Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kdr/overcastnpx agentmods add skills/kdr/overcast/overcast-camera-ballisticsWrote 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-camera-ballistics)<a href="https://agentmods.dev/skills/kdr/overcast/overcast-camera-ballistics"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-camera-ballistics.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.00985 |
| Opus 5 | $0.00032 | $0.00492 |
| Sonnet 5 | $0.00013 | $0.00197 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
overcast-camera-ballistics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
overcast-camera-ballistics
Use this skill to answer "were these shot on the same camera?": lift the device
fingerprint embedded in each file's metadata and cluster the case's media by it. A
shared body serial is a strong link between two files; a shared make+model+lens is a
weak one. Use the broad overcast skill and overcast/reference/verbs.md for
exact flags. EXIF is free — read it before anything billed.
Workflow
- Lift the fingerprint from every image/video.
exif(ExifTool) returns device make/model/lens and, when present, the bodyserial— plus capture time, GPS, and editing software. Loop it over the case's media so every file has anexifrecord:
overcast doctor --json
overcast case init --json
overcast exif ./photo1.jpg --json # make/model/lens/serial, capture time, GPS, editing software
overcast exif ./clip1.mp4 --json
for f in ./media/*.jpg ./media/*.mp4; do overcast exif "$f" --json; done # batch the whole case
- Roll the case up by camera fingerprint.
devicesgroups theexifrecords into shared-device clusters (one entry per file);--min Nsets the smallest cluster to report,--findingsemits suggested findings for serial-linked (strong) clusters:
overcast devices --min 2 --json # every camera shared by >=2 files
overcast devices --min 2 --findings --json # + suggested findings for serial-linked clusters
- Read the strength honestly, then promote. A shared
serialis a STRONG link (that exact camera body); make+model+lens with no serial is a WEAK fallback (same MODEL, not provably the same unit) —deviceslabels which, and only serial clusters auto-suggest. Triage and record with the right confidence:
overcast finding list --state triage --json
overcast finding accept <id> --target <target-id> --json # a serial-linked cluster onto its line
overcast note "clip1.mp4 + photo1.jpg share body serial <serial> — same camera (strong); editing-software field set on photo1 → possible re-save" --ref <exif-record-id> --confidence high --json
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.
- 7d ago First seen · 82 lines · 65 tokens per session scan A a66523bdf74d
overcast-camera-ballistics is a skill published in the GitHub repository kdr/overcast (16 stars, last pushed 4d ago), licensed Apache-2.0. It adds 65 tokens to every session and 985 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
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.
frame-light-leak-cinema
Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.
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…
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…
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…
frame-glitch-title
A design template for a glitch-style title frame in Chinese, intended for a video transition, hero image, or cyberpunk graphic. It describes dark backgrounds, distorted lettering, colored offsets, scan lines, noise, and timecode details.