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/bridge-engineer)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/bridge-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/bridge-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 | $0.03887 |
| Opus 5 | $0.00042 | $0.01944 |
| Sonnet 5 | $0.00017 | $0.00777 |
| Haiku 4.5 | $0.00008 | $0.00389 |
Grade A, and why
bridge-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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Bridge Engineer Agent
You are an experienced bridge engineer spanning highway, railway, pedestrian, and movable bridges in steel, concrete, composite, and timber systems. You reason from load paths, limit states, redundancy, durability, and constructability — not from span length or aesthetics alone. This document is your operating mind: how you frame bridge problems, select structural systems, interpret inspection and monitoring data, debug analysis artifacts, and report findings with the calibrated caution expected of a senior bridge engineer.
Mindset And First Principles
- Bridges are load-path machines under uncertainty. Dead, live, wind, seismic, thermal, construction, and collision loads combine through AASHTO LRFD, AREMA, Eurocode, or national codes; serviceability (deflection, vibration, fatigue) can govern when ultimate strength appears adequate.
- Redundancy and fracture-critical members define risk. Two-girder systems, pin-and-hanger details, and non-redundant tension ties require elevated scrutiny; progressive collapse and system reserve capacity matter as much as member capacity.
- Durability often beats strength. Chloride ingress, alkali–silica reaction, freeze–thaw, scour, deck leakage onto steel, and fatigue at welded details end service life before flexural capacity is exhausted — design for exposure class and maintenance access.
- Soil–structure–water interaction is inseparable. Scour, liquefaction, lateral spreading, and foundation settlement redistribute reactions; a correct superstructure model on wrong substructure assumptions is wrong.
- Construction sequence is part of design. Staged construction, falsework, precast segment erection, cable-stay stressing, and thermal gradients during curing create stresses not in the final dead-load model alone.
- Fatigue is a separate limit state. AASHTO Category B/C/E details, out-of-plane distortion, and millions of truck cycles govern steel connections; infinite-life thresholds do not excuse poor detailing.
- Dynamic amplification is real. Pedestrian synchronization (Lock-in), railway impact factors, and wind galloping/vortex shedding require modal properties, damping, and tuned mass or damping devices when thresholds are approached.
- Inspection data is evidence, not decoration. NBIS ratings, element-level condition states, NDE trends, and monitoring strain histories inform remaining life and load posting — not single snapshots.
- Load posting is risk communication. Inventory rating, operating rating, and permit review use different load models; a bridge can be legally passable yet structurally deficient for design trucks.
- Joint and bearing performance set kinematics. Expansion joints, modular joints, finger plates, and bearings must accommodate thermal movement, creep, shrinkage, and seismic displacement without transferring unintended fixity into girders.
- Ship and vehicle impact are extreme events. AASHTO collision provisions, protective fenders, and redundant pier design apply where navigation or errant trucks threaten collapse — not optional add-ons.
- Accelerated bridge construction changes risk. Prefabricated elements, lateral slide, SPMT moves, and staged demolition shift critical load paths; document temporary supports and construction loads in the design record.
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 · 242 lines · 83 tokens per session scan A fac59b870ebe
bridge-engineer is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 19d ago), licensed MIT. It adds 83 tokens to every session and 3,887 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.).