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 phishing-triagegit 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/phishing-triage)<a href="https://agentmods.dev/skills/vigil-soc/vigil/phishing-triage"><img src="https://agentmods.dev/badge/skills/vigil-soc/vigil/phishing-triage/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/phishing-triage"><img src="https://agentmods.dev/badge/skills/vigil-soc/vigil/phishing-triage.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 | $0.00041 | $0.01393 |
| Opus 5.5 | $0.00016 | $0.00557 |
| Sonnet 5.5 | $0.00008 | $0.00279 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
phishing-triage 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phishing triage
Use this for a reported email. Judge from raw_data, iocs and description.
If you hold only an id and you hold get_finding, fetch the finding first. If
no tool is callable this turn, judge from the input in front of you and still
finish the report. Never end the turn on a tool call you announced, and never
invent a lookup, a click, or a domain age.
Extract
From the finding, note the display name, envelope from, reply-to and sender
domain; the recipients; the subject; each URL's display text and destination;
each attachment's name, type and hash; and SPF, DKIM and DMARC when present.
A field the finding does not contain is unknown.
Checks
Call a tool only when it is in your grant and callable this turn. Otherwise record the gap and continue.
recall_entityon the sender domain and each URL, if you hold it. Whether that sender or URL has already hit other users:search_findings, if you hold it. If you hold neither, or you cannot call them, writenot checked.- Domain age is
not checkedunless a tool returned it. Never guess one. - Reputation of each URL and each file hash: read
ioc-enrichmentwhen you holdread_skill, and follow that skill for the lookup. Do not restate its procedure, and do not end on its indicator report. What it returns is evidence for this verdict. A reputation check you did not run isnot queried. - Note the pretext: urgency, a request for a password or code, a payment or bank-detail change, executive impersonation (a leader's or the company's display name on a domain that is not the recipient's).
- Note whether the link destination host differs from the text the user sees, and the attachment type (macro-enabled Office, executable, script, disk).
- The recipient clicked or opened something only when the finding says so.
user-actionisclickedoropenedin that case,reported-onlywhen the finding says they reported it and did not click or open, andunknownwhen it is silent.
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 · 111 lines · 41 tokens per session scan A e2c4fc5d1660
phishing-triage is a skill published in the GitHub repository Vigil-SOC/vigil (374 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 1,393 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.