classify-or-flag

classify-or-flag is a skill for Claude Code from Borda/vision-delivery. It costs 144 tokens per session (1,123 once invoked), scanned A, original, Apache-2.0.

A whole-image classification workflow that returns one verdict, such as pass or fail, a category, or an anomaly flag. An anomaly is an image that differs from what is expected.

In plain words
What is it for?
Use it for image-level quality checks, product categories, compliance decisions, defect flags, and other binary or multi-class judgments about a complete image.
Why use it?
It keeps image-wide decisions separate from tasks that must locate individual objects or defective regions.

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

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.

agentmods
npx agentmods add skills/borda/vision-delivery/classify-or-flag
Any agent
npx skills add Borda/vision-delivery --skill classify-or-flag
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 classify-or-flag

README.md
[![agentmods](https://agentmods.dev/badge/skills/borda/vision-delivery/classify-or-flag.svg)](https://agentmods.dev/skills/borda/vision-delivery/classify-or-flag)
Your own site
<a href="https://agentmods.dev/skills/borda/vision-delivery/classify-or-flag"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/classify-or-flag.svg" alt="Measured on agentmods" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,123 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00144 $0.01123
Opus 5 $0.00072 $0.00562
Sonnet 5 $0.00029 $0.00225
Haiku 4.5 $0.00014 $0.00112

Measured 6d ago against content hash b13e1662e7ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

classify-or-flag 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.

claude-skills/classify-or-flag/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Produce one verdict for the whole image that supports a named business action and passes independent acceptance. This covers binary or multi-class labels, image-level compliance, and anomaly flagging. It does not localize individual objects.

Platform execution boundary. Read ../../resources/roboflow-platform-lookup.md before any provider-specific search, dataset, training, inference, 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. Keep volatile model names, IDs, request shapes, and platform sequences out of Sentinel.

Follow ../../resources/fde-methodology.md; apply these classification-specific rules.

1. Resolve the output unit

Inspect existing images, labels, code, and operating procedure. Confirm that the required output is one verdict for the whole image. If the action must identify which worker lacks equipment, route per-person PPE to detect-and-analyze. If it needs the defective region, route to detection or segmentation.

Ask only missing operational questions:

  • What exact action follows each class or flag?
  • Which error costs more: a missed positive or a false alarm?
  • What class balance and operating conditions occur in production?

Freeze before candidate search:

Acceptance ID: <session/revision>
Business decision: <action enabled by each image verdict>
Gold set: <independent labels, split, class counts, adjudicator>
Primary metric and threshold: <F1/recall/precision/exact accuracy>
Secondary guardrails: <per-class floor, false alarms, latency>
Frozen before baseline: <timestamp and confirmation>
Baseline result (diagnostic only): <not run yet>

2. Define labels and abstention

Write a mutually understandable class dictionary with positive/negative examples and ambiguous-case handling. Define whether the system may abstain or send low-confidence cases to a human. Prevent data leakage by grouping near-duplicates, bursts, products, sites, or subjects before splitting.

Read the full file on GitHub · 96 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. 6d ago First seen · 96 lines · 144 tokens per session scan A b13e1662e7ee

Subscribe to this mod's changes

classify-or-flag is a skill published in the GitHub repository Borda/vision-delivery (4 stars, last pushed 26d ago), licensed Apache-2.0. It adds 144 tokens to every session and 1,123 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

Computer Vision Helper

Assist with image analysis, object detection, and visual AI tasks.

eddiebelaval/squire · 16 tokens

moss-formulas-variables

Create or edit Moss formulas and variables, including UI entry, persisted Markdown, linked instances, derived values, bound references, IDs, and stale metadata.

brsbl/moss-skills · 37 tokens

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

optimize-claude-opus-5-prompts

Clarify, audit, and rewrite rough or existing prompts for Claude Opus 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt, system prompt, or agent harness for Claude Opus 5 (claude-opus-5), including requests phrased as Opus 5 prompt…

IchenDEV/prompt-optimizer-plugins · 182 tokens

optimize-claude-fable-5-prompts

Clarify, audit, and rewrite rough or existing prompts for Claude Fable 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt for Claude Fable 5, including requests phrased as Fable or Fabel prompt optimization, Fable/Fabel 提示词优化, or when an…

IchenDEV/prompt-optimizer-plugins · 137 tokens