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 sentdm/sent-plugin --skill sent-contactsgit clone --depth 1 https://github.com/sentdm/sent-pluginWrote 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/sentdm/sent-plugin/sent-contacts)<a href="https://agentmods.dev/skills/sentdm/sent-plugin/sent-contacts"><img src="https://agentmods.dev/badge/skills/sentdm/sent-plugin/sent-contacts/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/sentdm/sent-plugin/sent-contacts"><img src="https://agentmods.dev/badge/skills/sentdm/sent-plugin/sent-contacts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00075 | $0.00766 |
| Opus 5.5 | $0.00030 | $0.00306 |
| Sonnet 5.5 | $0.00015 | $0.00153 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
sent-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 17d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sent Contacts
Operate contacts with contacts.list, contacts.get, contacts.create_many, contacts.delete, and contacts.message_summary.
Establish connection and scope
Use client-managed OAuth 2.1/PKCE. Never request or expose a token, API key, authorization header, client ID, or secret. Before a mutation, surface the active organization and Sender Profile from the connection context; if either is unavailable, use sent-account-readiness to inspect the authorized scope.
Mask phone numbers where practical. Return only the contact fields needed for the task, and do not repeat contact data after it has been reviewed. Number presence or messaging history does not establish consent.
An organization grant may select an owned Sender Profile with the tool schema's optional profileId; omit it to act as the authenticated account. Validate ownership with sender_profiles.list or sender_profiles.get, and use the same selector for preflight reads, mutations, and follow-up reads. Profile grants cannot use this selector. Reauthorize for a different organization or a profile outside the grant. Never invent scope fields or request credentials.
Read contacts
- Use
contacts.listto search or page through contacts. Apply the narrowest available filter and do not dump an entire contact book unnecessarily. - Use
contacts.getwhen an exact contact identifier is known or before a delete. - Use
contacts.message_summaryfor the contact's messaging summary. Distinguish summary data from proof of consent or current reachability.
Read-only calls do not require mutation confirmation.
Create contacts in bulk
- Validate and deduplicate the proposed records locally. Preserve only fields the user actually supplied.
- Build the exact
contacts.create_manyarguments without calling the tool. - Show a payload preview with the selected organization, Sender Profile, record count, duplicate handling, and each exact target. Mask phone numbers where the operator can still verify them; reveal full values once only when exact verification requires it.
- Ask for explicit confirmation for this exact batch. Earlier or general approval is not sufficient.
- Call
contacts.create_manyimmediately after confirmation. Any change to the records or scope invalidates confirmation.
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.
- 17d ago Changed · +2 lines 5de417fe3892
- 1mo ago First seen · 47 lines · 75 tokens per session scan A 0ef8d10c5f28
sent-contacts is a skill published in the GitHub repository sentdm/sent-plugin (51 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 766 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
zoom
Zoom video conferencing platform - lets an agent retrieve meeting metadata, participant lists, cloud recording URLs, and auto-generated transcripts to support meeting intelligence workflows.
slack
Slack team messaging platform - lets an agent post messages, send direct messages, read channel history, and deliver notifications into employee workflows.
workflow_mapper
Workflow integration mapper — inventory your daily tools, map workflows, discover Enso integration opportunities, and build automation rules to eliminate friction.
meal_planner
Comprehensive meal planning with weekly scheduling, shopping lists, nutrition tracking, pantry management, and meal suggestions.
world_clock
World clock, timezone converter, countdown timers, and stopwatch utilities.
youtube_manager
YouTube Manager: subscription management, personalized feed, trending, AI-powered channel discovery, analytics, bulk cleanup.