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 hyfdev/moonbit-agent-skills --skill moonbit-languagegit clone --depth 1 https://github.com/hyfdev/moonbit-agent-skillsWrote 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/hyfdev/moonbit-agent-skills/moonbit-language)<a href="https://agentmods.dev/skills/hyfdev/moonbit-agent-skills/moonbit-language"><img src="https://agentmods.dev/badge/skills/hyfdev/moonbit-agent-skills/moonbit-language/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/hyfdev/moonbit-agent-skills/moonbit-language"><img src="https://agentmods.dev/badge/skills/hyfdev/moonbit-agent-skills/moonbit-language.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 | $0.00155 | $0.02453 |
| Opus 5.5 | $0.00062 | $0.00981 |
| Sonnet 5.5 | $0.00031 | $0.00491 |
| Haiku 4.5 | $0.00015 | $0.00245 |
Grade A, and why
moonbit-language 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 16d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MoonBit language
Verification contract
Executable claims in this skill are checked against moonc v0.10.14+7d59c7ec9 (MoonBit release 0.10.14, build 2026-09-18) on Linux x86_64. The repository runs every mbt check fence on wasm-gc, wasm, js, and native and runs diagnostic fixtures against the same pin. Facts that depend on an external runtime or were not executed are explicitly labeled Documented, not executed with an official source. Blocks marked mbt nocheck are explanatory rejected or deprecated forms; they are not executed.
MoonBit is pre-1.0 and changes quickly. Before relying on a load-bearing claim, run moon version --all. If local moonc differs from the pin:
- Treat the claim as a hypothesis.
- Reproduce the smallest relevant example with
moon check,moon test, ornode scripts/verify_snippet.ts. - Compare the local version with the official latest manifest and current documentation commit; a newer official pin means this skill is stale even when no website release article exists.
- State which version was actually tested and any remaining difference.
Work by task
- Understand code: identify unfamiliar syntax and the local compiler version; search this file for the exact token or diagnostic; load the routed reference; explain behavior only after matching the code to a checked example or an explicitly documented fact.
- Write code: load the smallest relevant reference, use its current forms, then run
moon checkand the narrowest usefulmoon test. Do not invent syntax from another language or an old MoonBit tutorial. - Fix code: preserve the program's intent, reproduce the diagnostic, search both the diagnostic text and suspicious token in the references, apply the current migration, and rerun with warnings denied when deprecation is involved. Do not silence a warning before proving the replacement.
- Judge a feature: distinguish verified, documented, proposal, and unknown. Official docs can lag or suppress warnings; the compiler at the stated pin decides executable behavior.
What ships with it
16 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.
- agents/openai.yaml 479 B
- references/async-and-ffi.md 14 KB
- references/attributes.mbt.md 11 KB
- references/control-flow-and-iteration.mbt.md 14 KB
- references/cross-language-and-stale-syntax.md 9.3 KB
- references/data-types.mbt.md 19 KB
- references/declarations-and-functions.mbt.md 10 KB
- references/errors-and-error-handling.mbt.md 7.9 KB
- references/lexical-conventions.md 4.2 KB
- references/pattern-matching.mbt.md 12 KB
- references/reporting-errors.md 3.5 KB
- references/tests-and-checked-docs.mbt.md 6.3 KB
- references/traits-and-generics.mbt.md 9.1 KB
- references/types-structs-enums.mbt.md 13 KB
- references/visibility.mbt.md 6.3 KB
- scripts/verify_snippet.ts 1.4 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.
- 16d ago Changed · +3 lines f60f2c793301
- 2mo ago First seen · 76 lines · 155 tokens per session scan A 96749ccdb722
moonbit-language is a skill published in the GitHub repository hyfdev/moonbit-agent-skills (6 stars, last pushed 17d ago), licensed MIT. It adds 155 tokens to every session and 2,453 once invoked, about $0.0006 per session on Opus 5.5. 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
promptfoo-provider-setup
Connect Promptfoo to a model, live HTTP API, local Python/JavaScript provider, or app code. Use for request/auth mapping, response parsing, OpenAPI setup, and connection smoke tests. Use promptfoo-evals for broader eval coverage and promptfoo-redteam-setup for attack selection.
migrating-mastra-to-pydantic-ai
Migrate TypeScript Mastra applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports @mastra/ or relies on Mastra agents, tools, workflows, memory, processors, streaming, approvals, skills, or subagents.
migrating-vercel-ai-sdk-and-eve-to-pydantic-ai
Migrate TypeScript Vercel AI SDK or Eve applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports ai, @ai-sdk/, or eve, or relies on generateText, streamText, ToolLoopAgent, useChat, Eve agents, tools, skills, subagents, approvals, sessions, channels, schedules…
migrating-openai-agents-sdk-to-pydantic-ai
Migrate Python OpenAI Agents SDK applications to Pydantic AI and, when warranted, Pydantic AI Harness. Use for agents.Agent, Runner, function tools, handoffs, guardrails, sessions, human approval, streaming, or SandboxAgent. Do not use for applications built directly on the OpenAI Responses API without the Agents SDK…
ax-cpp-gen
Use when writing C++ code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-java-gen
Use when writing Java code with dev.axllm:ax for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.