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/generous-corp/pulp/streamsnpx skills add Generous-Corp/pulp --skill streamsgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote 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/generous-corp/pulp/streams)<a href="https://agentmods.dev/skills/generous-corp/pulp/streams"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/streams.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.01965 |
| Opus 5 | $0.00022 | $0.00983 |
| Sonnet 5 | $0.00009 | $0.00393 |
| Haiku 4.5 | $0.00004 | $0.00197 |
Grade A, and why
streams 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 today.
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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Streams
Use this skill when reaching for any I/O in Pulp: reading files, sending
bytes over a socket, polling an HTTP endpoint, piping between processes,
or wrapping a new transport. The pulp::runtime::Stream / AsyncStream
hierarchy is the sanctioned path; do not add new Socket::send /
http_get callers unless you have a specific reason.
Decision tree
| You need to... | Use |
|---|---|
| Read or write a local file | FileStream (sync) — or wrap in AsyncStream for large files |
| Keep bytes in memory for tests / round-trips | MemoryStream |
| Talk to another process via pipe | PipeStream around NamedPipe |
| Open a TCP connection | TcpStream, wrapped in AsyncStream so connect() doesn't block the caller |
| Fetch an HTTP/S body | HttpStream::get(url) / post(url, body) |
| Fetch with custom headers or consume an incremental HTTP/S response | http_request(HttpRequest{...}) |
| Send structured WebSocket frames | WebSocketChannel::connect() / ::accept() over a TcpStream |
| Send/receive OSC messages | OscChannel::open(host, remote_port, local_port) |
| RPC-style request/response over any transport | JsonRpcPeer wrapping any MessageChannel |
| In-process message bridge (tests, inspector) | MemoryMessageChannel::make_pair() |
NamedPipe / PipeStream gotchas
On POSIX, NamedPipe presents one public pipe name but uses paired FIFOs
internally so bidirectional users cannot read back their own writes. Keep
that invariant when changing NamedPipe: a single O_RDWR FIFO looks
convenient, but InterprocessConnection read threads can consume outbound
frames from the same process and make child-process IPC flaky.
The paired FIFOs must stay directional after connection: server reads the
public FIFO and writes the .reply FIFO; the client does the opposite.
Do not keep a local writer open just to simplify setup, because EOF/HUP
then stops representing peer death. On macOS, protect FIFO write descriptors
with F_SETNOSIGPIPE; otherwise killing a connected child can terminate the
parent with SIGPIPE.
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.
- today First seen · 173 lines · 44 tokens per session scan A eea5f3ee04fa
streams is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,965 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…