overcast-where

overcast-where is a skill for Claude Code, Codex from kdr/overcast. It costs 37 tokens per session (627 once invoked), scanned A, original, Apache-2.0.

A visual-analysis skill that finds a named object in a video or image frame, crops the detected area, and checks the crop with an AI vision model. The detector proposes coordinates, while the vision check confirms that the crop contains the intended object.

In plain words
What is it for?
Use it to locate a target at a particular moment, create a padded bounding box and crop, and verify that the detected region really shows the requested object.
Why use it?
Language-based vision models are unreliable when asked to produce exact pixel coordinates. Using a dedicated detector first and then verifying the crop helps prevent incorrect boxes from being treated as evidence.

Skill for Claude CodeCodex

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

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.

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

Made for: Claude Code, Codex.

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-where

README.md
[![agentmods](https://agentmods.dev/badge/skills/kdr/overcast/overcast-where.svg)](https://agentmods.dev/skills/kdr/overcast/overcast-where)
Your own site
<a href="https://agentmods.dev/skills/kdr/overcast/overcast-where"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-where.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 627 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.00627
Opus 5 $0.00018 $0.00313
Sonnet 5 $0.00007 $0.00125
Haiku 4.5 $0.00004 $0.00063

Measured 5d ago against content hash 0627f32232c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

overcast-where 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 5d 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-where/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

overcast-where

Use this skill to turn a moment into spatial evidence: a bounding box on the target plus a verified crop. It follows the detector-proposes / VLM-verifies pattern (open-vocab detection like OWLv2, then confirm the crop) — because chat VLMs are unreliable at emitting raw coordinates, so a real detector draws the box and the VLM only judges the crop. Use the broad overcast skill and overcast/reference/verbs.md for exact flags.

Setup

see --detect needs a detection provider bound (boxes come from OWLv2, not the brain LLM):

scripts/visual-db-uv.sh --detect     # once: prints DETECT_PY (the venv python)
export DETECT_PY="$DETECT_PY"; overcast provider setup apply --preset owl-local --yes --json  # persists a portable shipped: ref for detect.py + the venv python

Workflow

  1. Have the moment (use overcast-pinpoint / overcast-frame-grid): timestamp T on record REC.

  2. Detect the target in that frame, then materialize + verify the box:

overcast see frame://REC@T --detect "<target phrase>" --json      # -> see record with detections[]
overcast crop <see-record-id> --all --class "<target phrase>" --pad 0.15 --json
overcast see <crop-path> --prompt "Does this crop show <target>? yes/no + describe" --json

The re-see of each crop is what kills false positives — open-vocab detectors emit confident boxes for almost any phrase at low thresholds.

  1. Optionally sharpen the exhibit and record the finding:
overcast enhance <crop-path> --ops upscale,denoise --json
overcast finding create "<target> located at T" --ref <see-record-id> --confidence medium --json
overcast brief --export ./where.md --json

Output

Per confirmed target: the timestamp, the box (from the see --detect record), the crop path, and the verification verdict. Cite the see detection record.id + media.at; note the crop is the durable, memory-friendly evidence artifact.

Caveats

Never ask the brain LLM for coordinates directly — bind a detector and verify crops. Detector confidence is not calibrated across free-form phrases: a high score on a rare phrase can still be wrong, so the crop re-check decides. For a specific PERSON, use face --match instead of --detect. Boxes are per sampled frame, not tracks.

Read the full file on GitHub · 65 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. 5d ago First seen · 65 lines · 37 tokens per session scan A 0627f32232c7

Subscribe to this mod's changes

overcast-where is a skill published in the GitHub repository kdr/overcast (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 627 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.

Related

Other skills, from other repositories

video-to-skill

Turn a video, tutorial, playlist, or course into an installed, evidence-grounded course Skill that can teach, give practice and feedback, apply demonstrated methods, and answer reference questions. Use when the user provides video sources and wants reusable learning or operational capability.

Lum1104/video-to-skill · 57 tokens

frame-light-leak-cinema

Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.

nexu-io/open-design · 31 tokens

osmedeus-expert

Expert guide for the Osmedeus security automation workflow engine. Use when: (1) writing or editing YAML workflows (modules and flows), (2) running osmedeus CLI commands (scan, workflow management, installation, server), (3) configuring steps, runners, triggers, or template variables, (4) debugging workflow execution…

j3ssie/osmedeus · 113 tokens

recon-tool-integration

Adding a new tool to the recon pipeline: the enrichment-module contract and its isolated wrapper (the actual fan-out and test call path), graph completeness, and the preset catalog that silently strips unknown settings. Miss the isolated wrapper and the tool never runs in parallel; miss the catalog and AI presets drop…

samugit83/redamon · 114 tokens

supply-chain-scan

Working on RedAmon's supply-chain scanner (offline OSV + GuardDog + retire + trufflehog): the offline OSV database that the scan path does not bootstrap, the world-readable requirement for the hardened scanner, and the soft-error markers that record what was never analysed. Trigger: editing…

samugit83/redamon · 115 tokens

frame-glitch-title

数字故障 / 像散偏移 / 数据腐败标题, 适合视频转场 / cyberpunk hero.

nexu-io/html-anything · 31 tokens