |
Pass file if a specific file is relevant |
| "write a haiku", "compose a poem" | familiar-haiku |
Pass topic if mentioned |
| "show stats", "how long have we worked together" | familiar-stats |
|
| "how are you feeling", "what mood", "be grumpy" | familiar-mood |
Pass set to change mood |
| "tell me your backstory", "what's your story", "show lore" | familiar-lore |
No args — list entries numbered by index |
| "add lore", "remember that..." | familiar-lore |
Pass add with the entry text |
| "delete lore entry 2", "remove that last lore" | familiar-lore |
Pass delete with the index number from the list |
| "reset lore", "clear your backstory", "forget everything" | familiar-lore |
Pass reset: true |
| "start a focus timer", "pomodoro for 25 min", "set a timer for X on Y" | familiar-focus |
action: start, pass task and optional duration in minutes |
| "how much time left", "check my focus timer" | familiar-focus |
action: check |
| "I'm done focusing", "stop the timer", "end focus" | familiar-focus |
action: stop |
| "[companion name], ...", "hey buddy, ..." (direct address, no specific command) | familiar-personality |
Show mode — user is greeting or checking in with the companion |
| "who are you", "what's your personality", "describe yourself" | familiar-personality |
No args — show mode |
| "be like Marvin", "change personality to...", "act like a pirate" | familiar-personality |
Pass description, optionally mood |
| "reset your personality", "go back to normal" | familiar-personality |
Pass reset: true |
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.
- 11d ago First seen · 166 lines · 161 tokens per session scan A 89f5e7660509
familiar-help is a skill published in the GitHub repository yaniv-golan/claude-familiar (2 stars, last pushed 5mo ago), licensed MIT. It adds 161 tokens to every session and 2,388 once invoked, about $0.0008 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.
Other skills, from other repositories
ashlr-lean-tools
Highest-impact token-saving habits for Claude Code tool use. Read-once, batch edits, orient-before-search, skip verification reads, grep-before-read, concise output at high spend. Reduces session token cost 30–60%.
mode-interactive
The interactive implementation posture (/foundry:mode-interactive) — the default lean direct loop. The operator drives edit→verify→merge in one accountable context; the operator reviews the diff at the merge button (the Regular-mode segregation). Sibling of mode-autonomous; they differ ONLY at the two ends (who paces…
img-pilot
AI-generated brand assets (logo, favicon, social, banner, icons) from Claude Code. Reads ux-pilot and brand-pilot briefs automatically. 9 providers, cost-optimized.
image-upload
Grab an image from the clipboard and analyze it. Use when the user says image upload, paste, screenshot, clipboard, or asks to look at something they copied.
memstack-content-youtube-script
Use this skill when the user says 'YouTube script', 'video script', 'write script for YouTube', 'YouTube video outline', or is creating scripted content for a YouTube video with hooks, chapters, and CTAs. Do NOT use for TikTok/Reels short-form scripts or webinar presentations.
slides
A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.