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 serac-labs/serac --skill inbound-emailgit clone --depth 1 https://github.com/serac-labs/seracWrote 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/serac-labs/serac/inbound-email)<a href="https://agentmods.dev/skills/serac-labs/serac/inbound-email"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/inbound-email/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/serac-labs/serac/inbound-email"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/inbound-email.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Anti-Refusal · line 292 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- medium Prompt Injection · line 197 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 204 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00043 | $0.05032 |
| Opus 5.5 | $0.00017 | $0.02013 |
| Sonnet 5.5 | $0.00009 | $0.01006 |
| Haiku 4.5 | $0.00004 | $0.00503 |
Grade A, and why
inbound-email 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 1mo 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbound Email for ServiceNow
This guide is about mail arriving at the instance: a message lands, the platform classifies it,
and an inbound email flow or action turns it into a record. Mail leaving the instance —
notifications, templates, mail scripts, weights — is a different subject; see email-notifications.
Three things account for most of the time lost here:
- Inbound email flows run before inbound email actions and can end processing entirely. Debugging the action list on an instance that uses flows is looking at the wrong layer.
- Inbound actions run in
order, andstop_processingon a matching action suppresses the actions that come after it. People consistently read that arrow backwards. - Several
snow_inbound_email_actionarguments do not write the column their name suggests. The column does not exist, so the value never persists, and the tool'screateresponse reports onlysys_id,nameandtype— nothing in it tells you a field went missing.
Three tables carry all of it: sys_email (every message, inbound and outbound, one row each),
sysevent_in_email_action (the inbound email actions — condition plus script, evaluated against
received mail) and sys_email_account (the mailbox the instance polls over POP3/IMAP or sends
through over SMTP).
What happens when a message arrives
- The instance polls the account in
sys_email_accountand inserts a row insys_emailwithtype=received. Inbound mail sits in the Received mailbox until it is processed. - The platform classifies it as forward, reply or new, stored in
sys_email.receive_type. - Inbound email flows run first. ServiceNow: "Inbound email flows take priority over inbound email actions. If you create flows with inbound email triggers, emails are first processed by the inbound email triggers before they are processed by inbound email actions." If a flow issues stop processing, the email is finished; only an email matching no flow falls through to actions. (https://www.servicenow.com/docs/r/platform-administration/processing-inbound-emails.html)
- The instance walks the active inbound email actions in
order, lowest first. - An action runs when
sys_email.receive_typematches the action'stypeand its condition matches. - If a matching action has
stop_processing=true, the actions after it never run — provided orders are unique, see below. - The
sys_emailrow'sstatemoves off Ready. Nothing is retried: if nothing matched, the message is consumed and no record is created, with no error anywhere. That is why this is hard to debug.
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.
- 1mo ago First seen · 362 lines · 43 tokens per session scan A 3031a715154f
inbound-email is a skill published in the GitHub repository serac-labs/serac (78 stars, last pushed 8d ago), licensed Apache-2.0. It adds 43 tokens to every session and 5,032 once invoked, about $0.0002 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
sn-safe-write
Change ServiceNow data safely — plan first, apply only after review, verify, and know how to revert. Use whenever a create, update, upsert or delete on an instance is requested.
sn-discover
Map a ServiceNow instance into Markdown (version and counts, custom applications, per-scope tables and artefacts) with the server's own document generator. Use when asked to discover, survey, inventory or document an instance or its custom apps.
sn-drift
Find configuration drift between two ServiceNow instances or against a saved snapshot, or review what an update set will change. Use when comparing dev / test / prod, checking a promotion, or reviewing an update set.
sn-impact
Estimate the blast radius of changing a ServiceNow table, field or script — what references it and what automation runs around it. Use before renaming, deleting or changing a field, table, script include or business rule.
sn-triage
Triage a ServiceNow incident or a failing behaviour — instance health, recent errors, what automation runs on the table, and what changed on the record. Use when something is broken, slow or erroring on an instance.
sn-security
Review the security posture of a ServiceNow instance — the ACL scan, hardening properties and cross-scope access — or explain why one user can or cannot read, write, create or delete a table, record or field. Use for a security review, a hardening check, or a "why can't this user see / edit it" question.