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.
npx skills add kdr/overcast --skill overcast-verify-mediagit clone --depth 1 https://github.com/kdr/overcastWrote 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-verify-media)<a href="https://agentmods.dev/skills/kdr/overcast/overcast-verify-media"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-verify-media/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.
<a href="https://agentmods.dev/skills/kdr/overcast/overcast-verify-media"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-verify-media.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00060 | $0.01064 |
| Opus 5 | $0.00030 | $0.00532 |
| Sonnet 5 | $0.00012 | $0.00213 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
overcast-verify-media 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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
overcast-verify-media
Use this skill to assess whether a media file was manipulated or staged. Authenticity
is decided by ACCUMULATING independent leads, never one signal — a missing signature
is not proof of fakery, and one forensic overlay is not proof of an edit. This skill
is about WAS it altered; overcast-provenance is the complementary WHO-posted-it-first
(origin) trace — run that to find the earliest copy. Use the broad overcast skill
and overcast/reference/verbs.md for exact flags.
Workflow
- Check embedded provenance FIRST (free).
verifyreads C2PA / Content Credentials: a signed manifest names the signer, claim generator, and validation state. No manifest is a cleanreadyrecord, NOT proof of fakery — most files simply have none:
overcast doctor --json
overcast case init --json
overcast verify ./suspect.jpg --json # C2PA: has_manifest, signer, validation state (needs c2patool)
- Read the capture metadata (free).
exifsurfaces editing software (a re-save flag), the capture time to compare against the claimed time, and the device — each a lead, not a verdict:
overcast exif ./suspect.jpg --json # editing software, capture time, device, GPS (needs exiftool)
- Run the forensic overlays as edit-detection LEADS, and LOOK at them.
enhance --ops elawrites ELA / noise / luminance maps that can highlight a spliced or pasted region — a heuristic, so view the output, don't trust the label:
# --ops ela needs a bound enhance provider (once per profile). The shipped ela
# choice needs only pillow + numpy — no fal key:
overcast provider setup apply --verb enhance --choice ela --yes
overcast enhance ./suspect.jpg --ops ela --json # ELA/noise/luminance overlays (or a bound local-models / fal provider)
overcast view <ela-record-id> --json # eyeball the overlays — inconsistent regions are the lead
- If the file carries (or claims) a time and place, cross-check the sun. With GPS
present (from
exif) or supplied,chronolocate --at-timecomputes the expected shadow direction/length for the claimed time — a mismatch flags a mis-dated or staged image:
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.
- 9d ago First seen · 88 lines · 60 tokens per session scan A f9b2a1d7e02b
overcast-verify-media is a skill published in the GitHub repository kdr/overcast (16 stars, last pushed 6d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,064 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.