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 agentmods add skills/jtsternberg/claude-plugins/contactsnpx skills add jtsternberg/claude-plugins --skill contactsgit clone --depth 1 https://github.com/jtsternberg/claude-pluginsWrote 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/jtsternberg/claude-plugins/contacts)<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/contacts"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/contacts.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.01396 |
| Opus 5 | $0.00049 | $0.00698 |
| Sonnet 5 | $0.00020 | $0.00279 |
| Haiku 4.5 | $0.00010 | $0.00140 |
Grade A, and why
contacts 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 5d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contacts
A local address book for agent mail: humans and other agents, with the address, the role, and — the part that matters — how the address was verified.
Why this is a local file
AgentMail has no contacts resource. Checked three ways: zero hits for contact across the
82 paths in docs.agentmail.to/openapi.json, no contacts page in the docs index, and no
contacts resource in CLI 0.7.14.
The nearest native thing is Lists (lists, inboxes:lists) — send/receive/reply ×
allow/block ACLs whose entries are an address-or-domain plus an optional reason. No name,
no role, no notes. And they are a security control: writing one changes what the inbox is
allowed to talk to, so a "remove a contact" gesture would silently alter deliverability.
Don't use them as an address book. If the user asks to block or allow a sender, that
genuinely is Lists — a different job, covered in using-agentmail.
The store
${XDG_CONFIG_HOME:-$HOME/.config}/agentmail/contacts.json, mode 0600, beside the
state.json this plugin already writes.
Never in the repository. It holds personal addresses, and anything under a git worktree
is one git add -A from being published. The script derives its path from the environment
and takes no path flag, so there is nothing to point somewhere else by mistake.
Running it
# Codex: substitute the installed plugin directory for this path.
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT}"
bash "$PLUGIN_ROOT/scripts/agentmail-contacts.sh" list
Repeat that assignment in every block you run — Codex shells keep no state between blocks.
init create an empty store; never overwrites
list [--format json|text]
get <query> [--format json|text]
add --name N --email E [--kind human|agent] [--role R] [--notes T]
[--alias A]... [--verified-from V]
update <query> [any add flag]
remove <query> --yes
Exit codes, so you can branch without reading prose: 0 ok · 3 no match · 4 conflict
(duplicate address, ambiguous query, or init over an existing store — nothing is
written) · 5 store present but unparseable · 6 no python3 · 64 usage.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 111 lines · 99 tokens per session scan A bc1c0e19b7e8
contacts is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 1,396 once invoked, about $0.0005 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.