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 aiguicai/MCP-Gateway --skill read_filegit clone --depth 1 https://github.com/aiguicai/MCP-GatewayWrote 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/aiguicai/mcp-gateway/read_file)<a href="https://agentmods.dev/skills/aiguicai/mcp-gateway/read_file"><img src="https://agentmods.dev/badge/skills/aiguicai/mcp-gateway/read_file/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/aiguicai/mcp-gateway/read_file"><img src="https://agentmods.dev/badge/skills/aiguicai/mcp-gateway/read_file.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 | $0.00080 | $0.00737 |
| Opus 5 | $0.00040 | $0.00368 |
| Sonnet 5 | $0.00016 | $0.00147 |
| Haiku 4.5 | $0.00008 | $0.00074 |
Grade A, and why
read_file 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read File
Use this bundled skill to read text files from configured allowed directories. Prefer it over terminal commands such as cat, Get-Content, type, sed, or head when you need file contents for code understanding or manual edits.
The gateway returns stable, line-numbered text and records the exact path being read before any content is returned. This makes file reads easier to audit and safer to combine with multi_edit_file.
Input
{
"path": "src/example.rs",
"cwd": "D:/path/to/workspace",
"offset": 1,
"limit": 200,
"skillToken": "..."
}
pathis the file to read. Relative paths resolve fromcwd. Absolute paths are allowed only when they remain inside configured allowed directories.cwdis required when more than one allowed directory is configured.offsetis the 1-based starting line. Omit it to start at line 1.limitis the number of lines to return. Omit it to read up to 2000 lines. The maximum is 2000.skillTokenis required for normal file reads. The documentation read for this SKILL.md is the only call that does not require it.
Output
Returned text uses:
line_number<TAB>content
Example:
41 fn handle_request() {
42 route();
43 }
Do not include the line-number prefix or tab when copying old_string into multi_edit_file. The prefix is only for orientation and startLine hints.
The structured result includes:
pathstartLineendLinenumLinestotalLinestruncatedlineTruncatedcontent
Rules
- Use
read_filebefore manually editing an existing file unless the exact current content is already in the conversation. - Read only the focused region you need. For large files, use
offsetandlimitinstead of reading the whole file repeatedly. - Use
offsetvalues from search results or compiler diagnostics to inspect nearby context. - If
multi_edit_filereports an ambiguous or missingold_string, re-read the relevant region withread_fileand copy the current text exactly. - Do not use terminal commands for ordinary text file reads unless
read_fileis disabled, unavailable, or unsuitable for the file type. - Use terminal commands for directory listings, generated command output, test/build output, and project tools.
read_filereads files, not directories.
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 · 85 lines · 80 tokens per session scan A fed36fd65833
read_file is a skill published in the GitHub repository aiguicai/MCP-Gateway (154 stars, last pushed 3mo ago), licensed MIT. It adds 80 tokens to every session and 737 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…