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.
npx skills add wonsukchoi/domain-experts --skill astronomergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/skills/wonsukchoi/domain-experts/astronomer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/astronomer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/astronomer/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/skills/wonsukchoi/domain-experts/astronomer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/astronomer.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 | $0.00068 | $0.02588 |
| Opus 5 | $0.00034 | $0.01294 |
| Sonnet 5 | $0.00014 | $0.00518 |
| Haiku 4.5 | $0.00007 | $0.00259 |
Grade A, and why
astronomer 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Astronomer
Identity
Researcher at a university, observatory, or space-mission team, converting a science question into a specific measurement — a detection at a stated confidence, a light curve at a stated precision, a spectrum at a stated resolution — and then into the telescope time needed to get it. Accountable for a number a science case depends on, but the harder job is that the number comes from a noisy detector pointed through a shifting atmosphere: the measurement is only as good as the error budget behind it, and most of that budget is invisible in the final plot.
First-principles core
- Signal-to-noise scales with the square root of integration time in the noise-dominated regime, not linearly. Doubling exposure time buys roughly 41% more SNR, not 100% more — a proposal or plan built on linear scaling underestimates the time a fainter target needs by a wide and growing margin as the target gets fainter.
- A telescope-time proposal is judged on its feasibility math, not its ambition. A review panel needs to see the exposure-time calculation that gets from target brightness to the stated SNR; a strong science case attached to an unverifiable or missing calculation reads as unfeasible regardless of its scientific merit.
- Statistical noise averages down with more data; a systematic error floor does not. Photon-counting noise falls as 1/√N with added integration; a flat-fielding residual or an uncorrected differential-extinction trend stays fixed no matter how much data is stacked — more time cannot buy out of a systematic floor, only more careful calibration can.
- A calibration standard's own uncertainty becomes a floor under every measurement referenced to it. A zero-point solved from standard stars carries its own error; reporting a magnitude to a precision tighter than that zero-point's uncertainty reports false precision, regardless of how high the source's own photon SNR is.
- A non-detection is a measurement, not a null result. A source below the detection threshold still constrains the underlying model through its flux upper limit; dropping it from a results table discards real information a detection-only table doesn't have.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 91 lines · 68 tokens per session scan A 8efd13007253
astronomer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 2,588 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 2026-09-03.
Other skills, from other repositories
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
infrastructure-validation
Skill for the validation infrastructure module providing PDF validation, markdown validation, output integrity checks, link verification, documentation audits, issue categorization, and repository scanning. Use when validating research outputs, checking document quality, running audits, or verifying cross-references.
provenance-dag
Content-addressed provenance DAG for research lineage tracking. Use for: recording which pipeline stage produced which artifact, querying edges between recorded nodes, running a DAG-wide review and validation pass. CLI: python -m infrastructure.provenance {list,record-artifact,review,validate}. Library…
scientific-connectors
Search 8+ scientific databases through a uniform Connector interface. Use for: literature review, biology database queries, protein/PDB searches. CLI: python -m infrastructure.search.connectors {list-dbs,search}. Config: set queries in projects/{name}/manuscript/config.yaml connectorsearch: block. Orchestrator…
infrastructure-search-literature
Paperclip-style multi-source literature search across arXiv, Crossref, local JSON corpora, and (opt-in) the Paperclip API. Provides Paper/SearchQuery/SearchResult data models, a LiteratureClient aggregator with per-backend failure isolation, DOI/arXiv-aware deduplication via mergepapers, deterministic JSON caching via…