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-attack-surfacenpx skills add kdr/overcast --skill overcast-attack-surfacegit clone --depth 1 https://github.com/kdr/overcastWhat 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 | $0.00044 | $0.01539 |
| Opus 5 | $0.00022 | $0.00770 |
| Sonnet 5 | $0.00009 | $0.00308 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
overcast-attack-surface 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 3d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
overcast-attack-surface
Use this skill to inventory a target's internet-exposed infrastructure with
Shodan: open ports, products/versions, banners, TLS certs, and known CVEs, keyed
by org, network, hostname, or a single IP. Use the broad overcast skill and
overcast/reference/verbs.md for exact flags.
⚠️ Authorized recon only. Shodan reports real hosts' exposed services and vulnerabilities. Run it only against infrastructure you are permitted to investigate.
shodanis never a default source — you bind it deliberately.
Setup
overcast doctor --sources --json # confirm SHODAN_API_KEY is set
overcast case init --json
overcast case setup --target "<org or domain>" --yes --json
overcast source add 'shodan:org:"<Org Name>"' --json # register the shodan source
Enumerate the surface
Each host hit carries ip/port/transport/org/product/cpe/os/vulns
- geolocation in the payload;
media.refis theshodan.io/host/<ip>report page, so--pullstores a real evidence page. The ad-hoc--queryoverrides the bound ref, so one registered source serves every pivot.
overcast scan --source shodan --limit 25 --pull --json # the bound org query
overcast scan --source shodan --query 'net:<CIDR>' --limit 25 --pull --json # pivot by IP range
overcast scan --source shodan --query 'ssl:<domain>' --limit 25 --pull --json # pivot by TLS certificate
overcast scan --source shodan --query 'hostname:<domain>' --limit 25 --pull --json
overcast scan --source shodan --query '<ip>' --json # deep-dive ONE host: full service map
Useful filters for --query: org:"…", net:<CIDR>, ssl:<domain>,
hostname:<domain>, product:<name>, port:<n>, country:<ISO2>,
vuln:<CVE> (membership). Every service on a host is a distinct hit (the
media.ref/url carry a #<port>-<transport> fragment), so monitor catches
newly exposed ports on an already-seen IP.
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.
- 3d ago First seen · 119 lines · 44 tokens per session scan A c36088765bd4
overcast-attack-surface is a skill published in the GitHub repository kdr/overcast (15 stars, last pushed 7d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,539 once invoked, about $0.0002 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…
orchestrator-container-spawn
Spawning and hardening scan containers from the recon orchestrator: the security flags that look correct and break the container, and the sibling bind-mount path handling. capdrop and no-new-privileges were each reverted after breaking real scans. Trigger: editing reconorchestrator/containermanager.py; changing how a…
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…
add-partial-recon
Adding partial-recon support for a tool: running a single pipeline phase on demand from the workflow graph, reading its inputs from the existing Neo4j graph and merging results back. The input-node map decides the modal UI, and some input types must never be manually entered. Trigger: adding a tool to partial recon; a…
frame-flowchart-sticky
SVG 曲线连接 + 便利贴节点 + 光标交互, 像白板 brainstorm.