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 agentmods add skills/kdr/overcast/overcast-scannernpx skills add kdr/overcast --skill overcast-scannergit 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-scanner)<a href="https://agentmods.dev/skills/kdr/overcast/overcast-scanner"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-scanner.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00066 | $0.01021 |
| Opus 5 | $0.00033 | $0.00511 |
| Sonnet 5 | $0.00013 | $0.00204 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
overcast-scanner 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 4d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
overcast-scanner
Use this skill to watch police CAD / calls-for-service over an area in near-real
time. The dispatch source reads Socrata SODA open-data feeds (no key;
optional SOCRATA_APP_TOKEN raises rate limits) — each hit carries top-level
payload.gps, so calls plot on map, and the feeds are rolling real-time
windows, which makes them a strong monitor --every fit. Use the broad
overcast skill and overcast/reference/verbs.md for exact flags.
Workflow
- Register a dispatch feed. Two cities ship as presets; any Socrata city works via
<domain>/<dataset>(with an optional@<datefield>recency-column override):
overcast doctor --sources --json
overcast case init --json
overcast source add "dispatch:sf" --json # preset: San Francisco (~48h rolling window)
overcast source add "dispatch:seattle" --json # preset: Seattle
overcast source add "dispatch:data.cityofchicago.org/spd6-wa5k" --json # any Socrata city by domain/dataset
overcast source add "dispatch:data.example.gov/abcd-1234@call_datetime" --json # override the recency column
- Validate with a single scan before leaving a loop running — confirm rows parse and carry gps/call-type/id columns (auto-detected per row):
overcast scan --source dispatch --limit 20 --json
- Stand the scanner up.
media.refis a stable per-row SODA deep link, which is the monitor dedup key, so re-polls don't re-surface the same call:
overcast monitor --once --json # one diff pass, scheduler-friendly
overcast monitor --source dispatch --every 15m --limit 20 --json # rolling real-time watch
- Plot the geolocated calls and triage them against the case. Hits carry
payload.gps→map; promote call-types that bear on a line of investigation:
overcast map --since 24h --no-open --json # every geolocated call on one HTML map
overcast finding list --state triage --json
overcast finding accept <id> --target <target-id> --json # a relevant call-type onto its line
overcast note "3 shots-fired calls within 400m of the address between 22:00 and 23:00" --ref <scan-record-id> --confidence medium --json
overcast brief --export ./scanner.html --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.
- 4d ago First seen · 86 lines · 66 tokens per session scan A fe58fa83e4df
overcast-scanner is a skill published in the GitHub repository kdr/overcast (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 1,021 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.
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…
redamon-testing
How RedAmon tests actually run and how to author them: the per-file Docker gate, the unit/integration/live tiers, and the failure modes that make a green run a lie. Trigger: editing any test.py, .test.ts(x) or tests/.sh; a test that is red, skipped or xfailed; a request to "run the tests", "make it green" or check…
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…
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.
motion-frames
可循环 CSS 动效组合: 旋转环、地球仪、计时器、视差标签.