By Borda Verified
Business-first computer vision delivery guide for Claude Code and Codex. Turn an operational goal into a scoped proof plan, verified evidence, costs, and a decision.
Computer-vision problem solver. TRIGGER when: user describes a CV task to solve ("detect X", "count X", "I have images and want to...", "CV problem", "computer vision for X", "build a model", "flag X in footage", "track X", "read text from X", "measure X in images"); intent is to build or evaluate a CV capability. SKIP when: user asks an economics-only question about annotation cost, training cost, deployment cost, or scale with no unsolved build problem in play (route to economics-consultant); user asks a pure Roboflow platform how-to question with an already-working model; user invokes `$estimate-economics` in Codex or `/sentinel:estimate-economics` in Claude Code (economics-consultant handles it).
Computer-vision economics consultant. TRIGGER when: user invokes `$estimate-economics` in Codex or `/sentinel:estimate-economics` in Claude Code, asks for annotation or labeling cost, training cost, managed vs self-hosted cost, build-vs-buy, scale economics, deployment crossover, or selected the "managed at scale" / "deploy to a managed endpoint" branch from the build-flow seam offer. SKIP when: user is still in build work with no working PoC in play, including requests to build a detector, detect damaged boxes, count objects, read text, track people, or use sample images (route to cv-problem-solver); user asks a pure platform how-to question; user has not yet reached a passing eval on their problem unless they explicitly accept a rough estimate.
Connect or troubleshoot Sentinel's URL-only Roboflow MCP sign-in. TRIGGER when: the user asks to connect Roboflow, sign in, authorize OAuth, configure the plugin, or diagnose unavailable/unauthorized Roboflow MCP tools; the user asks whether a Roboflow API key is required for plugin installation. SKIP when: Roboflow MCP tools already work; the task is purely local, such as discussing a labeling approach for raw footage, and needs no Roboflow operation; a generated standalone client needs credentials (delegate its exact auth shape to the current official Roboflow API/inference skill).
Run an offline Sentinel package doctor and separate local installation defects from host enablement or Roboflow sign-in problems. TRIGGER when: the user asks to check, verify, diagnose, or troubleshoot a Sentinel plugin installation; run the setup doctor; find missing skills, packaged files, or Roboflow tools; or confirm Sentinel installed correctly. SKIP when: Sentinel and Roboflow work and the user wants to count boxes or solve a CV task; the package is healthy but OAuth/sign-in alone failed (auth-setup); or the request is deployment economics/crossover only (estimate-economics).
Produce one whole-image verdict: pass/fail, category, compliance, or anomaly. TRIGGER when: user asks whether an image is defective/compliant; to flag bad parts, classify product images, run image-level quality control, detect an anomaly, or build binary/multi-class classification. SKIP when: user asks how many boxes/pallets or for other object counts or per-person PPE (detect-and-analyze); masks/area (segment-and-analyze); identity across video (track-and-count); OCR/codes (read-text); to compare self-hosting vs managed or cost only (estimate-economics); or delivery/export of a working classifier (deliver-cv-project).
Generate a portable stakeholder decision report for a CV deployment decision. TRIGGER when: user explicitly asks for a decision report, manager report, or stakeholder doc after a cost crossover has been computed; phrases: "write me a decision report", "generate a report for my manager", "I need a stakeholder doc", "produce the decision doc", "decision-report skill", "report for my team". SKIP when: no cost crossover exists yet — estimate-economics must run first and deliver a crossover number; user is still in build work; user wants a one-paragraph summary (answer inline instead).
Decompose a complex vision-and-reasoning requirement into the cheapest measurable pipeline. TRIGGER when: user asks to monitor/alert, analyze footage over time, combine perception with aggregation/reporting, determine whether something is feasible to detect (including sensor limits or smoldering), or replace repeated vision-language calls with a cheaper system. SKIP when: the request is single-frame detection/counting (detect-and-analyze), whole-image classification (classify-or-flag), deployment cost only (estimate-economics), or the pipeline is already working and needs delivery (deliver-cv-project).
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Verified owner:Jirka Borovec
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
vision-delivery ships the sentinel plugin for Codex and Claude Code. Tell it the operational outcome you need from images or video; it helps turn that request into a measurable computer-vision proof, checks a baseline before recommending training, and frames the cost and next decision.
Sentinel is designed to lower the computer-vision methodology burden. You do not need to arrive knowing model families, metric names, or Roboflow APIs. You still own four things the plugin cannot infer safely: permission to use the data, the business outcome, representative examples, and the consequence of a wrong answer. Production acceptance remains a human decision.
"Count pallets crossing this line and report the hourly total. I have 60 sample frames.
A missed pallet is worse than a duplicate count."
Sentinel should turn that into a task definition, success gate, baseline, evidence artifact, and go/no-go recommendation—not a model shopping list.
| Support tier | Meaning | Current scope |
|---|---|---|
| 🕰️ Historical evidence | A recorded result exists with its original limits; it is not a current support guarantee. | One pre-v0.2 Claude routing run, a synthetic process A/B, and one small private detection fixture. |
| 🧩 Guided | The plugin contains a structured workflow, but the route lacks equivalent live end-to-end evidence. | Detection, classification, tracking, OCR, segmentation, pose/gesture, multi-step decomposition, delivery, and economics. |
| 🔗 Delegated upstream | Sentinel frames and evaluates the work; current product details come from the official source. | Roboflow MCP operations, model IDs, Workflows, plans, pricing, and platform navigation. |
| 🧑⚖️ Expert required | Do not rely on the plugin alone. | Regulated or safety-critical decisions, people surveillance, medical use, physical measurement, production streaming/edge architecture, legal review, and final production sign-off. |
Read Support & Evidence before treating a guided route as production-ready.
npx claudepluginhub borda/vision-delivery --plugin sentinelOSS Claude Code config: agents, skills, and hooks for professional AI-assisted development workflows
OSS maintenance plugin: agents (shepherd, cicd-steward, gh-scraper, repo-warden) and skills (analyse, resolve, review, release)
Implementation workflow skills: feature, fix, refactor, plan, debug, review
ML research skills: topic, plan, judge, run, sweep, verify, fortify, retro
Codebase structural index - scan Python projects once, query the import graph for blast-radius and coupling before touching code — Python projects only
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.