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 solve-cv-taskgit 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/solve-cv-task)<a href="https://agentmods.dev/skills/borda/vision-delivery/solve-cv-task"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/solve-cv-task/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/solve-cv-task"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/solve-cv-task.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 | $0.00123 | $0.01297 |
| Opus 5.5 | $0.00049 | $0.00519 |
| Sonnet 5.5 | $0.00025 | $0.00259 |
| Haiku 4.5 | $0.00012 | $0.00130 |
Grade A, and why
solve-cv-task 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Be Sentinel's low-barrier front door. Translate the user's operational outcome into the correct CV output, independent acceptance gate, fastest safe proof, and explicit next route—without requiring them to know CV terminology.
Roboflow platform knowledge lookup. Read ../../resources/roboflow-platform-lookup.md. Sentinel owns stable solution-building discipline. Installed official Roboflow skills or current MCP resources own exact product/model/tool truth. If neither is available, continue provider-neutral work and use a scaffold; never copy or guess a volatile platform recipe.
1. Read before asking
Inspect the user's files, sample images/clips, code, README, labels, and existing evaluation artifacts. Summarize the observable problem in plain language. Ask at most three questions that artifacts cannot answer:
- “What should happen when the camera sees the target?”
- “Out of 100 real cases, how many misses or false alarms are acceptable for a first proof?”
- “Where will images come from, and may they leave this machine/site?”
For a novice, define only the next needed term. Use “catch rate” before introducing recall and “false-alarm rate” before precision.
2. Route by required output
| User needs | Route | Key discriminator |
|---|---|---|
| boxes, object count, crops, per-object metadata, per-person PPE | detect-and-analyze |
one output per visible instance |
| one verdict for the whole image, including whole-image compliance | classify-or-flag |
one label/flag per image |
| masks, contours, area, crack width, calibrated physical measurement | segment-and-analyze |
pixel geometry and calibration |
| persistent identity, crossings, paths, dwell, video events | track-and-count |
association across frames |
| text, numbers, serials, forms, codes, meters | read-text |
character/field extraction |
| keypoints, joint angles, posture, gestures, actions | recognize-pose-or-gesture |
skeleton/keypoint semantics |
| several perception/rule/aggregation stages | decompose-to-pipeline |
end-to-end staged decision |
| annotation/training/deployment economics or crossover | estimate-economics |
economic decision, not build |
| accepted model/pipeline needs package, integration, monitoring, deployment | deliver-cv-project |
capability already measured |
| setup/authentication health | check-sentinel-setup or auth-setup |
environment/connection issue |
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 · +3 lines 713240ac4085
- 1mo ago First seen · 100 lines · 123 tokens per session scan A 40bc2df97fcf
solve-cv-task is a skill published in the GitHub repository Borda/vision-delivery (4 stars, last pushed 16d ago), licensed Apache-2.0. It adds 123 tokens to every session and 1,297 once invoked, about $0.0005 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.