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/adancurusul/serial-mcp-server/serial-debugnpx skills add Adancurusul/serial-mcp-server --skill serial-debuggit clone --depth 1 https://github.com/Adancurusul/serial-mcp-serverWhat 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 | $0.00074 | $0.00617 |
| Opus 5 | $0.00037 | $0.00309 |
| Sonnet 5 | $0.00015 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
serial-debug 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 2d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serial Debug
Operating Rule
Use the serial-mcp-server CLI first unless the user explicitly asks for MCP or an MCP client is already configured. Keep stdout data separate from diagnostics, cite exact commands, and base hardware success on real command evidence from the device.
Workflow
- Confirm the binary is available:
serial-mcp-server --help
- List available ports before choosing a device:
serial-mcp-server list-ports --json
- For a device smoke test, probe the port first, then write/read only when the probe succeeds:
serial-mcp-server probe --port <port> --baud 115200 --json
serial-mcp-server write --port <port> --baud 115200 --data H --read --timeout-ms 1000 --json
- If RTS or DTR is involved, state the requested line levels and use the control-line command:
serial-mcp-server set-control-lines --port <port> --rts high --dtr low --json
- For repeatable serial procedures, prefer JSON macro packs and validate or plan them before real hardware execution:
serial-mcp-server macro validate --file <pack.json> --json
serial-mcp-server macro plan --file <pack.json> --macro <name> --json
serial-mcp-server macro run --file <pack.json> --macro <name> --simulate-read <response> --json
serial-mcp-server macro run --file <pack.json> --macro <name> --port <port> --baud 115200 --json
Macro packs are restricted JSON DSL files. v0.3 supports send, delay, expect contains, expect equals, and assemblies that call macros. It does not support shell commands, language execution, loops, variables, Quick commands, or RTS/DTR macro steps.
References
- Read
references/cli.mdfor exact command behavior, output expectations, and automation rules. - Read
references/mcp.mdwhen the user asks for MCP setup or MCP tool usage. - Read
references/hardware-safety.mdbefore changing baud, wiring, voltage levels, RTS, DTR, or reset/boot lines. - Read
references/troubleshooting.mdwhen a command fails, times out, returns no ports, or cannot open the device.
What ships with it
5 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.
- 2d ago First seen · 60 lines · 74 tokens per session scan A dff69d12f0f8
serial-debug is a skill published in the GitHub repository Adancurusul/serial-mcp-server (88 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 617 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
beautify-github-readme
Redesign GitHub README homepages or create project-native pure SVG, hybrid SVG-composed PNG/WebP, and opt-in animated GIF assets. Use when a user asks to beautify, redesign, rebrand, visually upgrade, simplify, or audit a GitHub README; create only a hero, section headers, diagrams, badges, motion graphics, showcase…
anti-defensive-writing
Reduce defensive writing in drafts and revisions by removing unnecessary caveats, disclaimers, hedges, apology-like framing, negative self-limiting statements, and over-explanations while preserving necessary scope, accuracy, safety, legal, ethical, and methodological limits. Use when drafting or revising academic…
oil-frontend
用于实现、修改、重构或评审产品前端。当前任务涉及页面、组件、交互、表单、状态、数据流、Hook、类型、视觉层级、排版、颜色、圆角、阴影、图标、响应式、动效、改变可见结果的 CSS 或前端代码组织时自动触发。触发后先阅读 SKILL.md，按任务的主要决策只加载最小规则集。纯 CSS 语法、导入或类名修复且不改变界面结果时不触发；纯构建、部署、依赖升级、安全、后端任务，以及只解释前端概念而不处理项目实现的请求也不触发。.
thesis-defense-pptx
Create, polish, and quality-check editable undergraduate or graduate thesis defense PowerPoint decks from a local thesis PDF/LaTeX project and an existing PPTX template. Use when the user asks for a formal defense PPT, thesis presentation, academic答辩PPT, template-matched PPTX, or local PowerPoint deck generation with…
rig
Minimal agent cli harness for defining harnesses in prompts as rig markdown fences.
tossinvest-web-api
Use this skill when users need public, read-only TossInvest/토스증권 data visible on tossinvest.com, including KR/US quotes, order books, candles, financials, filings, market search, news, rankings, industries/sectors, bond pages, screeners, calendars, indices, FX, crypto-like index pages, sanitized public community data…