overcast-presence-window

overcast-presence-window is a skill for Claude Code from kdr/overcast. It costs 35 tokens per session (549 once invoked), scanned A, original, Apache-2.0.

A procedure for finding the time interval during which a person or object appears in a video. It starts from one confirmed appearance and searches earlier and later frames until the target is no longer present.

In plain words
What is it for?
Use it to track a specific person with a reference photo or check an object across video frames, controlling the time range, sampling rate, and match threshold.
Why use it?
It answers when something was visible, rather than returning only one matching frame or timestamp.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the overcast plugin — 35 skills, 1 hook shipped together

Good fit Use it to track a specific person with a reference photo or check an object across video frames, controlling the time range, sampling rate, and match threshold.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kdr/overcast/overcast-presence-window
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.

Any agent
npx skills add kdr/overcast --skill overcast-presence-window
Clone the repo
git clone --depth 1 https://github.com/kdr/overcast

Made for: Claude Code.

Or install overcast, the plugin that ships this one along with the rest of its 35 skills, 1 hook.

Wrote 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.

agentmods badge for overcast-presence-window

README.md
[![agentmods](https://agentmods.dev/badge/skills/kdr/overcast/overcast-presence-window/github.svg)](https://agentmods.dev/skills/kdr/overcast/overcast-presence-window)
Your own site
<a href="https://agentmods.dev/skills/kdr/overcast/overcast-presence-window"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-presence-window/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.

agentmods 80×15 button for overcast-presence-window

Your own site · 80×15
<a href="https://agentmods.dev/skills/kdr/overcast/overcast-presence-window"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-presence-window.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 549 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00035 $0.00549
Opus 5 $0.00017 $0.00275
Sonnet 5 $0.00007 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured 8d ago against content hash 9a2c494a870a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

overcast-presence-window 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.

skills/overcast-presence-window/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

overcast-presence-window

Use this skill to answer "from when to when is on screen?" — a first/last appearance interval, not a single instant. It anchors one confirmed appearance and expands until the target stops appearing, the presence-tracking analog of a temporal search. Use the broad overcast skill and overcast/reference/verbs.md for exact flags.

Workflow

  1. Local clip + record id:
overcast doctor --json
overcast case init --json
overcast watch ./clip.mp4 --json        # -> record id REC
  1. Anchor one appearance (whichever fits the target):
overcast face ./clip.mp4 --match ./person.jpg --json          # a specific person (similarity 0-100)
overcast grid ./clip.mp4 --count 16 --json                    # then see the montage for an object
  1. Sweep outward from the anchor until K consecutive misses on each side:
# person: widen the window; --fps controls sample density (precision vs cost)
overcast face ./clip.mp4 --match ./person.jpg --start <a> --end <b> --fps 1 --min-similarity 55 --json
# object: step frames outward and check presence
overcast see frame://REC@<t> --prompt "Is <target> present? answer only yes or no" --json
  1. Emit the presence interval(s) and show them:
overcast note "<target> present" --ref REC --at <first-last> --confidence medium --json
overcast view REC --at <first-last> --json
overcast brief --export ./presence.md --json

Output

One or more [first-last] intervals with the per-hit citations (record.id + media.at) that bound them, and the sample density used. If the target leaves and returns, report each interval separately rather than one span covering the gap.

Caveats

Sampled detections are per-frame, not continuous — presence between samples is inferred; raise --fps to tighten boundaries at higher cost. Occlusion or an off-camera moment splits one presence into several intervals — that's a real result, not noise. Face similarity is 0-100. Needs the video local.

Read the full file on GitHub · 63 lines

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. 8d ago First seen · 63 lines · 35 tokens per session scan A 9a2c494a870a

Subscribe to this mod's changes

overcast-presence-window is a skill published in the GitHub repository kdr/overcast (16 stars, last pushed 5d ago), licensed Apache-2.0. It adds 35 tokens to every session and 549 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 2026-08-30.