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 Borda/vision-delivery --skill classify-or-flaggit clone --depth 1 https://github.com/Borda/vision-deliveryWrote 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/borda/vision-delivery/classify-or-flag)<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/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/borda/vision-delivery/classify-or-flag"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/classify-or-flag.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 | $0.00144 | $0.01141 |
| Opus 5.5 | $0.00058 | $0.00456 |
| Sonnet 5.5 | $0.00029 | $0.00228 |
| Haiku 4.5 | $0.00014 | $0.00114 |
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 15d 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 — 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 outside the host-gated path. 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.
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.
- 15d ago Changed dbd75a9433bd
- 1mo ago First seen · 96 lines · 144 tokens per session scan A b13e1662e7ee
classify-or-flag is a skill published in the GitHub repository Borda/vision-delivery (4 stars, last pushed 16d ago), licensed Apache-2.0. It adds 144 tokens to every session and 1,141 once invoked, about $0.0006 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
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…
Computer Vision Helper
Assist with image analysis, object detection, and visual AI tasks.
xllm-setup
Setup and doctor for xllm. Creates artifact dirs, remembers advisor script path for this project, checks cloud/local providers, and prints recommended commands.
pipeline
Use when the user asks to take a substantial feature from an initial idea through implementation in one mostly autonomous run.
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.
optimize-claude-opus-5-prompts
A prompt-editing skill for clarifying and rewriting prompts intended for Anthropic’s Claude Opus 5 model.