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 Nevaberry/nevaberry-plugins --skill bun-knowledge-patchgit clone --depth 1 https://github.com/Nevaberry/nevaberry-pluginsWrote 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/nevaberry/nevaberry-plugins/bun-knowledge-patch)<a href="https://agentmods.dev/skills/nevaberry/nevaberry-plugins/bun-knowledge-patch"><img src="https://agentmods.dev/badge/skills/nevaberry/nevaberry-plugins/bun-knowledge-patch/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/nevaberry/nevaberry-plugins/bun-knowledge-patch"><img src="https://agentmods.dev/badge/skills/nevaberry/nevaberry-plugins/bun-knowledge-patch.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 | $0.00008 | $0.02224 |
| Opus 5.5 | $0.00003 | $0.00890 |
| Sonnet 5.5 | $0.00002 | $0.00445 |
| Haiku 4.5 | $0.00001 | $0.00222 |
Grade A, and why
bun-knowledge-patch scanned grade A 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `child_process.spawn()` streams always emit `Buffer`s regardless of How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bun Knowledge Patch
Use this skill when working on Bun applications, packages, builds, tests, servers, or Node.js compatibility. Check the relevant reference before relying on older Bun behavior or translating Node-oriented code.
Reference index
| Reference | Topics |
|---|---|
| Builds and frontend | Bundling, compiled executables, HTML/CSS, loaders, plugins, decorators, HMR, React, metafiles |
| Databases and storage | Bun.SQL, Postgres/MySQL/SQLite, bun:sqlite, S3, Redis, secrets, archives, images |
| HTTP and networking | Bun.serve, Fetch, WebSocket, TLS, HTTP/2/3, QUIC, UDP, Unix sockets, proxies |
| Node.js compatibility | Implemented and missing Node APIs, module hooks, workers, child processes, streams, crypto |
| Packages and workspaces | Installs, lockfiles, linkers, catalogs, scripts, audit, publish, workspace commands |
| Runtime and platform | Runtime APIs, files, subprocesses, formats, terminal text, profiling, cron, platform behavior |
| Testing | bun:test, node:test, concurrency, sharding, timers, mocks, coverage, reporters |
Upgrade hazards to check first
Installation layout is lockfile-driven
New workspace projects can use isolated installs, but existing projects do not
change linker merely because Bun is upgraded. bun.lock/bun.lockb
configVersion decides defaults: version 1 plus workspaces is isolated;
version 0 is hoisted. Set [install] linker = "isolated" or
bun install --linker=isolated when an existing monorepo needs isolation. See
packages and workspaces.
TLS verification is stricter
Connections that formerly tolerated hostname or client-certificate problems may
now fail. tls.connect() derives SNI and identity from host when servername
is absent; Bun socket TLS APIs default to rejectUnauthorized: true; Redis TLS
checks the URL host; and only literal rejectUnauthorized: false disables
verification. Review each TLS caller, including redirects and per-host
Bun.serve configurations. See
HTTP and networking.
What ships with it
8 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.
- 1mo ago First seen · 199 lines · 8 tokens per session scan A 76dd205c0f3d
bun-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (23 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 2,224 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pinme-email
Use this skill when a PinMe project (Worker TypeScript) needs to integrate email sending (sendemail). Guides AI to generate correct Worker TS code.
node-modern
Use this skill when writing, reviewing, or refactoring Node.js code — modules, async flow, cancellation, file and process I/O, HTTP — on a current Node.js release. Triggers: user mentions "Node", "Node.js", "ESM", "CommonJS", "require", "import", "fetch", "AbortSignal", "AbortController", "stream", "childprocess"…
better-auth
Skill for integrating Better Auth - comprehensive TypeScript authentication framework for Cloudflare D1, Next.js, Nuxt, and 15+ frameworks. Use when adding auth, encountering D1 adapter errors, or implementing OAuth/2FA/RBAC features.
nodejs-backend
Node.js backend patterns: layered architecture, TypeScript, validation, error handling, security, observability, logging, metrics, deployment. Use when building REST APIs, REST endpoints, middleware, Express/Fastify/Hono/NestJS/Koa servers, tRPC procedures, Bun servers, or server-side TypeScript.
api-framework-nestjs
NestJS backend framework - modules, controllers, services, DI, guards, pipes, interceptors, exception filters, middleware, DTOs with class-validator.
web-data-fetching-trpc
Skill "web-data-fetching-trpc" from agents-inc/skills, covering trpc patterns, which path applies, before writing trpc code, philosophy and core patterns.