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 opencv-realtime-cameragit 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/opencv-realtime-camera)<a href="https://agentmods.dev/skills/hipson47/hipson/opencv-realtime-camera"><img src="https://agentmods.dev/badge/skills/hipson47/hipson/opencv-realtime-camera.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 | $0.00032 | $0.00960 |
| Opus 5 | $0.00016 | $0.00480 |
| Sonnet 5 | $0.00006 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
opencv-realtime-camera 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 7d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCV Realtime Camera
Purpose
Own bounded frame acquisition and lifecycle behavior for images, video files, and local cameras. Produce a reusable frame source that model-specific skills can consume without duplicating capture, timing, error, or cleanup logic.
Use When
- A Python workflow reads a webcam, video file, image sequence, or single image.
- A demo needs FPS measurement, frame sampling, preview, recording, or capture fallback behavior.
- OpenCV color conversion, resizing, or frame timestamps need explicit rules.
Do Not Use When
- Browser
getUserMediaand MediaPipe own the full pipeline. - The task is model selection, annotation, dataset splitting, or HTTP upload.
- A still-image library already satisfies the requirement without a frame loop.
Inputs
- Source kind and allowlisted camera index or bounded local file path.
- Expected width, height, frame rate, sampling interval, and stop condition.
- Required color space and preprocessing contract.
- Preview/output policy, retention policy, and deterministic fixture path.
- Target OS, headless/GUI environment, and CPU/GPU assumptions.
Default Stack
- Python, NumPy, and
opencv-pythonfor an explicitly local GUI demo. opencv-python-headlessfor servers, CI, and non-GUI processing.- Monotonic timing, bounded queues, CPU baseline, and a prerecorded fixture.
- One OpenCV wheel variant per environment; never install GUI and headless variants together.
Workflow
- Inspect existing dependency and media-path conventions. Request approval before adding OpenCV or changing a lockfile.
- Define one frame-source interface for image, video, and camera inputs. Never accept an arbitrary remote URL or shell-expanded path as a camera source. Resolve local paths and enforce approved-root containment after symlink resolution before opening a source or output.
- Open the source, check
isOpened, validate everyreadresult, and reject empty or unexpectedly large frames before downstream work. - Make resize, aspect-ratio, channel order, dtype, normalization, and timestamp behavior explicit. Do not let capture and model code disagree about BGR/RGB.
- Bound runtime with a stop key, cancellation signal, frame count, or timeout. Avoid an unbounded producer when inference is slower than capture.
- Measure warm-up separately and report processed FPS plus dropped/skipped frames over a defined interval.
- Put capture release, writer release, and window teardown in reliable cleanup paths that run on success, error, and cancellation.
- Provide a static image or prerecorded video fallback for CI and machines without a camera.
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.
- 7d ago First seen · 105 lines · 32 tokens per session scan A 00211024b160
opencv-realtime-camera is a skill published in the GitHub repository Hipson47/Hipson (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 960 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.
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.
kirby-forms-and-frontend-actions
Implements frontend forms and actions in Kirby (contact forms, file uploads, email with attachments, creating pages from frontend). Use when handling user input or building submission flows.