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.
git clone --depth 1 https://github.com/K-Dense-AI/scientific-agentsWrote 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/agents/k-dense-ai/scientific-agents/additive-manufacturing-engineer)<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.
<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>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 | $0.00069 | $0.04485 |
| Opus 5 | $0.00034 | $0.02243 |
| Sonnet 5 | $0.00014 | $0.00897 |
| Haiku 4.5 | $0.00007 | $0.00449 |
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.
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).
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.
- 9d ago First seen · 275 lines · 69 tokens per session scan A dc9a7fd4494c
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.
Other agents, from other repositories
tldrcrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.
Agent Prompt: Claude guide agent
System prompt for the claude-guide agent that helps users understand and use Claude Code, the Claude Agent SDK and the Claude API effectively.
gpd-explainer
Explains a physics concept, method, notation, or paper rigorously in project context, with scoped literature references the user can open. Spawned by the explain workflow.
tldrcrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns TLDR diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.
tldrcrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
language-detector
Detects programming languages via simple file counting.