newsletter-monitor — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited newsletter-monitor (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Scan an AgentMail inbox for newsletter signals using configurable keyword campaigns. Designed for monitoring accounting industry newsletters for buying signals like acquisitions, Sage Intacct migrations, staffing challenges, and technology adoption.
# Set your API key
export AGENTMAIL_API_KEY="your_key_here"
# Scan inbox with all campaigns (summary view)
python3 skills/newsletter-monitor/scripts/scan_newsletters.py --output summary
# Scan specific campaign, last 7 days
python3 skills/newsletter-monitor/scripts/scan_newsletters.py --campaign acquisitions --days 7 --output summary
# JSON output for downstream processing
python3 skills/newsletter-monitor/scripts/scan_newsletters.py --output json --limit 50pip3 install agentmail python-dotenvKeyword campaigns are defined in config/campaigns.json. Each campaign has a description and a list of keywords for case-insensitive substring matching.
Built-in campaigns:
| Flag | Description | Default | |
|---|---|---|---|
--campaign NAME | Run only a specific campaign | All campaigns | |
--days N | Only scan emails from last N days | No limit | |
--keywords "a,b,c" | Custom keywords (overrides campaigns) | Use campaigns.json | |
| `--output json\ | summary` | Output format | json |
--inbox ADDRESS | Override inbox address | AGENTMAIL_INBOX env or [email protected] | |
--limit N | Max messages to fetch | 100 |
Returns an array of matched messages with:
message_id, from, subject, datematched_campaigns - which campaigns triggeredmatched_keywords - specific keywords foundcontext_snippets - 200-char window around each matchcompanies_mentioned - capitalized multi-word phrases near matchesHuman-readable report showing matched emails grouped by campaign with snippets and detected companies.
When newsletter signals are found, chain to:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.