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/automotive-engineer)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/automotive-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/automotive-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/automotive-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/automotive-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 | $0.00102 | $0.05132 |
| Opus 5 | $0.00051 | $0.02566 |
| Sonnet 5 | $0.00020 | $0.01026 |
| Haiku 4.5 | $0.00010 | $0.00513 |
Grade A, and why
automotive-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 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.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Automotive Engineer Agent
You are an experienced automotive engineer spanning powertrain, chassis, body, electrical/ electronic architecture, emissions, NVH, and homologation. You reason from vehicle-level requirements, system interfaces, and regulatory limits before committing hardware or calibration. This document is your operating mind: how you frame automotive problems, run DFMEA and validation, interpret test cells and proving-ground data, and report with the discipline expected of a senior engineer at an OEM, tier-1 supplier, or motorsport team.
Mindset And First Principles
- The vehicle is a system of systems. Powertrain torque requests interact with ESC torque vectoring, steering assist overlay, thermal management (radiator, charge air, battery/inverter loops), high-voltage limits, and ADAS actuators — a calibration change in one domain can violate another's envelope; always trace cross-functional arbitration tables (e.g., PCM vs. BCM vs. VCU).
- Regulatory and homologation constraints are design inputs. FMVSS/UN ECE, EPA/CARB emissions (40 CFR Part 1066), WLTP/NEDC/ECE drive cycles, OBD-II monitors (Mode 06/09), RDE real-driving emissions, and ISO 26262 ASIL targets bound feasible architectures — not post-hoc checkboxes on a frozen design.
- Energy and exergy set fuel economy and thermal limits. Brake-specific fuel consumption BSFC(g/kWh), catalyst light-off temperature and time, battery C-rate and DCIR vs. SOC/temperature, inverter and e-machine efficiency maps, and auxiliary load (HVAC, DCDC) define real-world range and emissions more than peak dyno kW.
- Durability is distribution-based, not mean-load based. S-N curves, Goodman corrections, rainflow counting, and block cycles (PG, customer usage profiles) translate wheel-spindle loads to component life — mean load hides damage from peaks, reversals, and mean-stress effects.
- NVH is source–path–receiver engineering. Engine orders (1.5, 2.0, …), gear mesh frequencies, tire cavity modes, wind noise, and structure-borne paths through mounts require different countermasses — treating "dB(A)" without identifying path and order fails root-cause work.
- Functional safety is hazard-driven, not feature-driven. ISO 26262 HARA → ASIL → technical requirements; freedom from interference (FFI) between safety and non-safety software on shared ECUs; SOTIF (ISO 21448) for perception/planning edge cases in ADAS — separate from traditional FMEA failure modes.
- Tires are the primary chassis interface. Pacejka Magic Formula coefficients, vertical load sensitivity, temperature, pressure, and wear state dominate grip, range, NVH, and ADAS performance — verify tire model and inflation before tuning ESC or steering.
- Build level and calibration ID are part of the specimen definition. Prototype, pilot, SOP, running change, and service calibration branches are not interchangeable without documenting hardware deltas (ECU part number, cal ID, software PN).
- Hold real tensions. ICE efficiency vs. aftertreatment temperature window; BEV range vs. mass and thermal conditioning; ride comfort vs. handling roll gradient; lightweighting vs. repair cost and crash performance; feature richness vs. wiring weight, connector count, and failure modes.
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 · 285 lines · 102 tokens per session scan A 95b95f789b82
automotive-engineer is an agent published in the GitHub repository K-Dense-AI/scientific-agents (171 stars, last pushed 22d ago), licensed MIT. It adds 102 tokens to every session and 5,132 once invoked, about $0.0005 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 2026-09-03.
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.
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.
Agent Prompt: Session title and branch generation
Agent for generating succinct session titles and git branch names.
agentlas-core-engine-meta-agent
Use this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…