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 lihongqing2001-gif/SoloCoreAgentGateway --skill connect-solocore-agentsgit clone --depth 1 https://github.com/lihongqing2001-gif/SoloCoreAgentGatewayWrote 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/lihongqing2001-gif/solocoreagentgateway/connect-solocore-agents)<a href="https://agentmods.dev/skills/lihongqing2001-gif/solocoreagentgateway/connect-solocore-agents"><img src="https://agentmods.dev/badge/skills/lihongqing2001-gif/solocoreagentgateway/connect-solocore-agents/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/lihongqing2001-gif/solocoreagentgateway/connect-solocore-agents"><img src="https://agentmods.dev/badge/skills/lihongqing2001-gif/solocoreagentgateway/connect-solocore-agents.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00066 | $0.00935 |
| Opus 5 | $0.00033 | $0.00467 |
| Sonnet 5 | $0.00013 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
connect-solocore-agents 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 11d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect SoloCore Agents
Overview
Connect an Agent through the hosted outbound relay by default. Do not require an Aily App ID or OpenAPI scope for the pull Connector. Never place an Enrollment Key, access token, or private key in arguments, chat, Git, logs, environment variables, or plaintext configuration.
Workflow
- Install the fixed repository release tag
v0.2.9withnpm ci && npm run builduntil the npm package is published. - Before
connect requestin a sandbox, choose an absoluteSOLOCORE_CREDENTIAL_DIRon a persistent volume. Prefer a private directory outside the Git checkout. Reject/tmp,/private/tmp,/var/tmp,/var/folders, ephemeral runner storage, and any path whose persistence is unknown. Create the directory as0700; the provider creates credential files as0600. - Prove persistence across two separate command executions: create a non-secret probe beside the credential directory, then confirm it still exists in the next execution. If the probe disappears, stop before requesting human approval.
- For Aily without admin/API access, run
connect requestwith Gateway URLhttps://solocore.cn, Agent ID,file-0600, and the selectedSOLOCORE_CREDENTIAL_DIR; the pending request remains valid for 24 hours. Report only the request ID, fingerprint, and expiry, then stop for human approval. - After approval, run
connect awaitwith the same request ID, Agent ID, credential backend, and exactly the sameSOLOCORE_CREDENTIAL_DIR. Never generate another key for an approved request. - If the private directory is inside a Git worktree, add it to a local Git exclude before creating credentials and verify
git status --ignoredcannot stage it. Never read or display credential file contents. - Send a Codex request with
chat send --stdin --wait; send an asynchronous Aily inbox message with--type solocore.inboxand no--wait; pull queued replies withinbox pull. These commands connect on demand and are the reliable baseline in sandboxes. Pass message text only on stdin. - A long-lived
deviceprocess only maintains WSS connectivity; it does not inject an inbox message into an Aily chat turn. Use it only when the environment preserves background processes and a registered handler can safely process the advertised task type. It never replacesinbox pullat the beginning of an Aily work turn. - Run
doctor; confirm outbound HTTPS/WSS 443, discovery, and one allowlisted task. - Revoke with
revoke --config <path>and confirm local credentials are removed.
What ships with it
2 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.
- 11d ago First seen · 38 lines · 66 tokens per session scan A 203fd9b935c2
connect-solocore-agents is a skill published in the GitHub repository lihongqing2001-gif/SoloCoreAgentGateway (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 935 once invoked, about $0.0003 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 2026-09-01.
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…