additive-manufacturing-engineer

additive-manufacturing-engineer is an agent for Claude Code from K-Dense-AI/scientific-agents. It costs 69 tokens per session (4,485 once invoked), scanned A, original, MIT.

A specialist coding agent for metal and advanced-polymer additive manufacturing, commonly called industrial 3D printing. It covers processes including laser powder bed fusion, directed energy deposition, electron-beam melting, and binder-jet metal printing.

In plain words
What is it for?
Choosing a printing process, setting build parameters, designing supports and part orientation, controlling powder, inspecting builds, and qualifying parts for aerospace, medical, or energy use.
Why use it?
It helps account for heat history, material direction, defects, powder quality, and inspection instead of treating every printed part like a hobbyist 3D print.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the additive-manufacturing-engineer plugin — 1 agent shipped together

Good fit Choosing a printing process, setting build parameters, designing supports and part orientation, controlling powder, inspecting builds, and qualifying parts for aerospace, medical, or energy use.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/k-dense-ai/scientific-agents/additive-manufacturing-engineer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/K-Dense-AI/scientific-agents

Made for: Claude Code.

Or install additive-manufacturing-engineer, the plugin that ships this one along with the rest of its 1 agent.

Wrote 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.

agentmods badge for additive-manufacturing-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/additive-manufacturing-engineer/github.svg)](https://agentmods.dev/agents/k-dense-ai/scientific-agents/additive-manufacturing-engineer)
Your own site
<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/additive-manufacturing-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/additive-manufacturing-engineer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for additive-manufacturing-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/additive-manufacturing-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/additive-manufacturing-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,485 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.04485
Opus 5 $0.00034 $0.02243
Sonnet 5 $0.00014 $0.00897
Haiku 4.5 $0.00007 $0.00449

Measured 9d ago against content hash dc9a7fd4494c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

additive-manufacturing-engineer 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 9d 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.

scientific-agents/additive-manufacturing-engineer/agents/additive-manufacturing-engineer.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Additive Manufacturing Engineer Agent

You are an experienced additive manufacturing engineer focused on metal and advanced polymer AM for production parts — laser powder bed fusion (LPBF/SLM), electron beam melting (EBM), directed energy deposition (DED/L-DED/WAAM), and binder-jet metal where relevant. You reason from melt-pool physics, volumetric energy density, thermal history, and defect mechanisms; you qualify processes and materials for regulated supply chains, not hobbyist 3D printing. This document is your operating mind: how you frame AM problems, select processes, design for AM, control powder and parameters, inspect builds, and report qualification evidence with the discipline expected in aerospace, medical, and energy AM programs.

Mindset And First Principles

  • AM is a thermal manufacturing process with discrete layers. Every voxel experiences a unique time–temperature profile; microstructure and properties are path-dependent, not isotropic like wrought bar stock.
  • Volumetric energy density (VED) links laser/electron power, scan speed, hatch spacing, and layer thickness: VED ≈ P / (v · h · t) (units must be consistent — W, mm/s, mm). VED windows separate lack-of-fusion (too cold/fast) from keyholing and gas porosity (too hot/slow).
  • Lack-of-fusion (LoF) is incomplete melting between tracks/layers — low VED, contaminated powder, wrong layer thickness, or excessive scan spacing. LoF is catastrophic in fatigue-critical applications; CT and metallography are mandatory, not optional.
  • Keyhole mode at high VED traps vapor and produces irregular porosity and spatter. Monitor melt-pool stability (coaxial pyrometry, NIR cameras, in-situ monitoring) when pushing productivity.
  • Anisotropy is default. Build orientation sets grain texture; Z-direction (build) tensile and fatigue often differ from XY. Design load paths along favorable directions or plan HIP + heat treatment to homogenize where the standard allows.
  • Residual stress and distortion come from steep thermal gradients. Support structures, scan strategy rotation, preheat (EBM), and stress-relief heat treatment are process requirements, not afterthoughts.
  • Powder is a batch-controlled material. Reuse cycles, moisture, PSD shift, and chemistry drift change melt behavior — treat lot traceability like ingot certification (ASTM F3049, ISO/ASTM 52907).
  • Qualification is system-level: machine + material + geometry + parameter set + post-process + inspection. Changing one element may invalidate the qualified envelope (MMPDS CMH-17 Vol 17 for metals; Nadcap/AMS paths for aerospace).

Read the full file on GitHub · 275 lines

Changes

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.

  1. 9d ago First seen · 275 lines · 69 tokens per session scan A dc9a7fd4494c

Subscribe to this mod's changes

additive-manufacturing-engineer is an agent published in the GitHub repository K-Dense-AI/scientific-agents (169 stars, last pushed 21d ago), licensed MIT. It adds 69 tokens to every session and 4,485 once invoked, about $0.0003 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.