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 agentmods add skills/serac-labs/serac/background-script-executionnpx skills add serac-labs/serac --skill background-script-executiongit clone --depth 1 https://github.com/serac-labs/seracWhat 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 | $0.00054 | $0.04707 |
| Opus 5 | $0.00027 | $0.02354 |
| Sonnet 5 | $0.00011 | $0.00941 |
| Haiku 4.5 | $0.00005 | $0.00471 |
Grade A, and why
background-script-execution 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 2d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Background Script Execution
snow_execute_script is the most-recommended tool in this catalog and the least explained. It does not use ServiceNow's Scripts - Background module. It ships its own transport, and knowing which of two paths your call took is the difference between reading a real result and reading a placeholder.
The two paths
| Sync path | Fallback path | |
|---|---|---|
metadata.method |
sync_rest_api |
sysauto_script_with_trigger, or scheduled_job_pending |
| How it runs | POST to a Scripted REST endpoint Serac installed; the operation evaluates your script inline and returns the result in the HTTP response | Creates a sysauto_script job plus a sys_trigger row set to fire two seconds out, then polls sys_properties for a marker the job writes when it finishes |
| Typical latency | 1–3s | 4s to the full timeout (default 30s) |
| You get output | Yes, in the response | Only if the poll caught the marker before it gave up |
Every call tries the sync path first. It falls back the moment the sync POST does not return a usable body — and that includes the case where your script ran and threw, because the endpoint answers a thrown script with HTTP 500 and the client treats any non-2xx as "endpoint didn't work". So a script with a bug in it can be executed up to three times: once by the sync POST, once by the retry after the endpoint is re-verified, once by the scheduled job. Assume a failing script is not executed exactly once, and never let a script that mutates data be the thing you debug through this tool. Get it right in a read-only form first.
The endpoint Serac installs
The first call against an instance deploys a Scripted REST API. Two records, both created through the Table API:
| Record | Table | Key values |
|---|---|---|
| Definition | sys_ws_definition |
name = Serac Script Executor, service_id = snow_flow_exec, active = true |
| Operation | sys_ws_operation |
name = Execute Script, http_method = POST, relative_path = /execute, requires_authentication = true |
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.
- 2d ago First seen · 230 lines · 54 tokens per session scan A 201cc09191df
background-script-execution is a skill published in the GitHub repository serac-labs/serac (78 stars, last pushed 7d ago), licensed Apache-2.0. It adds 54 tokens to every session and 4,707 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 2026-08-30.
Other skills, from other repositories
xcodebuildmcp-structured-output-review
Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…
tabnexus-mcp-evals
Generate, validate, and run isolated Codex-to-TabNexus MCP evaluations with a curated 600-query dataset, executable gold tool labels, safety checks, and best-of-three stability scoring. Use when testing TabNexus MCP tool coverage, Agent behavior, regression quality, destructive-action safety, prompt changes, or a…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
daily-task-prep
Morning preparation. Calendar lookahead, meeting context loading, open threads from yesterday, active task review. Extends briefing with actionable prep.