overcast-crime-board

overcast-crime-board is a skill for Claude Code from kdr/overcast. It costs 47 tokens per session (1,009 once invoked), scanned A, original, Apache-2.0.

A visual investigation board for arranging faces, objects, video clips, and their connections. It turns collected evidence into a CSI-style brief and a live monitoring wall.

In plain words
What is it for?
Use it to create reusable face and object image cards, link the same person across clips, connect related themes, and present case evidence visually.
Why use it?
It removes the need to keep relationships between scattered media in your head or in separate notes. The visual layout makes repeated people, objects, and themes easier to compare.

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 create reusable face and object image cards, link the same person across clips, connect related themes, and present case evidence visually.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kdr/overcast/overcast-crime-board
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-crime-board
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-crime-board

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kdr/overcast/overcast-crime-board"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-crime-board.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,009 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 $0.00047 $0.01009
Opus 5 $0.00023 $0.00504
Sonnet 5 $0.00009 $0.00202
Haiku 4.5 $0.00005 $0.00101

Measured 10d ago against content hash 487730be5956, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

overcast-crime-board 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.

skills/overcast-crime-board/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

overcast-crime-board

Use this skill when the case has accumulated media and you want the "red-string corkboard": the people, objects, and connections laid out visually. It composes existing evidence into two shareable surfaces. Use the broad overcast skill and overcast/reference/verbs.md for exact flags.

Workflow

  1. Materialize the evidence cards — faces and objects as durable crops (run face --thumbnails first so crop has frame images to cut from). Object cards need a bound open-vocabulary detector (OWLv2): crop cuts from detection boxes, so bind a detector as the see provider before --detect, then crop the --detect record (a caption/OCR see record has no boxes to crop):
overcast doctor --json
overcast face ./clip.mp4 --thumbnails --json
overcast crop <face-record-id> --all --class face --square --pad 0.1 --json
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 ./clip.mp4 --detect "car, bag, weapon, phone" --json
overcast crop <detect-record-id> --all --kind object --json   # crop the --detect record (it has boxes)
  1. Draw the strings — link the same person across clips with the local face DB, and connect visual themes with CLIP semantic search:
overcast index create people --type face-cluster --local --json
overcast cluster add ./clip.mp4 --index <cluster-index-id> --json
overcast cluster identify ./person-of-interest.jpg --index <cluster-index-id> --json
overcast index create scenes --type basic-clip --local --json
overcast similar add ./clip.mp4 --index <clip-index-id> --json
overcast similar search "red backpack on a bicycle" --index <clip-index-id> --json
  1. Record the connections as notes so they land on the board:

Read the full file on GitHub · 87 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. 10d ago First seen · 87 lines · 47 tokens per session scan A 487730be5956

Subscribe to this mod's changes

overcast-crime-board is a skill published in the GitHub repository kdr/overcast (16 stars, last pushed 7d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,009 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.