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 nyaomaru/is-kit --skill use-is-kitgit clone --depth 1 https://github.com/nyaomaru/is-kitWrote 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/nyaomaru/is-kit/use-is-kit)<a href="https://agentmods.dev/skills/nyaomaru/is-kit/use-is-kit"><img src="https://agentmods.dev/badge/skills/nyaomaru/is-kit/use-is-kit/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/nyaomaru/is-kit/use-is-kit"><img src="https://agentmods.dev/badge/skills/nyaomaru/is-kit/use-is-kit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.00858 |
| Opus 5 | $0.00043 | $0.00429 |
| Sonnet 5 | $0.00017 | $0.00172 |
| Haiku 4.5 | $0.00009 | $0.00086 |
Grade A, and why
use-is-kit 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 7d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use is-kit
Build runtime checks that preserve TypeScript control-flow narrowing without inventing project architecture or duplicating guards that already exist.
1. Inspect before editing
- Read the repository instructions and relevant package scripts.
- Confirm the installed
is-kitversion from the package manifest and lockfile. - Inspect the installed declarations, package exports, or monorepo source before relying on an API name. Prefer the installed version over online examples.
- Search for an equivalent local guard, wrapper, barrel export, schema, or established import boundary.
- Reuse an existing guard when it already expresses the required semantics.
Do not add a wrapper layer merely because this skill mentions one. If the
project already has an is-kit boundary, respect it; otherwise import from
is-kit directly.
2. Choose the smallest correct guard
Read guard-selection.md when choosing between built-ins, logical combinators, custom predicates, equality guards, and collection combinators.
For object or API response validation, always read
object-validation.md before choosing
struct, typedStruct, optionalKey, or safeParse.
For replacement or cleanup work, read migration-checklist.md before changing manual checks.
Prefer composition over a handwritten type-predicate signature. Keep guards total, deterministic, and side-effect free.
3. Place the guard by responsibility
- Put broadly reusable, domain-free guards in the project's existing shared guard location, if one exists.
- Keep a schema beside the boundary that consumes the validated value when the schema exists for one API, file, parser, or integration.
- Keep business decisions and domain state predicates in their owning feature or domain module.
- Add or update barrel exports only when the project already uses them.
- Follow the repository's naming, documentation, and test-collocation rules.
What ships with it
4 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.
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.
- 7d ago First seen · 92 lines · 85 tokens per session scan A 9dc0597732ce
use-is-kit is a skill published in the GitHub repository nyaomaru/is-kit (74 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 858 once invoked, about $0.0004 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 2026-09-01.
Other skills, from other repositories
typescript-expert
TypeScript expert for type system, generics, utility types, and strict mode patterns.
write-script-bun
MUST use when writing TypeScript scripts. Bun is the default and preferred TypeScript runtime — pick it for TypeScript unless the script specifically needs Deno.
write-script-deno
Use ONLY when a TypeScript script specifically requires the Deno runtime (Deno stdlib or deno.land URL imports). For all other TypeScript, use write-script-bun instead.
write-script-python3
MUST use when writing Python scripts.
write-script-rust
MUST use when writing Rust scripts.
write-script-go
MUST use when writing Go scripts.