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.
git clone --depth 1 https://github.com/leopu00/job-hunter-teamnpx agentmods add skills/leopu00/job-hunter-team/email-monitorWrote 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/leopu00/job-hunter-team/email-monitor)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/email-monitor"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/email-monitor/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/leopu00/job-hunter-team/email-monitor"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/email-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00116 | $0.01225 |
| Opus 5 | $0.00058 | $0.00613 |
| Sonnet 5 | $0.00023 | $0.00245 |
| Haiku 4.5 | $0.00012 | $0.00122 |
Grade A, and why
email-monitor 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 12d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
email-monitor — reading forwarded job alerts, at day start
The user creates a dedicated email address (e.g. [email protected]) and
sets up forwarding rules in their own client that send us the job alerts
(LinkedIn, Glassdoor, Indeed and any other platform that notifies by mail).
You read that mailbox and turn the alerts into positions. It is the most
accurate source (the alert is already filtered on the target by the user) and
the most token-cheap one (no blind scraping).
📍 Optional but recommended. If it is not configured, the team works as before (web sourcing). Nothing is blocked.
When
- At the start of the work window (day-start): read the email BEFORE web scraping. Overnight alerts are already there.
- Then at most every ~30 min (the IMAP server rate-limits beyond that, and new alerts do not arrive more often). Do not poll more frequently.
- Claim the source in STEP 0 (
scout-coord):scout_workspace.py claim <agent> email:<box>— one Scout only per mailbox, no collisions.
Procedure
1. Is it configured?
python3 /app/shared/skills/email_monitor.py status
configured=false → the mailbox is not there: skip, do normal web sourcing.
any_platform=true means we process the entire dedicated inbox (no narrow
from_filters) → every sender the user forwards gets read.
2. Estimate the VOLUME (cheap, no body fetch)
python3 /app/shared/skills/email_monitor.py count
Returns new_total + by_sender. It tells you and the Captain whether this
is a manageable volume or a flood. On a flood, the Captain (C-16) tells you
how many / which ones to ingest: the goal is that positions reach a score,
not to pile up 200 that are never evaluated.
3. Poll → leads
python3 /app/shared/skills/email_monitor.py poll --since-days 1
Every JSONL line is a lead: {"url","source","subject","sender","received_at"}.
source=linkedin-email/glassdoor-email/indeed-emailfor the known providers,email:<domain>for any other platform (generic extraction).- Idempotency (Message-ID in
state/email_monitor_seen.json) guarantees that a re-run does not reprocess the same alerts.
What ships with it
6 files 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.
- 12d ago First seen · 89 lines · 116 tokens per session scan A 6e27203eeb79
email-monitor is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 1,225 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-researcher
Organize research — manage references, notes, and collaboration.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
recipe-review-meet-participants
Review who attended a Google Meet conference and for how long.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
recipe-draft-email-from-doc
Read content from a Google Doc and use it as the body of a Gmail message.