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 vikram-karety/ServiceNow --skill servicenow-code-reviewgit clone --depth 1 https://github.com/vikram-karety/ServiceNowWrote 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/vikram-karety/servicenow/servicenow-code-review)<a href="https://agentmods.dev/skills/vikram-karety/servicenow/servicenow-code-review"><img src="https://agentmods.dev/badge/skills/vikram-karety/servicenow/servicenow-code-review/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/vikram-karety/servicenow/servicenow-code-review"><img src="https://agentmods.dev/badge/skills/vikram-karety/servicenow/servicenow-code-review.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 | $0.00220 | $0.02340 |
| Opus 5 | $0.00110 | $0.01170 |
| Sonnet 5 | $0.00044 | $0.00468 |
| Haiku 4.5 | $0.00022 | $0.00234 |
Grade A, and why
servicenow-code-review 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 11d 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.
ServiceNow engineering: write, review, complete, debug, find-missing
Work ServiceNow code the way a platform architect would, and always keep the platform's defining trap in mind: the silent no-op. Broken code here rarely throws — it compiles to nothing (Rhino reserved keys), renders to nothing (Jelly eats ${}), lands in the wrong scope, matches the wrong record, or silently drops a misspelled field. "It ran and printed nothing" usually means it never ran at all. Whatever you are doing — writing, reviewing, fixing — prove the code actually ran and acted on the right data.
Step 0: Pick the mode
Detect what the user wants and follow that mode's workflow. When unstated, default to review.
| Mode | Trigger | Workflow |
|---|---|---|
| review | "review / audit / check / harden this" | Steps 1→2→3→4 below (the default) |
| author | "write / build / scaffold an X that does Y" | Step 1 (context) → author from references/authoring-patterns.md → Step 2 (lint your output) → author self-check |
| complete | "finish / complete this stub", partial code | Step 1 → identify the intended pattern in authoring-patterns.md → complete to that shape → Step 2 |
| debug | "it's broken / not firing / blank / errors / slow / not saving" | references/debugging.md: symptom → make the silence talk → hypothesis → root cause → fix + confirm |
| find-missing | "what's missing / what did I forget / is this complete" | Step 1 → run the completeness lens: each matched reference's own checklist plus Step 3's four questions, read as "what SHOULD be here and isn't" |
All modes share Step 1 (classify by context), Step 2 (lint), and the four platform questions (Step 3). Authoring, completion, and find-missing all lean on references/authoring-patterns.md for the canonical correct shape; debugging leans on references/debugging.md.
Step 1: Classify by execution context
Every judgment depends on execution context. The same line can be correct in one context and fatal in another (document.getElementById is fine in a UI Page, banned in a Service Portal client script; a template literal is fine in a widget's Angular controller, fatal inside a sys_ui_page.client_script). Identify the context(s) and read the matching reference(s) — each carries a METHOD and checklist, not just smells:
What ships with it
12 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.
- README.md 4.2 KB
- references/authoring-patterns.md 14 KB
- references/client-side.md 6.0 KB
- references/debugging.md 7.7 KB
- references/integrations-deploy.md 11 KB
- references/more-script-types.md 12 KB
- references/performance-analytics.md 5.5 KB
- references/security-acl.md 7.1 KB
- references/server-side.md 15 KB
- references/service-portal.md 6.4 KB
- references/ui-pages-jelly.md 6.4 KB
- scripts/sn-lint.js 23 KB runs code
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.
- 11d ago First seen · 89 lines · 220 tokens per session scan A 0f30ba2af0e6
servicenow-code-review is a skill published in the GitHub repository vikram-karety/ServiceNow (0 stars, last pushed 1mo ago), licensed MIT. It adds 220 tokens to every session and 2,340 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
platform-apex-generate
Primary Apex authoring skill for class generation, refactoring, and review. ALWAYS ACTIVATE when the user mentions Apex, .cls, triggers, or asks to create/refactor a class (service, selector, domain, batch, queueable, schedulable, invocable, DTO, utility, interface, abstract, exception, REST resource). Use this skill…
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
api-contract-review
Use when auditing CloudBase cloud API wrappers, MCP tools, generated action metadata, or related docs for outdated or incorrect action names, parameters, casing, request shapes, or missing contract tests, especially during periodic quality review or before preparing corrective PRs.
principle-model-the-domain
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.
api-reviewer
A review of an API contract, the agreed description of how software systems exchange requests, responses, events, or files.