A command-line manager for Sentinel, a background service that watches corporate email and Telegram for urgent messages. It can start, stop, inspect, and configure the service.

Use it to check Sentinel's status, run it in the foreground or background, test it without sending notifications, and view logs.

It gives operators a controlled way to manage urgent-message monitoring instead of handling the daemon manually.

sentinel — Skill for Claude Code by mishahanin

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/mishahanin/heading-os

agentmods

npx agentmods add skills/mishahanin/heading-os/sentinel

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mishahanin/heading-os/sentinel/github.svg)](https://agentmods.dev/skills/mishahanin/heading-os/sentinel)

Your own site

<a href="https://agentmods.dev/skills/mishahanin/heading-os/sentinel"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/sentinel/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mishahanin/heading-os/sentinel"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/sentinel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,505 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 7
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.01505
Opus 5	$0.00030	$0.00753
Sonnet 5	$0.00012	$0.00301
Haiku 4.5	$0.00006	$0.00151

Measured 9d ago against content hash 62fb4ec6d16a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sentinel 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 9d 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.

.claude/skills/sentinel/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sentinel -- Unified Comms Monitor

Manage the Sentinel background daemon that monitors corporate email (Exchange) and Telegram for urgent messages.

Trigger

Activate when the user says "sentinel", "/sentinel", "start sentinel", or "stop sentinel". Also activate on "sentinel status", "check sentinel", "is sentinel running", and "comms monitor". Any question about the background monitoring system activates it too.

Actions

Parse the user's intent and run the appropriate command:

Default (no arguments / just "/sentinel")

Check status first. If Sentinel is already running, show the status. If it is NOT running, start it in daemon mode automatically, then show the status.

python scripts/sentinel.py --status
# If output says "NOT running" -> start daemon, then show status again:
python scripts/sentinel.py --daemon && python scripts/sentinel.py --status

Start Sentinel (foreground)

python scripts/sentinel.py

Start Sentinel (background/headless)

python scripts/sentinel.py --daemon

Test mode (single cycle, dry-run -- notifications are logged, never sent)

python scripts/sentinel.py --test

Check status

python scripts/sentinel.py --status

Stop daemon

python scripts/sentinel.py --stop

View recent logs

tail -50 .sentinel/sentinel.log

Edit configuration

Read and present the live config for editing. The real config is private instance data at <data-root>/config/sentinel_config.yaml (resolved via get_data_config_dir()); the engine ships scripts/sentinel_config.example.yaml as the template/fallback. On the transitional CEO workspace the data root is in-tree, so the live file is config/sentinel_config.yaml.

Configuration

Config file: config/sentinel_config.yaml (private data-config; engine fallback scripts/sentinel_config.example.yaml)

Key settings:

general.check_interval_minutes -- polling frequency (default: 15)
general.urgency_threshold -- minimum score to trigger notification (default: 7, scale 1-10)
email.vip_senders -- emails that always get elevated priority
email.ignore_patterns -- senders/patterns to skip entirely
telegram.monitored_chats -- specific groups/channels to watch
notification.dedup_cooldown_minutes -- do not repeat the same alert within N minutes (default: 60). Where alerts LAND is not a config key: they go out over the notifications bot to SENTINEL_TELEGRAM_TARGET (falling back to ODIN_CADENCE_TELEGRAM_TARGET) in .env.
digest.morning_time / digest.evening_time -- daily summary times (local TZ)
calendar.enabled -- enable meeting invite monitoring (default: true)
calendar.auto_accept -- auto-accept policy-compliant invites
calendar.auto_decline -- auto-decline non-compliant invites (non-VIP)
calendar.escalate_vip -- always escalate VIP/external senders
calendar.protected_blocks -- protected time windows from CEO Calendar Policy
calendar.day_themes -- weekly theme structure for topic alignment

Read the full file on GitHub · 152 lines

Files

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.

tests.md 915 B

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.

9d ago First seen · 152 lines · 61 tokens per session scan A 62fb4ec6d16a

Subscribe to this mod's changes

sentinel is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,505 once invoked, about $0.0003 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 2026-09-03.

Claude Code LLM Security ai-agent anthropic automation

sentinel