overcast-bolo

overcast-bolo is a skill for Claude Code from kdr/overcast. It costs 56 tokens per session (1,854 once invoked), scanned A, original, Apache-2.0.

A continuous visual watchlist that checks incoming media for a match to a reference face or image. It sends possible matches to a review queue and raises alerts.

In plain words
What is it for?
Use it for an ongoing be-on-the-lookout search across incoming media, with possible matches collected for review.
Why use it?
It removes the need to inspect every new photo or video manually when looking for one known person or image.

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

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-bolo
Any agent
npx skills add kdr/overcast --skill overcast-bolo
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-bolo

README.md
[![agentmods](https://agentmods.dev/badge/skills/kdr/overcast/overcast-bolo.svg)](https://agentmods.dev/skills/kdr/overcast/overcast-bolo)
Your own site
<a href="https://agentmods.dev/skills/kdr/overcast/overcast-bolo"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-bolo.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,854 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 $0.00056 $0.01854
Opus 5 $0.00028 $0.00927
Sonnet 5 $0.00011 $0.00371
Haiku 4.5 $0.00006 $0.00185

Measured 5d ago against content hash fdaf39a7f1ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

overcast-bolo 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-bolo/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

overcast-bolo

Use this skill for a be-on-the-lookout / all-points-bulletin: "here is a face, alert me on any match across incoming media." It is a standing watch keyed on a VISUAL reference (a face or image), not a one-shot lineup search. Use the broad overcast skill and overcast/reference/verbs.md for exact flags. Only leave a continuous loop running when the user asks for ongoing monitoring.

This packages existing machinery: a target --image is the reference line hits attach to, monitor --pull --pipe captures + senses new media, and the persist hook auto-runs the score triggers on every evidence record — a face --match ≥75 (or similar match ≥85) auto-emits a suggested finding linked to that line. The BOLO flow names and sequences those pieces. It is the close cousin of overcast-stakeout (a general standing watch, often keyed on a text target) and overcast-lineup (a one-shot identify against a local face DB); reach for those when the watch is text-keyed or the job is a single database lookup.

Prerequisites

Pick the matcher up front — it decides the backend the watch needs:

  • tinycloud face (default face provider): CLOUDGLUE_API_KEY set, tinycloud CLI on PATH. No local Python. face <clip> --match <ref> runs against the clip.
  • deepface-local (offline, no cloud): the uv-managed visual-DB Python (scripts/visual-db-uv.sh --face, then OC_VISUAL_DB_PY). Reference faces live in a local deepface-local index; similar match uses a local basic-clip index instead. Nothing leaves the case.
overcast doctor --json                 # confirm the face/visual-db backend is ready
overcast case init --json

Workflow

  1. Register the watchlist reference. The reference face becomes an image target — the line of investigation every hit attaches to. Add one target per person/object you are looking out for:
overcast target add ./suspect.jpg --image --question "Does the watchlisted person appear in incoming media?" --json
overcast target list --json                                  # confirm the image line (kind: image)

Read the full file on GitHub · 146 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 · 146 lines · 56 tokens per session scan A fdaf39a7f1ad

Subscribe to this mod's changes

overcast-bolo is a skill published in the GitHub repository kdr/overcast (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,854 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.

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