Routing Outbound API Calls
PostHog/posthog
Use before adding or changing Python code that calls a third-party HTTP API from PostHog (a vendor REST call, a vendor SDK client, a scraping or enrichment service), and before adding or changing a…
[RU: интеграция proxy6.net — покупка/продление прокси, пул, ipauth, scraping] proxy6.net REST API — RU proxy provider for IPv4/IPv4 Shared/IPv6/MTproto.
$ npx skills add VKirill/claude-lane-stack --skill proxy6 -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VKirill/claude-lane-stack proxy6 --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/lane-stack/skills/proxy6 .claude/skills/proxy6 && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "proxy6" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/proxy6 into .claude/skills/proxy6/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy6", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/proxy6Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add VKirill/claude-lane-stack --skill proxy6 -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VKirill/claude-lane-stack proxy6 --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/lane-stack/skills/proxy6 .agents/skills/proxy6 && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "proxy6" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/proxy6 into .agents/skills/proxy6/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy6", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VKirill/claude-lane-stack --skill proxy6 -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VKirill/claude-lane-stack proxy6 --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/lane-stack/skills/proxy6 .cursor/skills/proxy6 && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "proxy6" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/proxy6 into .cursor/skills/proxy6/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy6", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/VKirill/claude-lane-stack.git --path plugins/lane-stack/skills/proxy6--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VKirill/claude-lane-stack --skill proxy6 -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VKirill/claude-lane-stack proxy6 --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/lane-stack/skills/proxy6 .gemini/skills/proxy6 && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "proxy6" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/proxy6 into .gemini/skills/proxy6/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy6", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install VKirill/claude-lane-stack proxy6Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add VKirill/claude-lane-stack --skill proxy6 -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/lane-stack/skills/proxy6 .github/skills/proxy6 && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "proxy6" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/proxy6 into .github/skills/proxy6/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy6", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VKirill/claude-lane-stack --skill proxy6 -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VKirill/claude-lane-stack proxy6 --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/lane-stack/skills/proxy6 .opencode/skills/proxy6 && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "proxy6" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/proxy6 into .opencode/skills/proxy6/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy6", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
proxy6[RU: интеграция proxy6.net — покупка/продление прокси, пул, ipauth, scraping] proxy6.net REST API — RU proxy provider for IPv4/IPv4 Shared/IPv6/MTproto.
Proxy6 is an agent skill from VKirill/claude-lane-stack. [RU: интеграция proxy6.net — покупка/продление прокси, пул, ipauth, scraping] proxy6.net REST API — RU proxy provider for IPv4/IPv4 Shared/IPv6/MTproto. Methods getprice/getcount/getcountry/getproxy/buy/prolong/delete/setdescr/check/ipauth via https://px6.link/api/{key}/. Money + destructive + 3 req/s rate limit. Use when: proxy6, proxy6.net, px6.link, прокси6, ipv4 shared, ipv6 прокси, mtproto, buy proxy api, getprice, prolong proxy, setdescr, getproxy, ipauth, scraping rotation ru, errorid 100, errorid 105…
Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 17 other files, including reference files (for example `CHANGELOG.md`, `references/REFERENCE.md` and `references/error-codes.md`).
It sits in Backend & APIs, covering Rate limiting, Web scraping and REST APIs. It works with Node.js, Bright Data and Python. The repository describes itself as: Multi-agent AI coding factory for one person — Claude Code PM + Codex/Qwen/Grok/Kimi/AGY writers, durable conveyor, auto-merge to main. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit ad5d501. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
px6.linkFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
PROXY6_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Proxy6 loads about 3.6k tokens when it runs, and up to ~29k if it reads all its reference files. Until then it costs about 189 tokens; SKILL.md has 1,569 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from VKirill/claude-lane-stack at commit ad5d501, republished under its MIT licence (© VKirill). 1,569 words, ~3,634 tokens.
.claude/skills/proxy6/SKILL.md (or your agent's skills folder). This skill also uses 16 other files; get the full folder from GitHub.<!-- versions:start -->
Primary pins:
docs-only (stable REST, no version path)3.14.x24.x (Active LTS)Source of truth: STACK_VERSIONS.md — verified 2026-08-24
<!-- versions:end -->
Loaded automatically when its description matches the active task. Read only the section you need, then follow the link to the relevant reference file for full detail.
buy, prolong, deletegetproxy results, organising it via descr tags, rotating per request / per workergetprice + getcount + balance check before calling buy (money safety)ipauth IP allowlist for production scrapers — full-replace semantics, dev/prod separationerror_id envelopeserror_id 100 (auth), 105 (IP not allowed), 300 (insufficient stock), 400 (no money), 410 (zero price), 429 (rate limited)version for the workload — 3 (IPv4 Shared), 4 (IPv4), 5 (MTproto), 6 (IPv6) — and the right countrystate=expired) and a renewal job before date_endhttpx for Python, nodejs for Node)telegram-bot and the MTProto client docsproxy6.net is one of the dominant Russian retail proxy providers — IPv4 (dedicated), IPv4 Shared, IPv6, and MTproto-flavoured proxies, sold per proxy per day with a single REST endpoint at https://px6.link/api/{api_key}/{method}/. It is widely used by Russian scraping shops, ad-operations teams, social-media automation, and price-monitoring pipelines that need cheap, short-lived, country-targeted proxies.
This skill is high-stakes because three of the ten methods cost money or destroy state and the API is hard-limited to 3 requests per second:
buy debits the merchant balance immediately; auto_prolong silently re-charges on expiry.prolong debits again and (for mixed-version ids) returns no price_single — easy to miscalculate.delete is irreversible; with the descr filter you can wipe an entire pool in one call.ipauth REPLACES the full allowlist — passing a partial list deletes everything else.The skill owns provider-domain knowledge — method shapes, error semantics, version tradeoffs, billing safety, rate-limit handling, pool management via descr tags, and ipauth gotchas. HTTP plumbing (retries, async clients, secret loading) belongs to the runtime skill (httpx, nodejs).
Single endpoint pattern: https://px6.link/api/{api_key}/{method}/?{params} (api_key in the URL path). Success envelope: {"status":"yes", user_id, balance, currency, ...}. Error envelope: {"status":"no", error_id, error}. Auth via api_key only; optional IP allowlist in dashboard (returns error_id 105 if source IP not allowed). The key in the URL path means it appears in nginx / reverse-proxy access logs — log scrubbing is mandatory.
Full reference: references/setup.md
getprice (price calc) · getcount (stock check) · getcountry (countries by version) · getproxy (list owned proxies, paged) · setdescr (update comment tag) · buy (purchase — money) · prolong (extend — money) · delete (irreversible) · check (validate one proxy) · ipauth (full-replace allowlist).
Full reference: references/methods.md
Four version values map to four distinct products with different prices and protocol support: 3 = IPv4 Shared (cheapest, shared across users), 4 = IPv4 dedicated, 5 = MTproto (Telegram-specific), 6 = IPv6. Pick by target: IPv6 only works against IPv6-aware destinations; MTproto only for Telegram clients; IPv4 Shared is fine for low-trust scraping but flags faster on sensitive sites.
Full reference: references/proxy-versions.md
Provider enforces 3 requests per second. Practical client budget: 2 req/s (33% headroom) under steady load, brief bursts up to 3. Use a token bucket / leaky bucket gate or per-call sleep ≥ 333 ms. Retry policy: 429 → backoff base 500 ms, cap 30 s, max 5 attempts; never retry 4xx envelope errors except error_id 30 (unknown — single retry).
Full reference: references/rate-limit-and-retry.md
Canonical pre-buy sequence: getprice(count, period, version) → getcount(country, version) → balance check (from any successful envelope) → buy(...). Always set descr to a stable ops tag so the order is reattributable later. Default auto_prolong = OFF — surprise renewals are a top operational complaint. Document a balance-low threshold (alert when balance < N × daily_burn).
Full reference: references/purchase-and-billing.md
Organise live proxies by descr tag (e.g. descr=pool:scraper-A:prod). Rotation strategies: sticky (worker keeps one proxy until ban / expiry), round-robin (per-request from a shuffled pool), weighted (prefer freshest by date_end). Ban detection: track per-proxy 4xx/5xx ratio; quarantine on threshold; replace via buy with the same descr. Schedule a daily cleanup that getproxy(state=expired) → delete(ids=...).
Full reference: references/pool-management.md
ipauth sets the full list of source IPs allowed to use the proxies (separate from API allowlist — that's in the dashboard). Critical gotcha: every ipauth call REPLACES the prior list. Always send the complete union of dev + prod + CI IPs; pass ip=delete to clear all bindings. Prefer ipauth over user/pass for production worker fleets — fewer secrets in code.
Full reference: references/ipauth-strategy.md
Async httpx.AsyncClient with tenacity retry decorators, pydantic models for response shapes, api_key in env var (PROXY6_API_KEY), per-method functions returning typed envelopes, rate-limit token bucket via asyncio.Semaphore + sleep.
Full reference: references/integration-python.md
fetch or axios with axios-retry / p-retry, TypeScript types for each method's response, env-based key, rate limit via p-limit or bottleneck.
Full reference: references/integration-node.md
getprice + getcount + envelope balance BEFORE every buy — never trusts an outdated balance valuedescr on buy for ops attribution; never relies on id alone for identifying a logical poolauto_prolong to OFF; opts in only when there's a documented billing-alert pathipauth call as a full-list overwrite — composes the union of all known IPs before sending429, network errors, 5xx, and error_id 30 — never retries 100/105/200/210/220/230/240/250/260/270/280/300/400/404/410id, ip, port, user, pass, date_end, descr, active from getproxy in a local table and refreshes dailydelete with ids= only after a getproxy dry-run that lists exactly those ids — never blindly with descr= filterapi_key from PROXY6_API_KEY env var; scrubs it from access logs at the reverse proxyapi_key in source, commit history, or client bundles — it grants full balance-spending powerbuy without a fresh getprice + getcount + balance check — silent overdraft / out-of-stock buys waste moneyipauth — it REPLACES the allowlist, instantly cutting off prod workers not in the callauto_prolong=1 without a budget alert and an off-switch — runaway charges are the #1 incident classdelete with descr= filter without a getproxy(descr=...) dry-run that prints every id about to dieprolong mixed-version returns price_single — for heterogenous ids the field is ABSENT; sum from listapi_key is in the path and ends up in nginx access logs / APMapi_key from reverse-proxy access logs (Angie/Nginx log_format with regex masking)90%-filter applied — mainstream 2026 choices used in scraping / automation pipelines.
httpx — Python async HTTP client (primary runtime for scraping with proxy6 outputs)nodejs — Node 24 (alternative scraping runtime)python — Python 3.14 (parent runtime for scraping pipelines)pydantic — validate proxy6 response envelopes and proxy recordspytest — test the client and rotation logic against fixture envelopescloudpayments — RU payment SaaS skill (high-stakes pattern reference)yookassa — RU payment SaaS skill (high-stakes pattern reference)redis — Redis 8 (token-bucket rate limiter, pool cache)postgresql — PostgreSQL 18 (pool state, descr tagging, expiry tracking)karpathy-guidelinesDomain-specific references (Pattern 2) — load only what's relevant:
| Topic | File |
|---|---|
| Index, decision map, when-to-use which doc | references/REFERENCE.md |
| API key handling, log scrubbing, IP allowlist, rate-limit overview | references/setup.md |
| All 10 methods — params, response shapes, examples | references/methods.md |
| Proxy versions 3/4/5/6 — IPv4 Shared vs IPv4 vs MTproto vs IPv6, when to use which | references/proxy-versions.md |
| All 17 error codes — diagnose / cause / fix (symptom-indexed) | references/error-codes.md |
| Rate limit & retry — 3 req/s budget, token bucket, tenacity / p-retry config, 429 backoff | references/rate-limit-and-retry.md |
| Purchase & billing — getprice→getcount→buy idempotency, balance check, auto_prolong, descr tagging | references/purchase-and-billing.md |
| Pool management — descr organisation, rotation, ban detection, scheduled cleanup | references/pool-management.md |
| ipauth strategy — when to use, full-replace semantics, dev/prod separation | references/ipauth-strategy.md |
| Python integration — httpx, tenacity, pydantic, asyncio limiter | references/integration-python.md |
| Node.js / TS integration — fetch/axios, p-retry, types, bottleneck limiter | references/integration-node.md |
| Recommended defaults — SSOT: rate budget, request timeout, retry policy, auto_prolong default, balance threshold | references/recommended-defaults.md |
| Wrong vs Right — paired anti-patterns: key leakage, missing retry, blind delete, ipauth wipe, auto_prolong runaway | references/wrong-vs-right.md |
| Troubleshooting — symptom-indexed: 429 storm, 100 auth, 105 IP block, 300 stock, 400 balance, 410 zero price, descr overflow, mixed-version prolong, accidental delete | references/troubleshooting.md |
| Eval cases — routing tests (positive + negative + edge) | references/eval-cases.md |
How to use: open the topic file relevant to the current task. Purchase work → purchase-and-billing.md + methods.md. Rate-limit / 429 work → rate-limit-and-retry.md + troubleshooting.md. Pool work → pool-management.md. New integration → setup.md + integration-python.md or integration-node.md. Tuning knobs → recommended-defaults.md.
© VKirill, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 16 other files (references) in plugins/lane-stack/skills/proxy6 of VKirill/claude-lane-stack.
Open the folder on GitHubat commit ad5d501
Proxy6 next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Proxy6 this skillVKirill/claude-lane-stack | 122 | — | ~3.6k | Automated safety check: Pass | MIT | |
| Routing Outbound API CallsPostHog/posthog | 40k | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| Brightdata SDK JSbrightdata/skills | 264 | — | ~3k | Automated safety check: Pass | MIT | |
| Cloudflare Email Servicehodgef/apiker | 127 | 3 repos | ~2k | Automated safety check: Pass | MIT | |
| Nxvutensils/nxv | 136 | — | ~7.9k | Automated safety check: Notes | MIT | |
| Frappe Impl WhitelistedImpertio-Studio/Frappe_Claude_Skill_Package | 187 | 1 repos | ~3.1k | Automated safety check: Pass | MIT |
PostHog/posthog
Use before adding or changing Python code that calls a third-party HTTP API from PostHog (a vendor REST call, a vendor SDK client, a scraping or enrichment service), and before adding or changing a…
brightdata/skills
Web data extraction and discovery using the Bright Data JavaScript/TypeScript SDK (@brightdata/sdk).
hodgef/apiker
Send and receive transactional emails with Cloudflare Email Service (Email Sending + Email Routing).
utensils/nxv
Find any version of any Nix package across nixpkgs git history using the nxv CLI or HTTP API.
Impertio-Studio/Frappe_Claude_Skill_Package
A skill your agent uses when building API endpoints with @frappe.whitelist() in Frappe.
sasjs/core
Installing, configuring, and running @sasjs/server - the open-source NodeJS wrapper around the SAS binary that provides a REST API, filesystem (SASjs Drive), Stored Program execution, and web app…
VKirill/claude-lane-stack
Lane-stack design + brand intelligence (vendored ui-ux-pro-max).
VKirill/claude-lane-stack
Owner-facing architect for a new app or service. An agent skill from VKirill/claude-lane-stack.
VKirill/claude-lane-stack
Live browser QA + Playwright-compatible replay. An agent skill from VKirill/claude-lane-stack.
VKirill/claude-lane-stack
Карта файлов копирайта в .agents/copy/: шаблоны, статусы, цепочка audience→headlines→ux.
VKirill/claude-lane-stack
Dispatch copy-lead helpers: Tavily, Codex luna/terra, grok/X, OpenCode DeepSeek, Cursor Grok 4.6 medium-fast.
VKirill/claude-lane-stack
Keep living docs/ honest after code changes. An agent skill from VKirill/claude-lane-stack.
Works with
Categories
[RU: интеграция proxy6.net — покупка/продление прокси, пул, ipauth, scraping] proxy6.net REST API — RU proxy provider for IPv4/IPv4 Shared/IPv6/MTproto. Proxy6 is an agent skill from VKirill/claude-lane-stack.net REST API — RU proxy provider for IPv4/IPv4 Shared/IPv6/MTproto.
Proxy6 fits situations like: scraping rotation ru; Балансовая проверка.
Run `npx skills add VKirill/claude-lane-stack --skill proxy6 -a claude-code`. Or copy the skill folder (plugins/lane-stack/skills/proxy6 in VKirill/claude-lane-stack) into .claude/skills/proxy6 in your project. Claude Code loads it when a task matches its description.
Run `npx skills add VKirill/claude-lane-stack --skill proxy6 -a codex`. Or copy the skill folder (plugins/lane-stack/skills/proxy6 in VKirill/claude-lane-stack) into .agents/skills/proxy6 in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VKirill/claude-lane-stack --skill proxy6 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/proxy6, .gemini/skills/proxy6, .github/skills/proxy6 and .opencode/skills/proxy6 in your project.
Going by SKILL.md and its folder, Proxy6 needs credentials named PROXY6_API_KEY. Our summary lists: Python 3; Node.js; A credential in PROXY6_API_KEY.
SKILL.md names 1 domain. In commands or code: px6.link; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Proxy6 is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.6k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 25k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Proxy6: Routing Outbound API Calls (PostHog/posthog, 40k stars), Brightdata SDK JS (brightdata/skills, 264 stars), Cloudflare Email Service (hodgef/apiker, 127 stars) and Nxv (utensils/nxv, 136 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
VKirill (a GitHub user) maintains it in VKirill/claude-lane-stack, which has 122 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 6, 2026.
Source: VKirill/claude-lane-stack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.