segment-and-analyze

segment-and-analyze is a skill for Claude Code from Borda/vision-delivery. It costs 136 tokens per session (1,116 once invoked), scanned A, original, Apache-2.0.

An image-analysis workflow that outlines objects or defects in pictures and calculates measurements such as area, shape, perimeter, or width. It can distinguish pixel results from real-world measurements that need calibration.

In plain words
What is it for?
Use it to outline damage, cracks, corrosion, lesions, or other objects, and to calculate their size or shape from images.
Why use it?
It helps turn visual observations into measured results while showing when those results are not reliable physical dimensions. It also sets an acceptance check for the output.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the sentinel plugin — 13 skills, 2 agents, 1 hook, 1 MCP server shipped together

Good fit Use it to outline damage, cracks, corrosion, lesions, or other objects, and to calculate their size or shape from images.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/borda/vision-delivery/segment-and-analyze
Install

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.

Any agent
npx skills add Borda/vision-delivery --skill segment-and-analyze
Clone the repo
git clone --depth 1 https://github.com/Borda/vision-delivery

Made for: Claude Code.

Or install sentinel, the plugin that ships this one along with the rest of its 13 skills, 2 agents, 1 hook, 1 MCP server.

Wrote 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.

agentmods badge for segment-and-analyze

README.md
[![agentmods](https://agentmods.dev/badge/skills/borda/vision-delivery/segment-and-analyze/github.svg)](https://agentmods.dev/skills/borda/vision-delivery/segment-and-analyze)
Your own site
<a href="https://agentmods.dev/skills/borda/vision-delivery/segment-and-analyze"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/segment-and-analyze/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.

agentmods 80×15 button for segment-and-analyze

Your own site · 80×15
<a href="https://agentmods.dev/skills/borda/vision-delivery/segment-and-analyze"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/segment-and-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00136 $0.01116
Opus 5 $0.00068 $0.00558
Sonnet 5 $0.00027 $0.00223
Haiku 4.5 $0.00014 $0.00112

Measured 9d ago against content hash c688ced05d11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

segment-and-analyze 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 9d 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.

claude-skills/segment-and-analyze/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Produce masks and derived measurements that clear an independently labeled acceptance gate. Pixel results are not physical measurements unless calibration, camera geometry, and uncertainty support that claim.

Platform execution boundary. Read ../../resources/roboflow-platform-lookup.md before any provider-specific search, dataset, training, inference, workflow, or deployment action. Use installed official Roboflow skills or current MCP resources only for read-only discovery and sourced action-brief inputs; never invoke provider execution. Sentinel retains the measurement contract and evidence.

Follow ../../resources/fde-methodology.md; apply these segmentation-specific requirements.

1. Define mask ownership and decision

Inspect images, masks, calibration artifacts, code, and intended action. Ask at most three missing questions:

  • Is the business action driven by outline, area, maximum width, or presence?
  • What independently produced masks or physical reference measurements exist?
  • Must the answer be pixels/relative area, or real-world units?

Freeze before measuring a candidate:

Acceptance ID: <session/revision>
Business decision: <action enabled by mask/measurement>
Gold set: <independent masks or sensor measurements, split, adjudicator>
Primary metric and threshold: <IoU/Dice/area error/width error>
Secondary guardrails: <boundary error, false masks, latency, calibration uncertainty>
Frozen before baseline: <timestamp and confirmation>
Baseline result (diagnostic only): <not run yet>

Visual inspection without gold masks may guide diagnosis but cannot produce IoU or Dice.

2. Define the geometry contract

Record mask encoding, coordinate origin, image dimensions, empty-mask behavior, overlap ownership, and whether holes/disconnected components are retained. For derived values, define:

  • area: mask pixel count and any conversion factor;
  • perimeter/boundary: contour method and smoothing policy;
  • width: the geometric definition, not merely a box width;
  • physical units: calibration target, plane, camera setup, distortion correction, and propagated uncertainty.

Read the full file on GitHub · 94 lines

Changes

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.

  1. 9d ago First seen · 94 lines · 136 tokens per session scan A c688ced05d11

Subscribe to this mod's changes

segment-and-analyze is a skill published in the GitHub repository Borda/vision-delivery (4 stars, last pushed 28d ago), licensed Apache-2.0. It adds 136 tokens to every session and 1,116 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

pipeline

Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…

kardebadas/claude-plugin · 80 tokens

craft

Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…

kardebadas/claude-plugin · 83 tokens

bug-fix

Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.

kardebadas/claude-plugin · 74 tokens

bug-investigate

Use when someone wants to know WHY something is broken and has not asked for it to be fixed — "why is this happening", "what's causing this error", "find out what's wrong", "diagnose this before we decide". Also use before committing to a fix, when the cause is unknown and the decision depends on it. Not for fixing …

kardebadas/claude-plugin · 83 tokens

setup

Use when superb's skills need their dependencies installed or checked — "set up superb", "install the dependencies", "why does pipeline say superpowers is missing", after a fresh plugin install, or on a new machine. Also use when a skill fails complaining that a superpowers sub-skill cannot be found.

kardebadas/claude-plugin · 64 tokens

boundedrelay-adaptive-sdd

Coordinate the optional BoundedRelay Spec Kit workflow with strict independent reviews, deterministic effort routing, bounded proposals, convergence, and handoff.

mohammad19974/bounded-relay · 34 tokens