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 aeren23/image-processing-skills --skill 05-contour-analysisgit clone --depth 1 https://github.com/aeren23/image-processing-skillsWrote 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/aeren23/image-processing-skills/05-contour-analysis)<a href="https://agentmods.dev/skills/aeren23/image-processing-skills/05-contour-analysis"><img src="https://agentmods.dev/badge/skills/aeren23/image-processing-skills/05-contour-analysis/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/aeren23/image-processing-skills/05-contour-analysis"><img src="https://agentmods.dev/badge/skills/aeren23/image-processing-skills/05-contour-analysis.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 | $0.00022 | $0.01219 |
| Opus 5.5 | $0.00009 | $0.00488 |
| Sonnet 5.5 | $0.00004 | $0.00244 |
| Haiku 4.5 | $0.00002 | $0.00122 |
Grade A, and why
contour-analysis 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 1mo 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contour Analysis
When to Use This Skill
- Counting objects in an image
- Measuring object area, perimeter, or physical dimensions
- Classifying shapes (round vs elongated, regular vs irregular)
- Medical image analysis (tumor shape assessment)
- Drawing bounding boxes or centroids on detected objects
Decision Framework
Shape Metric Selection
| Metric | Formula | Range | Tells You |
|---|---|---|---|
| Aspect Ratio | width / height | 0→∞ | Shape elongation (1.0 = square/circle) |
| Extent | Object Area / Bounding Box Area | 0→1.0 | How much the box is filled |
| Solidity | Object Area / Convex Hull Area | 0→1.0 | Surface regularity (1.0 = smooth, <1.0 = irregular) |
| Eccentricity | Minor Axis / Major Axis | 0→1.0 | Circularity (0 = circle, 1 = line) |
Medical Application — Tumor Shape Classification
Solidity value?
├── ≈ 1.0 (smooth, convex surface)
│ └── Likely BENIGN — regular, well-defined boundary
│
└── << 1.0 (irregular, spiculated surface)
└── Likely MALIGNANT — irregular projections, infiltrative margin
Solidity is a gold-standard feature in medical image analysis for distinguishing benign vs malignant masses. Convex Hull wraps the object tightly — if the actual area is much smaller than the hull, the surface has indentations/spikes (suspicious morphology).
Contour Finding Parameters
| Parameter | Recommended | Alternative | When |
|---|---|---|---|
| Mode | RETR_EXTERNAL |
RETR_TREE |
External = outer boundaries only. Tree = nested hierarchy |
| Method | CHAIN_APPROX_SIMPLE |
CHAIN_APPROX_NONE |
Simple = corner points only (saves memory). None = all boundary pixels |
Critical Gotchas
1. Image MUST Be Binary Before findContours
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
_, binary = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
contours, _ = cv2.findContours(binary, cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
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.
- 1mo ago First seen · 141 lines · 22 tokens per session scan A 58721b7a8e58
contour-analysis is a skill published in the GitHub repository aeren23/image-processing-skills (7 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 1,219 once invoked, about $0.0001 per session on Opus 5.5. 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
3d-slicer
Automate 3D Slicer research workflows with MRML, VTK/ITK, DICOM data, and Segment Editor. Use for software workflows, not clinical interpretation.
horos
Configure Horos DICOM and PACS workflows, automate DCMTK transfers, and troubleshoot plugins without interpreting clinical findings.
drug-repurposing
Reason about drug repurposing strategies in HCLS — choosing between target-based and phenotype-based approaches, evaluating mechanism-of-action overlap, querying drug-gene interaction databases, assessing clinical translatability, and ranking candidates by evidence strength. Use when the user asks to repurpose a drug…
genomic-variant-interpretation
Reason about germline and somatic variant classification using ACMG/AMP 2015 and AMP/ASCO/CAP frameworks. Use when the user asks to classify a variant, interpret a VCF annotation, resolve a VUS, apply ACMG criteria, weigh ClinVar evidence, evaluate gnomAD allele frequencies, interpret REVEL/CADD/SpliceAI scores…
pharmacoepidemiology
Reason about pharmacoepidemiologic study design for causal inference from real-world data — choosing active comparator new-user designs, emulating target trials, avoiding immortal time bias, handling time-varying confounding with marginal structural models, and selecting propensity score methods. Use when the user…
biomarker-discovery
Reason about biomarker discovery and validation in HCLS — classifying biomarker intent, choosing feature-selection and cross-validation strategies, avoiding leakage, and planning external replication. Use when the user asks to discover, develop, or validate a biomarker; select features from high-dimensional omics or…