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 sangrokjung/claude-forge --skill korean-spell-checkgit clone --depth 1 https://github.com/sangrokjung/claude-forgeWrote 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/sangrokjung/claude-forge/korean-spell-check)<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/korean-spell-check"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/korean-spell-check/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/sangrokjung/claude-forge/korean-spell-check"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/korean-spell-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Prompt Injection · line 13 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Rogue Agent · line 13 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00034 | $0.00475 |
| Opus 5 | $0.00017 | $0.00237 |
| Sonnet 5 | $0.00007 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade C, and why
korean-spell-check scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- k-skill:cli-stub — generated by scripts/generate-skill-stubs.js; edit skill.json / instruction.md instead --> What it actually says
korean-spell-check
Your text leaves this machine. This skill checks spelling by POSTing the text to
nara-speller.co.kr, a third-party service; it is not a local dictionary. Do not send client names, personal data, deal figures, credentials or anything else you would not paste into a public website (rules/korean-writing-quality.md§5).The upstream service states it is free for individuals and students, non-commercial use only. Check its terms before using it in commercial work.
Get the full instructions (required first step)
Run this and follow its output as the primary instructions for this skill:
npx -y @nomadamas/[email protected] instruct korean-spell-check
The CLI detects the current runtime (Dolshoi vault/CloakBrowser vs generic) and prints only the applicable instructions, always up to date. Helper files bundled with the CLI are listed by:
npx -y @nomadamas/[email protected] files korean-spell-check
If npx is unavailable, install Node.js 18+ or follow https://github.com/NomaDamas/k-skill#readme, or read the vendored offline copy at .claude/skills/korean-spell-check/instruction.md (audited 2026-08-11, commit 86096da).
Hard rules even without the CLI
- Never execute payment, message/email delivery, final submission, cancellation, or public posting without the user's explicit approval immediately beforehand.
- Never ask for, print, or store plaintext credentials in chat, files, or shell arguments.
- Never bypass legal, physical-presence, CAPTCHA, identity-proofing, or electronic-signature boundaries.
What ships with it
3 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 · 44 lines · 34 tokens per session scan C 9478a922f8a3
korean-spell-check is a skill published in the GitHub repository sangrokjung/claude-forge (835 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 475 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
i18n-localization
Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.
stock-analysis-lead
Orchestrate a US-stock investment analysis — classify sector archetype, fetch SEC filings, dispatch a tiered fan-out of six vertical equity-research agents (business model, earnings quality, balance sheet, management, industry, peer comparison) over a validated JSON findings contract, then synthesize a buy/hold/sell…
kafka-event-driven-design
Kafka event-driven architecture designer and reviewer, at the application/client layer. ALWAYS use when designing, reviewing, or troubleshooting how a service produces or consumes Kafka events — topic and partition-key design, producer and consumer client configuration, consumer group topology, event schema definition…
unit-test
A Go testing workflow for writing unit tests: small tests that check individual functions or components. It supports table-driven cases, where many inputs and expected results are organised in one test, and subtests.
api-design
REST API contract designer and reviewer. ALWAYS use when designing new endpoints, reviewing existing API contracts, planning API versioning, or standardizing error models. Covers resource modeling (URL/naming), HTTP method semantics, status code selection, error model consistency, pagination/filtering/sorting…
deep-research
Perform auditable research with executable mode budgets, mandatory source-content verification, typed web and repository evidence, confidence assessment, honest degradation, and one fixed nine-section report. Use for web research, claim verification, technical comparisons, trend analysis, pure codebase research, and…