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/meltflexdevs/techdrawai-skills/claude-mdgit clone --depth 1 https://github.com/MeltFlexDevs/techdrawai-skillsWrote 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/meltflexdevs/techdrawai-skills/claude-md)<a href="https://agentmods.dev/instructions/meltflexdevs/techdrawai-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/meltflexdevs/techdrawai-skills/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 | $0.00323 | $0.00323 |
| Opus 5 | $0.00161 | $0.00161 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
techdrawai-skills 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
Notes for agents working in this repository
This repository distributes the TechDraw AI skills and the packaging around them. It is not the MCP server's source; that lives in the TechDraw AI application repository and ships to npm as techdrawai-mcp.
Layout
skills/techdrawai-drafting/SKILL.md: photo to dimensioned technical drawingskills/techdrawai-cad/SKILL.md: DXF, DWG, 3D reconstruction, product renders.claude-plugin/: Claude Code plugin and marketplace manifestsmcpb/: Claude Desktop extension manifest plus a compiled copy of the serverserver.json: MCP registry entry
Rules
- Version numbers move together.
VERSION,.claude-plugin/plugin.json,.claude-plugin/marketplace.json,mcpb/manifest.jsonandserver.jsonall carry one. Change one, change all of them. - Do not edit
mcpb/server/*.jsby hand. It is build output, copied from the npm package. Fix the TypeScript source instead and recopy. - Credit costs appear in several files. They are enforced server-side in the application. If a cost changes there, update the README table, both skills and
mcpb/manifest.json. - The skills carry judgement, not schemas. Do not turn a SKILL.md into a parameter list. That is what the tool definitions and https://techdrawai.com/api are for.
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 · 19 lines · 323 tokens per session scan A 44b72b7ea418
techdrawai-skills CLAUDE.md is an instructions file published in the GitHub repository MeltFlexDevs/techdrawai-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 323 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
circuit-synth CLAUDE.md
Instructions for circuit-synth/circuit-synth, covering claude.md - circuit-synth library development guide, project context, professional quality standards, 🎯 core development philosophy and 1. github issue-driven development.
IntentForge AGENTS.md
Instructions for jzjzzzzzzz/IntentForge, covering agent instructions, current phase, engineering rules and cad rules.
aspicio AGENTS.md
Instructions for frontsail-ai/aspicio, covering aspicio — agent guide, tech stack, architecture in 30 seconds, layout and commands.
AutoSage AGENTS.md
Instructions for SeattleUser0/AutoSage, covering autosage — agent instructions, non-negotiables, architecture, http api (compatibility surface) and tool system.
aspicio CLAUDE.md
Instructions for frontsail-ai/aspicio, a project described as: DXF and vector-PDF viewer for the web and AI agents — TypeScript parse→tessellate→render engine with a WebGL viewer, React/Vue/Svelte/web-component bindings, HTTP API, MCP server, and an in-chat viewer for ChatGPT & Claude (MCP Apps).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.