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 table-api-readsgit 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/table-api-reads)<a href="https://agentmods.dev/skills/serac-labs/serac/table-api-reads"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/table-api-reads/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/table-api-reads"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/table-api-reads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00063 | $0.05208 |
| Opus 5 | $0.00032 | $0.02604 |
| Sonnet 5 | $0.00013 | $0.01042 |
| Haiku 4.5 | $0.00006 | $0.00521 |
Grade A, and why
table-api-reads 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 yesterday.
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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading Records Through the Table API
Almost every skill in this collection tells you to call snow_query_table. None of them tell you what
comes back. Three tools read the same record from /api/now/table/{table} and return three different
shapes with three different content policies, and the most-used of them reports a record total that was
never counted.
Read this before you make a decision based on field content you got out of a query — especially a script body, a description, a journal entry, or a total.
The three read tools at a glance
| What it does | snow_query_table |
snow_record_manage (get/query) |
snow_get_by_sysid |
|---|---|---|---|
sysparm_display_value |
false unless you ask |
all unless you pass display_value: false |
false unless you ask |
| Reference fields | {link, value} objects |
query: {display_value, value}, no link. get: {display_value, link, value} |
{link, value} objects |
| Every other field | plain string | {display_value, value} object |
plain string |
| Long values | truncated at 200 chars by default | never truncated | never truncated |
sys_id |
always injected into sysparm_fields |
only if you ask for it | not injected — absent from the record if you pass fields without it |
Fields when you omit fields |
all of them | a hardcoded preset subset | all of them |
| Record total | a guess | real, from X-Total-Count |
n/a |
The rest of this guide is why each cell says what it says.
snow_query_table truncates, and the marker is easy to miss
truncate_output defaults to true. With it on, every field whose value is a string longer than 200
characters is checked — nothing at or under 200 is ever touched, whatever it is called:
- If the field name contains any of
template,script,server_script,client_script,css,html,xml,json,payload,body,content,description,comments,work_notes,additional_comments,close_notes,resolution_notes,instructions,short_description,long_description— it is cut at 200 characters. - Otherwise, if the value is longer than 400 characters, it is cut at 200 anyway.
- Otherwise it comes through whole.
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.
- yesterday First seen · 359 lines · 63 tokens per session scan A 709ca9b5af9b
table-api-reads is a skill published in the GitHub repository serac-labs/serac (78 stars, last pushed yesterday), licensed Apache-2.0. It adds 63 tokens to every session and 5,208 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 2026-09-11.
Other skills, from other repositories
manage
CRUD operations on the knowledge base — add, delete, update metadata. For bulk ingest / re-ingest / prune, use /gnosis:ingest instead. Requires GNOSISMCPWRITABLE=true.
status
Verify gnosis-mcp server connectivity, schema integrity, and corpus health. Use when MCP calls fail, return empty, or return unexpected data.
misata
Generate realistic multi-table test data, seed a development database, or build fixtures whose joins and totals actually hold. Use when the user needs test data, sample data, demo data, seed data, fixtures, a populated dev/staging database, or a relational dataset shaped to specific numbers (a revenue curve, a churn…
axiom-core-data-diag
Use when debugging schema migration crashes, concurrency thread-confinement errors, N+1 query performance, SwiftData to Core Data bridging, or testing migrations without data loss - systematic Core Data diagnostics with safety-first migration patterns.
axiom-swiftdata-migration
Use when creating SwiftData custom schema migrations with VersionedSchema and SchemaMigrationPlan - property type changes, relationship preservation (one-to-many, many-to-many), the willMigrate/didMigrate limitation, two-stage migration patterns, and testing migrations on real devices.
axiom-swiftdata
Use when working with SwiftData - @Model definitions, @Query in SwiftUI, @Relationship macros, ModelContext patterns, CloudKit integration, iOS 26+ features, and Swift 6 concurrency with @MainActor — Apple's native persistence framework.