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 buildmoonshot/skillpacks --skill crs-disciplinegit clone --depth 1 https://github.com/buildmoonshot/skillpacksWrote 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/buildmoonshot/skillpacks/crs-discipline)<a href="https://agentmods.dev/skills/buildmoonshot/skillpacks/crs-discipline"><img src="https://agentmods.dev/badge/skills/buildmoonshot/skillpacks/crs-discipline.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 | $0.00066 | $0.00610 |
| Opus 5 | $0.00033 | $0.00305 |
| Sonnet 5 | $0.00013 | $0.00122 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
crs-discipline 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRS Discipline
Coordinate reference systems are the #1 source of silent, serious GIS errors. Before any spatial operation, know the CRS of every dataset, and make them match.
Rules
-
Determine the CRS of every input before using it. Check it explicitly — the
.prjfor a shapefile, the SRID in PostGIS, the spatial reference of a feature class,gdf.crsin GeoPandas. Never start a spatial operation on data whose CRS you haven't confirmed. -
Treat an undefined CRS as a stop sign, not a default. Data with no embedded CRS — a shapefile missing its
.prj, an SRID of 0 or "unknown" — is the classic trap: it lines up perfectly on the author's machine but is meaningless anywhere else. Do not assume it's WGS84. Infer the likely CRS from the coordinate ranges (values in −180..180 → geographic degrees; large numbers in meters or feet → projected) and confirm with the source before proceeding. -
Reproject to a common CRS before combining data. Spatial joins, overlays, clips, and distance/area math require all inputs in the same CRS. Align them first — don't let a library silently compare coordinates in two different systems.
-
Match the CRS to the operation. Use a geographic CRS (e.g., EPSG:4326) for storage and web display; use an appropriate projected CRS (the right UTM zone, State Plane, or an equal-area projection) for distance, area, and buffer calculations. Measuring length or area in degrees is a bug.
-
Never confuse "define" with "project." Defining a CRS labels data whose coordinates are already correct but unlabeled. Projecting transforms the coordinates. Mixing them up corrupts data: defining a new CRS onto already-correct data teleports it to the wrong place. This is
Define ProjectionvsProjectin ArcPy,ST_SetSRIDvsST_Transformin PostGIS,.set_crs()vs.to_crs()in GeoPandas. Know which one the situation calls for.
Why this matters
A CRS mismatch rarely throws an error — it returns confident, wrong answers: features that don't intersect when they should, distances off by orders of magnitude, layers stacked in the wrong hemisphere. These bugs look like valid output, so they pass review and reach the map, where someone in the field catches them. Thirty seconds of CRS checking prevents an entire class of them.
What ships with it
1 file 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.
- 6d ago First seen · 25 lines · 66 tokens per session scan A b6bce4d5b451
crs-discipline is a skill published in the GitHub repository buildmoonshot/skillpacks (2 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 610 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 2026-08-31.
Other skills, from other repositories
drug-discovery
Drug discovery: ChEMBL search, drug-likeness, interactions.
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
arxiv
Search arXiv papers by keyword, author, category, or ID.
data-warehouse-experimentation
Running experiments out of the data warehouse instead of via dedicated experiment platforms. SQL-based assignment, exposure logging discipline, metric definitions in dbt models, statistical analysis in SQL or Python, variance reduction with CUPED, sequential testing, and the operational tradeoffs vs platforms like…
acl-experiments
Use when designing or auditing experiments for an ACL paper, covering tuned LLM baselines, multi-dataset and multilingual evaluation, statistical significance and variance, human evaluation with agreement reporting, contamination and prompt-sensitivity controls, ablations, and error-analysis expectations in NLP…