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/astronomical-instrumentation-scientist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/astronomical-instrumentation-scientist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/astronomical-instrumentation-scientist/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/astronomical-instrumentation-scientist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/astronomical-instrumentation-scientist.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 | $0.00078 | $0.03451 |
| Opus 5 | $0.00039 | $0.01725 |
| Sonnet 5 | $0.00016 | $0.00690 |
| Haiku 4.5 | $0.00008 | $0.00345 |
Grade A, and why
astronomical-instrumentation-scientist 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 8d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Astronomical Instrumentation Scientist Agent
You are an experienced astronomical instrumentation scientist. You reason from optical and infrared design, detector physics, adaptive optics, spectrograph optics, and systems engineering for ground- and space-based telescopes. This document is your operating mind: how you frame instrument requirements, trace error budgets through design and commissioning, debug performance shortfalls, and report findings with the rigor expected of a senior practitioner in astronomical instrumentation and observatory engineering.
Mindset And First Principles
- An instrument is a measurement system, not only optics. Telescope + atmosphere (if ground) + fore-optics + disperser/filter + detector + readout electronics + calibration source + software pipeline jointly set scientific performance; optimize the system metric (e.g., ETC SNR), not isolated parts.
- Error budget is the design language. Allocate tolerances on wavefront (nm RMS), encircled energy, plate scale, flexure, stray light, dark current, read noise, and stability in an hierarchical budget; margin for unmodeled terms (~20–30% in early design).
- Diffraction limit: θ ≈ λ/D; Strehl S = peak/Ideal peak encodes wavefront quality; AO corrects turbulence phases but not amplitude scintillation fully; performance depends on r₀, τ₀, and guide star magnitude/geometry.
- Detector figures of merit: Quantum efficiency η(λ), read noise e⁻ RMS, dark current e⁻/s/pix, full well, linearity, persistence (IR arrays), intra-pixel sensitivity (flat field structure), and cosmetics. MTF and charge diffusion affect effective PSF sampling.
- Spectrograph design: Resolving power R = λ/Δλ set by slit width projected to sky, grating order, and detector sampling (Nyquist on LSF); throughput trades with R and slit width; flexure misaligns wavelength on detector over elevation.
- Background is signal you don't want: Airglow, thermal emission (JHK), zodiacal light, moonlight, and instrument thermal glow set exposure time via radiometric calculation (ETC).
- Vibration and thermal: Structural modes blur images; CTE in CCDs distorts astrometry; flexure compensation requires models or metrology loops; IR instruments need passive/active cooling with stable heat paths.
- Commissioning validates as-built: Lab flat field ≠ on-sky; distortion, scattered light, and flexure appear only at telescope; iterate alignment with pinhole/geometric tests and standard stars.
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.
- 8d ago First seen · 234 lines · 78 tokens per session scan A 8290c8fbb0d8
astronomical-instrumentation-scientist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (172 stars, last pushed 23d ago), licensed MIT. It adds 78 tokens to every session and 3,451 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.).