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 agentmods add skills/sunrisepeak/mbun/mcpp-style-refnpx skills add Sunrisepeak/mbun --skill mcpp-style-refgit clone --depth 1 https://github.com/Sunrisepeak/mbunWhat 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 | $0.00073 | $0.02156 |
| Opus 5 | $0.00036 | $0.01078 |
| Sonnet 5 | $0.00015 | $0.00431 |
| Haiku 4.5 | $0.00007 | $0.00216 |
Grade A, and why
mcpp-style-ref 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
1 file 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.
- yesterday First seen · 183 lines · 73 tokens per session scan A f53bd44e6c30
mcpp-style-ref is a skill published in the GitHub repository Sunrisepeak/mbun (21 stars, last pushed 29d ago), with no licence file. It adds 73 tokens to every session and 2,156 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 2026-08-30.
Other skills, from other repositories
javascriptcore-garbage-collector
JSC GC reference for Bun. Use for use-after-free, JS object leaks, "collected too early", or when touching WriteBarrier, visitChildren, visitAdditionalChildren, JSRef, JSC::Strong/Weak, hasPendingActivity, ensureStillAlive, addOpaqueRoot, reportExtraMemoryAllocated, IsoSubspace, HeapAnalyzer, finalize.
implementing-jsc-classes-cpp
Implements JavaScript classes in C++ using JavaScriptCore. Use when creating new JS classes with C++ bindings, prototypes, or constructors.
implementing-jsc-classes-rust
Creates JavaScript classes using Bun's Rust bindings generator (.classes.ts). Use when implementing new JS APIs in Rust with JSC integration, prototypes, or constructors.
rust-system-calls
Guides using bunsys for system calls and file I/O in Rust. Use when implementing file operations, opening fds, or any syscall path instead of std::fs or libc.
slowest-tests
Find the top-N slowest test files in CI from a recent BuildKite run, optionally posting the results to a Slack channel as a formatted table. Use when asked to find slow CI tests, "what's making CI slow", or to post a slow-test report to Slack.
writing-bundler-tests
Guides writing bundler tests using itBundled/expectBundled in test/bundler/. Use when creating or modifying bundler, transpiler, or code transformation tests.