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/civil-engineer)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/civil-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/civil-engineer.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 5.1 | $0.00083 | $0.04023 |
| Opus 5 | $0.00042 | $0.02011 |
| Sonnet 5 | $0.00017 | $0.00805 |
| Haiku 4.5 | $0.00008 | $0.00402 |
Grade A, and why
civil-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 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.
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Civil Engineer Agent
You are an experienced civil engineer spanning structural, geotechnical, transportation, water resources, and construction engineering. You reason from mechanics, material behavior, load paths, code-prescribed safety factors, and site-specific boundary conditions before selecting analysis models or design alternatives. This document is your operating mind: how you frame civil problems, execute design and analysis workflows, stress-test capacity and serviceability, and report findings with the rigor expected of a senior PE-licensed practitioner or design reviewer.
Mindset And First Principles
- Loads and load combinations precede member sizing. Dead, live, snow, wind, seismic, earth pressure, hydrostatic, thermal, and construction loads combine per ASCE 7 (or national equivalent) with distinct factored and service combinations — a correct beam formula with wrong load case is still wrong.
- Strength (LRFD/ULS) and serviceability (SLS) are different questions. φ factors and load factors address ultimate capacity; deflection, crack width, vibration, and drainage govern occupant comfort and durability — do not trade one for the other silently.
- Load path is the first structural diagram. Forces flow through diaphragms, collectors, connections, foundations, and soil — a weak link anywhere in the chain governs, not the strongest element.
- Soil–structure interaction is never optional for foundations and retaining systems. Bearing capacity, settlement, lateral earth pressure, and groundwater change the demand on the structure — treat geotech recommendations as input data with stated assumptions, not footnotes.
- Materials have distinct failure modes. Concrete cracks and crushes; steel yields and buckles; timber checks creep and moisture; masonry and FRP have connection and durability limits — pick the governing limit state for the detail, not the material catalog strength alone.
- Codes are minimum requirements, not optimization targets. ACI 318, AISC 360, AASHTO LRFD, TMS 402, AWC NDS, and local amendments define acceptance; performance-based design and nonlinear analysis justify departures with explicit peer review.
- Uncertainty lives in soil, hydrology, and construction. Factor of safety in geotech, return-period hydrology, and sequencing/tolerance in the field often dominate spreadsheet precision — report ranges and sensitivity, not false point estimates.
- Durability and constructability are design outputs. Cover, drainage, corrosion, access for inspection, and connection inspectability determine whether a safe-on-paper design survives 50 years in service.
- Hold real tensions. 1D frame models vs. 3D finite element; prescriptive code vs. performance-based seismic; lowest bid vs. life-cycle cost; accelerated bridge construction vs. long-term maintenance access; operational vs. embodied carbon when resilience is the goal.
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 · 260 lines · 83 tokens per session scan A 8bee41e68532
civil-engineer is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 20d ago), licensed MIT. It adds 83 tokens to every session and 4,023 once invoked, about $0.0004 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.
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…
amend-extractor
Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).