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 kdr/overcast --skill overcast-enhance-and-resolvegit clone --depth 1 https://github.com/kdr/overcastWrote 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/kdr/overcast/overcast-enhance-and-resolve)<a href="https://agentmods.dev/skills/kdr/overcast/overcast-enhance-and-resolve"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-enhance-and-resolve/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/kdr/overcast/overcast-enhance-and-resolve"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-enhance-and-resolve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00956 |
| Opus 5 | $0.00026 | $0.00478 |
| Sonnet 5 | $0.00010 | $0.00191 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
overcast-enhance-and-resolve 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 10d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
overcast-enhance-and-resolve
Use this skill for the "zoom in… enhance" task: a plate, a face, or on-screen text
is too small or noisy to read, and you need to recover it and cite it honestly. Use
the broad overcast skill and overcast/reference/verbs.md for exact flags.
Workflow
- Ingest the raw clip and pin the moment worth resolving:
overcast doctor --json
overcast case init --json
overcast watch ./raw.mp4 --json
overcast note "plate unreadable, want to resolve" --ref <watch-record-id> --at 41-44 --json
- Enhance that segment. The bundled ffmpeg ops are
denoise, normalize, voice-isolate, upscale, stabilize, grayscale; the enhanced file comes back as amedia.enhancedrecord you chain forward:
overcast enhance ./raw.mp4 --ops denoise,upscale,stabilize --json
- Re-read the enhanced output.
--ocrrecovers text (a caption/OCR record, no boxes);--detectlocates a region and needs a bound detector (bind OWLv2 as theseeprovider first) — it produces the record with boxes thatcropcuts from:
overcast see frame://<enhanced-record-id>@<seconds> --ocr --json # -> <ocr-record-id> (text, no boxes)
scripts/visual-db-uv.sh --detect # once: uv-installs torch+transformers+scipy, prints DETECT_PY
export DETECT_PY="$DETECT_PY"; overcast provider setup apply --preset owl-local --yes --json # owl-local persists a portable shipped: ref for detect.py + uses $DETECT_PY (the venv python; system python3 lacks the deps)
overcast see frame://<enhanced-record-id>@<seconds> --detect "license plate, text" --json # -> <detect-record-id> (boxes)
- Materialize the resolved region as durable cropped evidence — crop the
--detectrecord (the--ocrrecord has no boxes to crop):
overcast crop <detect-record-id> --all --class "license plate" --pad 0.15 --square --json
- Record what was recovered with its provenance. State the ops applied and the
source record in the finding, keep a before/after note pair, and cite both the
raw and enhanced
record.id:
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.
- 10d ago First seen · 79 lines · 51 tokens per session scan A dbacffba31d0
overcast-enhance-and-resolve is a skill published in the GitHub repository kdr/overcast (16 stars, last pushed 7d ago), licensed Apache-2.0. It adds 51 tokens to every session and 956 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
frame-data-chart-nyt
NYT-newsroom typography, staggered reveal animation, and editorial-grade charts (line, bar, or range band).
frame-flowchart-sticky
SVG curve connectors, sticky-note nodes, and cursor interaction with a whiteboard-brainstorm feel.
frame-glitch-title
Digital glitch, chromatic offset, and data-corruption title frame for video transitions or cyberpunk heroes.
frame-light-leak-cinema
Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.
frame-logo-outro
Segmented logo assembly, glow bloom, and tagline reveal for video outros or brand closing frames.
vfx-text-cursor
Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.