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 Hipson47/Hipson --skill cv-project-routergit clone --depth 1 https://github.com/Hipson47/HipsonWrote 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/hipson47/hipson/cv-project-router)<a href="https://agentmods.dev/skills/hipson47/hipson/cv-project-router"><img src="https://agentmods.dev/badge/skills/hipson47/hipson/cv-project-router.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.00889 |
| Opus 5 | $0.00015 | $0.00445 |
| Sonnet 5 | $0.00006 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
cv-project-router 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 8d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computer Vision Project Router
Purpose
Turn a CV request into a small, explicit workflow before implementation begins. Select only the skills needed for the input modality, CV capability, execution target, privacy boundary, output artifacts, and verification environment.
Use When
- The request names a goal but not a model, runtime, or input source.
- Work spans capture, inference, datasets, demos, verification, or a web app.
- The team must choose between server-side Python and browser-side processing.
Do Not Use When
- The user already selected a single CV skill and its boundaries are clear.
- The task is generic image generation, design critique, or media editing.
- The task asks for identity recognition, biometric classification, surveillance, or medical diagnosis; escalate instead of routing to an implementation.
Inputs
- Goal and acceptance criteria.
- Input modality: image, upload, video file, webcam, frame stream, or dataset.
- CV task: detection, segmentation, tracking, pose, gestures, preprocessing, extraction, labeling, or evaluation.
- Target runtime, latency, hardware, privacy, retention, and offline constraints.
- Expected JSON, annotated media, UI events, metrics, and demo artifacts.
Default Stack
- Python, OpenCV, and NumPy for local image/video processing.
- Ultralytics YOLO only after a model and license decision.
- MediaPipe in the browser for supported gesture or pose interactions.
- Next.js App Router as frontend/BFF and FastAPI/Pydantic as the Python API.
- CPU baseline, local processing, no retention, deterministic fixtures.
Workflow
- Inspect the repository, manifests, existing API contracts, test commands, media paths, and privacy policy before proposing tools or dependencies.
- Classify modality, CV task, runtime, latency, hardware, privacy, and outputs.
- Choose a bounded stack:
- camera/video acquisition:
opencv-realtime-camera; - YOLO inference:
yolo-detector; - hands/gestures/pose UI:
mediapipe-human-interface; - frames/labels/splits/formats:
dataset-builder; - local presentation layer:
vision-demo-builder; - HTTP/browser application:
cv-webapp-starter.
- camera/video acquisition:
- Keep no more than four worker skills active. Drop the router from context after recording the decision when the workflow is clear.
- Add
vision-verifierto every implementation workflow and define a prerecorded or static fixture when hardware is optional or unavailable. - Record dependency, model-download, license, media-consent, and network gates.
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.
- 8d ago First seen · 100 lines · 31 tokens per session scan A b61b33c378a5
cv-project-router is a skill published in the GitHub repository Hipson47/Hipson (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 889 once invoked, about $0.0002 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.
Other skills, from other repositories
sc-skill
Capture deterministic macOS screenshots for testing, docs, release notes, and marketing assets. Use when asked to automate app screenshots, batch-generate screenshot sets, standardize window sizing/composition, or choose between Peekaboo and native macOS screenshot tooling.
agent-session-format-check
Verify agent session format compatibility for Agent Sessions. Use when any agent CLI updates, when monitoring flags drift, or when bumping max verified versions (fixtures + docs + tests). Covers session schema, usage/limits tracking, storage backends, and discovery path contracts for all supported agents.
handover
Use when wrapping up or capturing the current state of a coding session — writes a short, dated entry to the repo's RepoHandover.md so a future agent or you can resume without grepping archived sessions. Triggers on "handover", "hand off", "write handover", "capture state", "checkpoint this session".
agent-support-matrix
Maintain Agent Sessions agent support matrix and JSON/JSONL parsing compatibility. Use when checking upstream agent releases for session format changes, updating max verified versions in docs/agent-support/agent-support-matrix.yml, or updating docs/agent-json-tracking.md and fixtures/tests.
kirby-collections-and-navigation
Builds Kirby listings, pagination, search, filtering/sorting/grouping, and navigation menus. Use when implementing collection logic in templates/controllers/snippets.
kirby-debugging-and-tracing
Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.