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 sanic732/P2P-4PDA-edition --skill pxpipegit clone --depth 1 https://github.com/sanic732/P2P-4PDA-editionWrote 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/sanic732/p2p-4pda-edition/pxpipe)<a href="https://agentmods.dev/skills/sanic732/p2p-4pda-edition/pxpipe"><img src="https://agentmods.dev/badge/skills/sanic732/p2p-4pda-edition/pxpipe/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/sanic732/p2p-4pda-edition/pxpipe"><img src="https://agentmods.dev/badge/skills/sanic732/p2p-4pda-edition/pxpipe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00086 | $0.01262 |
| Opus 5 | $0.00043 | $0.00631 |
| Sonnet 5 | $0.00017 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
pxpipe-compressor 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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Оптический executor P2P (pxpipe)
Это исполнитель («руки»). РЕШЕНИЕ когда сжимать принимает политика:
compression.md → L-OPTICAL (роутер сжатия) и agents.md → PXPIPE_GATE
(хендофф между агентами). Этот скилл только рендерит по команде и меряет выгоду.
Что делает
Конвертирует текст в плотные PNG. Vision-модели тарифицируют картинку по площади пикселей, а не по числу символов. На реальном контенте P2P замерено ~81–83% экономии токенов (одна страница, ratio ~5×, режим <10× ≈ 97% точности по DeepSeek-OCR, arXiv 2510.18234). Экономия — это математика пикселей, она не зависит от модели; от модели зависит только читаемость (см. reader-gate).
Три ЖЁСТКИХ гейта (не советы — enforcement в compress.mjs)
- READER GATE — сжимать только для моделей, которые доказанно читают рендеры:
claude-fable-5. Для Opus/Sonnet → отказ (путают ~7%, verbatim hex 0/15).gpt-5.6убран из гейта 2026-07-26 вслед за upstream: автор pxpipe вывелgpt-5.6-solиз дефолтного скоупа после raw-recall пилота — 0/4 точных идентификаторов и четыре выдуманных значения, на обоих профилях (6×11 и 5×8). Читатель, который выдумывает идентификаторы, несовместим с запретом фабрикации. Обойти:--force(на свой риск). - BYTE GUARD — точные строки (SHA, ключи,
#DB_*, id, пути, model-strings) вынимаются в text-sidecar рядом с картинкой (verbatim-safe, паттерн pxpipe). - PROFIT GATE — вход меньше
--min-chars(деф. 8000) → отказ (мелочь проигрывает накладным расходам картинки).
🔴 ЧТО НЕЛЬЗЯ имиджировать (byte-exact — уходит в sidecar как текст)
Исходный код · JSON-конфиги · diff-патчи · точные хеши/ID коммитов · ключи API · консольные команды для копипаста. РАЗРЕШЕНО: аналитику, логи рассуждений, словесные описания архитектуры, историю QUORUM, длинные разборы.
DECISION LEDGER (MUST): ключевые ЧИСЛА хендоффа (пороги, проценты, суммы, размеры) дублируй коротким текстовым списком рядом с картинкой. Слепой тест на Fable 5 (2026-07-07, плотная страница 1568×488): гист/слова — 7/7, точные числа/hex — 0/4, тихие конфабуляции ($38.61→«$16.61» уверенно). Числам с картинки не доверять — только sidecar/ledger.
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.
- 10d ago First seen · 68 lines · 86 tokens per session scan A 8166b0477b67
pxpipe-compressor is a skill published in the GitHub repository sanic732/P2P-4PDA-edition (17 stars, last pushed 22d ago), licensed MIT. It adds 86 tokens to every session and 1,262 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…