Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add InjayTseng/graph-engineering-on-research/plugin install graph-engineeringWrote 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/injaytseng/graph-engineering-on-research/route)<a href="https://agentmods.dev/skills/injaytseng/graph-engineering-on-research/route"><img src="https://agentmods.dev/badge/skills/injaytseng/graph-engineering-on-research/route.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 5.1 | $0.00042 | $0.00399 |
| Opus 5 | $0.00021 | $0.00199 |
| Sonnet 5 | $0.00008 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
route 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 6d 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.
What it actually says
Read ${CLAUDE_PLUGIN_ROOT}/prompts/06-router.md. Everything below its "## Copy this block" line is your instruction set — execute it exactly, with one substitution: the "My question:" slot at the end is filled by the user's input below.
My question: $ARGUMENTS
Harness rules:
- If the question above is empty, ask the user what they are trying to find out — do not invent a question, and do not default to a route.
- If the question above is written in Chinese, use
${CLAUDE_PLUGIN_ROOT}/prompts/06-router.zh-TW.mdinstead (its block starts at "## 複製這段", the slot is "我的問題：") and work in Traditional Chinese throughout. - Step 3 is a hard gate. Show the classification and the quote, then stop and wait. Never dispatch a route in the same turn you chose it, even if the user's phrasing sounds impatient — the whole point of the quote is that it arrives before the spend.
- Once the user approves, hand off to the installed command rather than re-implementing the template:
/first-graph→ 00 ·/false-edge-audit→ 01 ·/diamond-research→ 02 ·/adversarial-review→ 03 (give it a file path) ·/consultant-roundtable→ 04 ·/issue-tree→ 05. - "No route" is a real outcome, not a failure. If the question is answerable in one paragraph, say so and answer it.
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.
- 6d ago First seen · 19 lines · 42 tokens per session scan A f672ab69b01d
route is a skill published in the GitHub repository InjayTseng/graph-engineering-on-research (10 stars, last pushed 6d ago), licensed MIT. It adds 42 tokens to every session and 399 once invoked, about $0.0002 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
pandic-office
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
story-long-write
A planning and pipeline adapter for writing long online novels. It organizes requests such as opening a book, creating an outline, continuing chapters, or rewriting chapters for the novel-studio pipeline.
story-setup
A setup tool for installing a novel-writing project’s supporting files and rules. It can prepare projects for Claude Code, OpenCode, Codex, or OpenClaw.