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 Vigil-SOC/vigil --skill beaconing-reviewgit clone --depth 1 https://github.com/Vigil-SOC/vigilWrote 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/vigil-soc/vigil/beaconing-review)<a href="https://agentmods.dev/skills/vigil-soc/vigil/beaconing-review"><img src="https://agentmods.dev/badge/skills/vigil-soc/vigil/beaconing-review/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/vigil-soc/vigil/beaconing-review"><img src="https://agentmods.dev/badge/skills/vigil-soc/vigil/beaconing-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00051 | $0.01374 |
| Opus 5.5 | $0.00020 | $0.00550 |
| Sonnet 5.5 | $0.00010 | $0.00275 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
beaconing-review 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 23d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beaconing review
Grade one periodic outbound flow. Extract the facts, apply the first matching
rule, and finish with the labelled block. When no tool is callable in this
turn, do not announce a lookup and do not stop: reputation is not checked,
and the block is still written from the finding alone.
Facts
From raw_data, take src_ip, the destination, dst_port, bytes_sent,
bytes_received, and frequency. The destination is dst_ip when that
field is present; otherwise dst_host or dst_domain. A domain or IP in
iocs does not replace dst_ip. The title and description are where a
source labels the flow as C2.
Note the source host's role from src_ip (an RFC 1918 address is an internal
client). Role explains who is phoning out. It does not pick the verdict.
Jitter is absent when frequency states one period. "every 60 seconds" and
"every 300 seconds" are fixed intervals with no jitter, including when the
text itself says "fixed" or "no jitter". A span ("40 to 110 seconds"), or
"roughly", "about", or an unnegated "jitter", means jitter is present.
Reputation
Name a tool only when you hold it:
- If you hold
recall_entity, call it on the destination before any external lookup. - If you hold
lookup_indicators, query the local feed for that indicator. - If you hold
cf_lookup_ip_threat, use it for an IP. If you holdcf_lookup_domain_threat, use it for a hostname.
A check you could not run is written not checked. Never invent a lookup
result. When the destination needs a full enrichment, read ioc-enrichment
and follow it. Do not restate that procedure here.
Look-alikes
A fixed interval is normal for every row below. It does not make the flow a beacon. A bare IP is none of these rows. Port 443 or 80 to a bare IP is not an update check. Port 123 to a bare IP is not NTP.
- NTP. Hostname is an NTP pool or vendor time host (
pool.ntp.org,time.google.com,time.windows.com,time.cloudflare.com), port 123, payloads small and symmetric (a few dozen bytes each way, including 48 and 48). A fixed 300 second poll with no jitter still matches. - Update check. Hostname is the vendor's update host
(
windowsupdate.microsoft.com,update.microsoft.com,download.windowsupdate.com,archive.ubuntu.com), port 80 or 443, client payload small. A fixed interval, including 300 seconds, still matches. Symmetric small payloads match this row too. - Monitoring agent. Hostname is the vendor's monitor (Datadog, New Relic, Elastic) and payloads are small check-ins on that vendor's usual port.
- Telemetry. Hostname is the vendor's own telemetry host and payloads are small regular posts.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago First seen · 114 lines · 51 tokens per session scan A 42c94ce1e536
beaconing-review is a skill published in the GitHub repository Vigil-SOC/vigil (374 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 1,374 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-24.
Other skills, from other repositories
analyzing-network-traffic-with-wireshark
Captures and analyzes network packet data using Wireshark and tshark to identify malicious traffic patterns, diagnose protocol issues, extract artifacts, and support incident response investigations on authorized network segments.
scrape-batch
Extract many known URLs in one polite, rate-limited pass. Use when the user hands over a list of links, a set of search hits to read in full, or asks to "scrape these pages" / "pull the content from all of them". Drives extract(action="batch"), which fans out with per-domain rate limiting and returns partial results…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
research-topic
Multi-step research orchestration. Use when user asks "research X", "summarize current state of Y", "what's the latest on Z", or compares approaches. Calls extract(action="agent") which searches the web, extracts top results, then synthesises a citation-preserving Markdown answer with one configured LLM.
temporal-query
Answer time-travel questions over stored memory — what was believed at a past point in time, when a belief changed, and what replaced it. Use when the user says "as of", "back in", "at the time", "history of", "timeline", "what did I think then", or asks why a current memory contradicts an older one.
knowledge-audit
Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.