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 Impertio-Studio/QGIS-Claude-Skill-Package --skill qgis-errors-projectionsgit clone --depth 1 https://github.com/Impertio-Studio/QGIS-Claude-Skill-PackageWrote 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/impertio-studio/qgis-claude-skill-package/qgis-errors-projections)<a href="https://agentmods.dev/skills/impertio-studio/qgis-claude-skill-package/qgis-errors-projections"><img src="https://agentmods.dev/badge/skills/impertio-studio/qgis-claude-skill-package/qgis-errors-projections/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/impertio-studio/qgis-claude-skill-package/qgis-errors-projections"><img src="https://agentmods.dev/badge/skills/impertio-studio/qgis-claude-skill-package/qgis-errors-projections.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 | $0.00099 | $0.04546 |
| Opus 5 | $0.00049 | $0.02273 |
| Sonnet 5 | $0.00020 | $0.00909 |
| Haiku 4.5 | $0.00010 | $0.00455 |
Grade A, and why
qgis-errors-projections 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 12d 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 — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qgis-errors-projections
Quick Reference
CRS Error Decision Table
| Symptom | Likely Cause | Jump To |
|---|---|---|
| Layer appears in wrong continent/ocean | Wrong EPSG code assigned | ERR-001 |
| Layer offset by ~100-200 meters | Missing datum transformation | ERR-003 |
| Layer appears stretched/squashed | Geographic CRS used for projected operations | ERR-001 |
| Coordinates swapped (X/Y flipped) | lat/lon vs lon/lat confusion | ERR-002 |
| Layer invisible (but valid) | CRS mismatch hidden by OTF reprojection | ERR-004 |
| Geometry operations return wrong values | Silent CRS corruption from wrong assignment | ERR-005 |
| Transform produces NaN or inf | QgsCoordinateTransform without context | ERR-006 |
| All CRS operations fail in standalone script | Missing srs.db (prefix path not set) | ERR-007 |
Critical Warnings
NEVER assign a CRS to "fix" misplaced data -- assigning a CRS changes interpretation, NOT coordinates. Use QgsCoordinateTransform to reproject.
NEVER create QgsCoordinateTransform without a QgsCoordinateTransformContext -- the bare constructor ignores datum transformation preferences and silently degrades accuracy.
NEVER assume QgsPointXY(x, y) matches the axis order of the EPSG definition -- QGIS ALWAYS uses lon/lat (x/y) order internally, regardless of the EPSG standard axis order.
NEVER ignore crs.isValid() == False -- an invalid CRS propagates silently through ALL downstream operations, producing wrong results without errors.
ALWAYS use QgsProject.instance().transformContext() for coordinate transforms -- it contains user-configured datum transformation preferences.
ALWAYS verify CRS validity immediately after creation with crs.isValid().
ALWAYS check crs.isGeographic() before performing distance/area calculations -- geographic CRS units are degrees, not meters.
Error Catalog
ERR-001: Wrong EPSG Code Selected
Symptoms:
- Layer appears in the wrong geographic location (wrong continent, ocean, or hemisphere)
- Layer appears extremely stretched or compressed
- Coordinates have unexpected magnitude (e.g., values in millions when expecting degrees)
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.
- 12d ago First seen · 492 lines · 99 tokens per session scan A 67badea17b03
qgis-errors-projections is a skill published in the GitHub repository Impertio-Studio/QGIS-Claude-Skill-Package (33 stars, last pushed 2mo ago), licensed MIT. It adds 99 tokens to every session and 4,546 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
opengis-all
Use when navigating end-to-end GIS workflows — discover the full toolchain from GDAL data processing through GeoServer publishing to CesiumJS/OpenLayers visualization. One-stop index covering the complete open-source GIS data pipeline.
threejs-errors-performance
Use when a Three.js scene has performance problems: low FPS, memory leaks, too many draw calls, or high GPU memory usage. Prevents the common mistake of forgetting dispose(), creating objects in the render loop, or not using InstancedMesh for repeated objects. Covers disposal patterns, draw call optimization…
threejs-errors-rendering
Use when a Three.js scene renders incorrectly: black screen, invisible objects, wrong colors, z-fighting, or broken shadows. Prevents the common mistake of wrong color space, missing material.side, or forgetting updateProjectionMatrix. Covers all common rendering errors with diagnosis steps and fix patterns. Keywords…
n8n-errors-connection
Use when troubleshooting API connection failures, credential errors, or timeout issues in n8n. Prevents misdiagnosis by providing deterministic symptom-cause-fix tables. Covers API failures, credential errors, timeout configuration, SSL/TLS issues, webhook URL problems (test vs production), rate limiting, queue mode…
n8n-errors-expressions
Use when debugging expression evaluation failures or undefined references in n8n workflows. Prevents data access errors by mapping every expression variable to its valid context. Covers undefined $json references, type mismatches, missing paired items, $itemIndex unavailability in Code node, $secrets restriction in…
n8n-errors-execution
Use when debugging workflow execution failures or implementing error recovery in n8n. Prevents silent failures by enforcing the 4 error handling patterns. Covers node failures, timeout handling, continueOnFail pattern, Error Trigger node, error workflows, retry on fail configuration, Stop And Error node, and execution…