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 change-rollbackgit 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/change-rollback)<a href="https://agentmods.dev/skills/serac-labs/serac/change-rollback"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/change-rollback/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/change-rollback"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/change-rollback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 57 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00051 | $0.04978 |
| Opus 5.5 | $0.00020 | $0.01991 |
| Sonnet 5.5 | $0.00010 | $0.00996 |
| Haiku 4.5 | $0.00005 | $0.00498 |
Grade A, and why
change-rollback 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Undoing a Change on a ServiceNow Instance
You overwrote a Business Rule script, or a widget's server script, or a Script Include, and the new version is wrong. Do not reconstruct the old code from memory. The instance already kept a copy of the record as it was before you touched it, in the sys_update_version table. Recovering it is a read, a copy, and a write — no guessing.
The rest of this guide is about getting that read right, and about the three or four cases where no read will save you.
Which mechanism undoes what
| Mechanism | Undoes | Driven from |
|---|---|---|
Version records (sys_update_version) |
One configuration record, field by field | This MCP (read the payload, write the field back), or the UI's Revert to this version |
| Back out an update set | Every change captured in one committed update set, including dictionary changes | ServiceNow UI only — there is no tool for it here |
Deleted Records (System Definition > Deleted Records) |
One deleted record plus its cascaded deletes, on audited tables | ServiceNow UI only |
| Nothing | Emails already sent, flows already run, data destroyed by a dropped column | — |
Pick the smallest one that covers the damage. Reverting one field of one record is safe and boring. Backing out an update set touches everything in it.
Step 0: delete nothing
Two instincts are wrong and both are expensive.
Deleting the update set does not undo anything. sys_update_set is a container; the changes themselves are rows in sp_widget, sys_script, sys_script_include and friends, and the record of each change is a sys_update_xml row pointing at the set. Deleting the set record leaves every changed artifact exactly as it is, and destroys the only inventory of what changed — the inventory a real back-out needs. You are strictly worse off than before.
Deleting the artifact is not a rollback either. If the record existed before your change, deleting it turns a bad script into a missing script, plus every reference to its sys_id now dangles.
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 · 255 lines · 51 tokens per session scan A 89ae5a49c50e
change-rollback is a skill published in the GitHub repository serac-labs/serac (78 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 4,978 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-upgrade
Review ServiceNow upgrade readiness — the upgrade history, the skipped records an upgrade left unresolved, base vs customer versions of one skip, and store apps with an update. Use after a family or patch upgrade, before planning one, or when asked which skipped records to revert, keep or merge.
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.
triage
Diagnose and fix broken MCP servers in mcptoon — doctor, health, per-server probes, and the common failure playbook.
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.