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/stephen-studying/tech-route-maker/tech-route-makernpx skills add Stephen-studying/tech-route-maker --skill tech-route-makergit clone --depth 1 https://github.com/Stephen-studying/tech-route-makerWrote 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/stephen-studying/tech-route-maker/tech-route-maker)<a href="https://agentmods.dev/skills/stephen-studying/tech-route-maker/tech-route-maker"><img src="https://agentmods.dev/badge/skills/stephen-studying/tech-route-maker/tech-route-maker.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.04671 |
| Opus 5 | $0.00057 | $0.02336 |
| Sonnet 5 | $0.00023 | $0.00934 |
| Haiku 4.5 | $0.00011 | $0.00467 |
Grade A, and why
tech-route-maker 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 4d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Route Maker
Purpose
Use this skill to turn source materials into evidence-grounded editable technical route diagrams for research and engineering projects across multiple disciplines.
Primary users are researchers, students, academic writers, engineering teams and agent/tool builders preparing paper framework figures, method overview diagrams, thesis proposal routes, defense visuals, course-design diagrams, engineering system routes and workflow pipelines.
Campaign or advertising routes are legacy/experimental use cases. Do not make them the default direction unless the user explicitly asks for them.
Portability
This skill is intentionally agent-agnostic. SKILL.md is the source of truth for Codex/OpenAI-style skill loaders and any agent that understands skill folders. Other adapters in the repository point back here:
AGENTS.mdfor generic coding agents.CLAUDE.mdfor Claude-style project context.GEMINI.mdand.gemini/settings.jsonfor Gemini CLI..cursor/rules/tech-route-maker.mdcfor Cursor..github/copilot-instructions.mdfor GitHub Copilot coding agent..aider.conf.ymlfor Aider-style workflows.
Default Interaction Policy
Do not interrupt the user with a long sequence of questions, but do not guess domain or delivery preferences from a field-agnostic request.
Before final rendering, explicitly establish the domain context and confirm the requested output format, target medium, layout family and visual style. Present one concise grouped choice with sensible defaults; allow single or multiple output formats. If the source explicitly proves a domain fact, extract it with an evidence locator instead of asking the user to repeat it.
Default behavior:
- Never render a final technical route diagram from a field-agnostic request such as "draw a technical route diagram" without first identifying the discipline, subfield, project type, research object, method family and evaluation logic.
- If source files are available, extract domain context only from explicit source evidence. Ask one concise field-specific clarification question for every material gap rather than silently inventing it.
- If the user asks for a quick draft before the field is complete, mark
domain_context.confidenceaslow, keep missing items inunresolved_questions, and report that the output is not final. - If the user asks in Chinese for 开题, 课题申报, 项目申请, 基金, 论文技术路线图, or a Chinese research route diagram, prefer the Chinese academic presets below.
- If the user asks for an editable presentation figure, generate
pptx,svgandjson. - If the user asks for a paper or research figure, generate
svg,pptxandjson. - If the user asks for a maintainable system diagram, generate
drawio,svgandjson. - If the user asks for Draw.io, diagrams.net, online editing, import code, copyable code, or "能复制到draw.io的代码", include
drawio-codeand explain how to paste the XML into diagrams.net. - If the user asks for documentation output, generate
markdown,mermaidandjson. - If the user asks for long-term maintenance, add
drawio. - If the user asks for all formats, render
pptx,svg,drawio,drawio-code,excalidraw,mermaid,html,markdownandjson.
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.
- 4d ago First seen · 369 lines · 114 tokens per session scan A 41f11a04d39c
tech-route-maker is a skill published in the GitHub repository Stephen-studying/tech-route-maker (2 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 4,671 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
yolo-training
This skill should be used when user asks to "improve my mAP", "why is my model overfitting", "my training is diverging", "read my results.csv", "interpret my training curves", "my AP50 is good but AP50-95 is bad", "my recall is low", "how do I pick learning rate", "which augmentations should I use", "should I use a…
manimce-best-practices
Trigger when: (1) User mentions "manim" or "Manim Community" or "ManimCE", (2) Code contains from manim import , (3) User runs manim CLI commands, (4) Working with Scene, MathTex, Create(), or ManimCE-specific classes. Best practices for Manim Community Edition - the community-maintained Python animation engine.…
data-scientist
Processes and analyzes data with resident-kernel engines (DuckDB, Polars) and one-shot tools. Use for CSV/parquet/JSON analysis, group-by/join/aggregation, time series, distributions, cleaning, or plotting a dataset.
paper-search-usage
This skill should be used when user asks to "search for papers", "find research papers", "search arXiv", "search PubMed", "find academic papers", "search IEEE", "search Scopus", or "look up scientific literature".
hypothesis-testing
Applies the scientific method to debugging by helping users form specific, testable hypotheses, design targeted experiments, and systematically confirm or reject theories to find root causes. Use when a user says their code isn't working, they're getting an error, something broke, they want to troubleshoot a bug, or…
torchtalk-analyzer
Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server. Use when asked about how PyTorch operators work internally, where functions are implemented, what would break if code is modified, or finding tests for PyTorch operators.