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-canvassWrote 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-canvass)<a href="https://agentmods.dev/skills/kdr/overcast/overcast-canvass"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-canvass.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 | $0.00078 | $0.01310 |
| Opus 5 | $0.00039 | $0.00655 |
| Sonnet 5 | $0.00016 | $0.00262 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade A, and why
overcast-canvass 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 8d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
overcast-canvass
Use this skill to run the "door-to-door camera canvass" around a point: which
public cameras sit near a location. It is almost entirely existing sources — the
overpass source reads OpenStreetMap fixed-camera nodes near a point, and the
webcam source lists live public webcams near a point. The only new primitive is
a forward geocode (address → coordinates) on the shipped geocode provider.
Use the broad overcast skill and overcast/reference/verbs.md for exact flags.
overpass camera hits carry top-level payload.gps, so they plot on map
directly. webcam hits are live stills that carry payload.lat/payload.lng
(not payload.gps), so they do not appear as map markers — review them as
image evidence (open the still / note the coordinates) rather than expecting them
on the map. Treat everything as leads, not a complete inventory — OSM cameras
are crowd-mapped (incomplete), and webcams are whatever public cams happen to be
registered nearby.
Workflow
1. Get a point (<lat>,<lng>)
The canvass runs on coordinates. If you already have them (a map pin, an exif
GPS fix, a chronolocate/scene-locate result), use them directly. To turn a
street address into a point, use the shipped geocode provider's forward
mode (OSM Nominatim, no key — same opt-in privacy note as reverse geocoding:
it egresses the queried address to a third party):
# forward geocode: address -> {lat,lng,place}
bash providers/senses/geocode/geocode.sh --query "350 Fifth Ave, New York, NY" --json
# -> {"verb":"geocode","payload":{"place":"Empire State Building, ...","lat":40.748,"lng":-73.985,"mode":"forward"},"state":"ready"}
Read payload.lat / payload.lng for the point. A non-match returns a clean
ready record with place:null (never a crash); point OVERCAST_GEOCODE_URL at
your own Nominatim/Photon endpoint for volume.
2. Fan the camera sources around the point at a radius
Register both camera sources centered on the point, then scan. man_made=surveillance
is the primary OSM tag for a fixed camera; man_made=camera catches some
mappings; surveillance:type / camera:* subtags carry direction/mount detail
on the nodes that have them.
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.
- 8d ago First seen · 102 lines · 78 tokens per session scan A 542e2c20d803
overcast-canvass is a skill published in the GitHub repository kdr/overcast (16 stars, last pushed 5d ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,310 once invoked, about $0.0004 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.