cv-problem-solver

A problem-solving role for computer-vision tasks, where software analyzes images or video to detect, count, track, measure, or read things. It is an adapter that routes these questions to a separate vision-delivery workflow.

In plain words
What is it for?
Use it when you want to build or evaluate a capability such as detecting objects, counting items, tracking movement, reading text, or measuring something in images or footage.
Why use it?
It gives image and video problems a defined starting point instead of requiring users to know which model or method to choose first.

Agent

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 agents/borda/vision-delivery/cv-problem-solver
Clone the repo
git clone --depth 1 https://github.com/Borda/vision-delivery
Per session 174 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 348 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 $0.00174 $0.00348
Opus 5 $0.00087 $0.00174
Sonnet 5 $0.00035 $0.00070
Haiku 4.5 $0.00017 $0.00035

Measured 2d ago against content hash 69720fd534df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cv-problem-solver 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 2d 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.

agents/cv-problem-solver.md · 22 lines

What it actually says

This is the Claude Code adapter for the vision-delivery problem-solver entry point.

The canonical Claude recipe lives in claude-skills/solve-cv-task/SKILL.md. Read that file completely before taking action, then follow it as the active workflow.

Keep this adapter thin:

  • Preserve Claude-specific frontmatter here: tools, model, color, and trigger text.
  • Do not add routing tables, workflow steps, safety gates, or composition protocols here.
  • When behavior changes, edit claude-skills/solve-cv-task/SKILL.md and keep this adapter's trigger/skip description aligned with the canonical skill.
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. 2d ago First seen · 22 lines · 174 tokens per session scan A 69720fd534df

Subscribe to this mod's changes

cv-problem-solver is an agent published in the GitHub repository Borda/vision-delivery (4 stars, last pushed 22d ago), licensed Apache-2.0. It adds 174 tokens to every session and 348 once invoked, about $0.0009 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 agents, from other repositories

HANDOFF

State: verified locally — publication and external CI remain user-owned.

mohammad19974/bounded-relay · 0 tokens

arckit-datascout

Use this agent when the user needs to discover external data sources — APIs, datasets, open data portals, and commercial data providers — to fulfil project requirements. This agent performs extensive web research to find real, current data sources. Examples: Context: User has a project with requirements and wants to…

tractorjuice/arckit-codex · 398 tokens

arckit-gov-landscape

Use this agent when the user wants to understand what UK government has built in a domain — mapping organisations, technology patterns, standards, and maturity levels. Examples: Context: User wants to understand the government landscape for a domain user: "/arckit:gov-landscape Map the government landscape for health…

tractorjuice/arckit-codex · 320 tokens

arckit-research

Use this agent when the user needs technology and service market research for a project, including build vs buy analysis, vendor evaluation, TCO comparison, and UK Government Digital Marketplace search. This agent performs extensive web research autonomously. Examples: Context: User has a project with requirements and…

tractorjuice/arckit-codex · 358 tokens

arckit-aws-research

Use this agent when the user needs AWS-specific technology research using the AWS Knowledge MCP server to match project requirements to AWS services, architecture patterns, Well-Architected guidance, and Security Hub controls. Examples: Context: User has a project with requirements and wants AWS service…

tractorjuice/arckit-codex · 389 tokens

arckit-azure-research

Use this agent when the user needs Azure-specific technology research using the Microsoft Learn MCP server to match project requirements to Azure services, architecture patterns, Well-Architected guidance, and Security Benchmark controls. Examples: Context: User has a project with requirements and wants Azure service…

tractorjuice/arckit-codex · 388 tokens