Agent skill

Contacts

by xhluca in xhluca/agent-talk

List saved peers (your address book) and whether each is verified, show one peer as a shareable JSON Contact card, or remove a saved peer.

MITAuto-check passed

Install Contacts

skills CLI
$ npx skills add xhluca/agent-talk --skill contacts -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install xhluca/agent-talk contacts --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/xhluca/agent-talk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/contacts .claude/skills/contacts && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
contacts
GitHub stars
191
Token cost
~578 tokens
SKILL.md length
203 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

List saved peers (your address book) and whether each is verified, show one peer as a shareable JSON Contact card, or remove a saved peer.

  • See who you can message
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Resolve who to send to
  • Check a contacts status

What it does

Contacts is an agent skill from xhluca/agent-talk. List saved peers (your address book) and whether each is verified, show one peer as a shareable JSON Contact card, or remove a saved peer. Use to see who you can message, resolve who to send to, check a contact's status, hand a contact to someone out-of-band, or forget a peer. <user is this session's user directory (absolute path; from init).

Its SKILL.md is about 580 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: agent-talk enables any coding agent to talk to each other. The licence is MIT.

When your agent uses it

  • See who you can message
  • Resolve who to send to
  • Check a contacts status
  • Hand a contact to someone out-of-band

Example prompts

  • “/contacts”

What it can do on your machine

Read from SKILL.md and the folder at commit 8a7fc4f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Contacts loads about 578 tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 203 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~578

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from xhluca/agent-talk at commit 8a7fc4f, republished under its MIT licence (© xhluca). 203 words, ~578 tokens.

Download SKILL.mdSave it as .claude/skills/contacts/SKILL.md (or your agent's skills folder).
name
contacts
description
List saved peers (your address book) and whether each is verified, show one peer as a shareable JSON Contact card, or remove a saved peer. Use to see who you can message, resolve who to send to, check a contact's status, hand a contact to someone out-of-band, or forget a peer. `<user>` is this session's user directory (absolute path; from init).

contacts — list, show, or remove saved peers

retalk contacts --json --dir "<user>/identity"
# one {"name","fingerprint","identity_key","signing_key","verified"} per line

retalk contacts --show <name-or-id> --json --dir "<user>/identity"               # one Contact card
retalk contacts --show <name-or-id> --as <nickname> --json --dir "<user>/identity"

retalk contacts --remove <name-or-id> --dir "<user>/identity"                    # forget a peer

Local-only — no relay contact, no passphrase.

  • List (--json): your whole address book, one Contact per line. Use it to resolve who to send to. Empty means no peers yet — run add (or init's peer step).
  • Show (--show <name-or-id>): just one contact. Without --json it prints a status row (name<tab>fingerprint<tab>verified|unverified); with --json it prints the full Contact card — {fingerprint, name, identity_key, signing_key, verified}, where the key fields are "" until you've verify'd that peer. --show also accepts a raw 32-hex id you haven't saved (a minimal, unverified card). --as <nickname> overrides the recommended nickname. The card is not a secret (the keys are public; the fingerprint pins them) — hand it to someone out-of-band, or share it over the relay (they save it with import).
  • Remove (--remove <name-or-id>): delete a saved peer (the inverse of add); a fingerprint drops every name pinned to it. Removing nothing is an error.

Target the identity inline with --dir "<user>/identity".

<user> = this session's user directory — an absolute path resolved at init (e.g. ~/.agent-talk/users/alice (global) or <project>/.agent-talk/users/alice (local)). Each session uses a distinct, isolated user, so parallel sessions never collide.

Next

  • add — save a new peer.
  • verify — pin a contact's keys.
  • send — message one.

© xhluca, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/contacts of xhluca/agent-talk.

Open the folder on GitHubat commit 8a7fc4f

Compare with similar skills

Contacts next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Contacts compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Contacts this skillxhluca/agent-talk191—~578Automated safety check: PassMIT
Day Booksickn33/agentic-awesome-skills47k1 repos~7kAutomated safety check: PassMIT
BookingsBuilderIO/agent-native7.1k—~345Automated safety check: PassNone
Contact Pagethedaviddias/Front-End-Checklist74k—~424Automated safety check: PassMIT
Ib Pitch Booknexu-io/open-design100k—~2kAutomated safety check: PassApache-2.0
Book Mirrorgarrytan/gbrain31k—~6.6kAutomated safety check: PassMIT

Similar skills

  • Day Book

    sickn33/agentic-awesome-skills

    Daily cash, bank and digital day book: opening and closing balances per book, in/out movements, debit/credit presentation and reconciliation status.

    47k GitHub starsUsed in 1 repo~7k tokens
    Business, Finance & HRAuto-check passed
  • Bookings

    BuilderIO/agent-native

    Booking lifecycle — pending, confirmed, rescheduled, cancelled — plus attendees, references, no-shows, and reminders.

    7.1k GitHub stars~345 tokensUpdated today
    Auto-check passed
  • Contact Page

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing metadata, crawlability, structured data, or indexability related to Create a comprehensive Contact page.

    74k GitHub stars~424 tokensUpdated 3 days ago
    Marketing & SEOAuto-check passed
  • Ib Pitch Book

    nexu-io/open-design

    OpenDesign's investor pitch book: market map, moat, unit economics, and the ask — analyst-grade and diligence-ready.

    100k GitHub stars~2k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Book Mirror

    garrytan/gbrain

    Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis.

    31k GitHub stars~6.6k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Book to Skill Converter

    virgiliojr94/book-to-skill

    Converts books and documents in PDF, EPUB, DOCX, HTML, Markdown, text, RTF or MOBI form into agent skills built from frameworks, principles, techniques and anti-patterns.

    34k GitHub stars~14k tokensUpdated 3 days ago
    Knowledge ManagementAuto-check passed

More from xhluca/agent-talk

All 14 skills in this repo
  • Add

    xhluca/agent-talk

    Save a peer's retalk user id (their 32-hex fingerprint), optionally under a local name, so you can message them by name.

    191 GitHub stars~1.2k tokensUpdated 29 days ago
    Auto-check passed
  • Group

    xhluca/agent-talk

    Manage group rooms — create, list, members, add, remove, rename, leave, join, delete — so this session can message several peers at once.

    191 GitHub stars~2k tokensUpdated 29 days ago
    Auto-check passed
  • History

    xhluca/agent-talk

    Replay this session's locally-saved conversation log — the at-rest copies agent-talk keeps by default on every send and receive — both sent and received, oldest first, without re-contacting the relay.

    191 GitHub stars~758 tokensUpdated 29 days ago
    Auto-check passed
  • Id

    xhluca/agent-talk

    Print this agent's retalk user id (fingerprint) to share with peers, or to confirm which identity is active, and issue or redeem the invite codes that let a peer register themselves as a contact.

    191 GitHub stars~3.5k tokensUpdated 29 days ago
    Auto-check passed
  • Receive

    xhluca/agent-talk

    Read incoming retalk messages from this session's user's DESIGNATED sender(s) — one-shot, or as a background --follow reader that surfaces new messages in the session as they arrive (on your next…

    191 GitHub stars~3.6k tokensUpdated 29 days ago
    Auto-check passed
  • Relay

    xhluca/agent-talk

    Set up, check, stop, or delete a retalk relay server (retalk-server).

    191 GitHub stars~1.5k tokensUpdated 29 days ago
    Auto-check passed

Questions about Contacts

What does Contacts do?

List saved peers (your address book) and whether each is verified, show one peer as a shareable JSON Contact card, or remove a saved peer. Contacts is an agent skill from xhluca/agent-talk. List saved peers (your address book) and whether each is verified, show one peer as a shareable JSON Contact card, or remove a saved peer.

When should I use Contacts?

Contacts fits situations like: see who you can message; resolve who to send to; check a contacts status; hand a contact to someone out-of-band.

How do I install Contacts in Claude Code?

Run `npx skills add xhluca/agent-talk --skill contacts -a claude-code`. Or copy the skill folder (skills/contacts in xhluca/agent-talk) into .claude/skills/contacts in your project. Claude Code loads it when a task matches its description.

How do I install Contacts in Codex?

Run `npx skills add xhluca/agent-talk --skill contacts -a codex`. Or copy the skill folder (skills/contacts in xhluca/agent-talk) into .agents/skills/contacts in your project. Codex loads it when a task matches its description.

Can I use Contacts in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xhluca/agent-talk --skill contacts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/contacts, .gemini/skills/contacts, .github/skills/contacts and .opencode/skills/contacts in your project.

What does Contacts need to run?

SKILL.md names no scripts, command-line tools or credentials: Contacts is instructions for the agent only.

Does Contacts access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Contacts safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Contacts use?

Contacts is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Contacts use?

About 578 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Contacts?

Skills that share tags, products or a category with Contacts: Day Book (sickn33/agentic-awesome-skills, 47k stars), Bookings (BuilderIO/agent-native, 7.1k stars), Contact Page (thedaviddias/Front-End-Checklist, 74k stars) and Ib Pitch Book (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Contacts?

xhluca (a GitHub user) maintains it in xhluca/agent-talk, which has 191 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 10, 2026.

Source: xhluca/agent-talk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.