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 instructions/stephen-studying/tech-route-maker/claude-mdgit 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/instructions/stephen-studying/tech-route-maker/claude-md)<a href="https://agentmods.dev/instructions/stephen-studying/tech-route-maker/claude-md"><img src="https://agentmods.dev/badge/instructions/stephen-studying/tech-route-maker/claude-md.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 | $0.00330 | $0.00330 |
| Opus 5 | $0.00165 | $0.00165 |
| Sonnet 5 | $0.00066 | $0.00066 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
tech-route-maker CLAUDE.md 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.
What it actually says
Claude Adapter
Use this repository as a Claude-compatible project context or skill folder.
Read SKILL.md first. It is the source of truth for when to use tech-route-maker, how to select default presets, when to ask necessary questions, and how to render editable outputs.
When a user asks for a technical route diagram, paper framework figure, engineering route, project roadmap, method flowchart, workflow, pipeline, or editable diagram:
- Inspect source evidence.
- Establish
domain_context: discipline, subfield, project type, research object, method family, data/materials, constraints and evaluation metrics. - Read
references/domain-profiles.mdwhen the discipline is unclear or unfamiliar. - Build
tech-route.json. - Inventory local sources with
trm ingestand record stable source IDs and SHA-256 hashes. - Offer the closest preset, then confirm missing domain and final delivery choices instead of guessing them.
- Run
trm validate <route> --strict. - Render selected formats with
trm renderonly after final blockers are resolved. - Report
QUALITY_REPORT.mdfindings and required manual revision.
If the user asks for copyable Draw.io or diagrams.net code, render drawio-code and tell them to paste tech-route.drawio-code.xml into diagrams.net / draw.io through Extras > Edit Diagram.
Use --allow-draft only for an explicitly unfinished draft. Do not render screenshots as the main editable output, and do not present inferred nodes as evidence.
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 · 22 lines · 330 tokens per session scan A 4b34e2a87890
tech-route-maker CLAUDE.md is an instructions file published in the GitHub repository Stephen-studying/tech-route-maker (2 stars, last pushed 1mo ago), licensed MIT. It adds 330 tokens to every session, about $0.0016 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 instructions, from other repositories
economics-paper-reviewer CLAUDE.md
Instructions for viplee110/economics-paper-reviewer: This repository is a portable English-only economics paper pre-review skill.
racehooks-mcp AGENTS.md
AGENTS.md instructions for racehooks/racehooks-mcp, covering agents.md — racehooks mcp server, install (end user), what it exposes, security model and contributing to this repo.
economics-paper-reviewer AGENTS.md
Instructions for viplee110/economics-paper-reviewer: This repository defines an English-only portable pre-review skill for economics papers.
clinical-ai-agent-skills AGENTS.md
Instructions for 2023Anita/clinical-ai-agent-skills, covering clinical ai agent rules, 1. evidence before confidence, 2. research is not medical advice, 3. scope before action and 4. small verified steps.
clinical-ai-agent-skills CLAUDE.md
Instructions for 2023Anita/clinical-ai-agent-skills, covering clinical ai agent rules for claude code, core behavior, evidence before confidence, research is not medical advice and scope before action.
paper2code-skill AGENTS.md
Instructions for issol14/paper2code-skill, covering agents.md - for llm agents, quick summary, repository structure, installation commands and one-liner installation.