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 ioc-enrichmentgit 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/ioc-enrichment)<a href="https://agentmods.dev/skills/vigil-soc/vigil/ioc-enrichment"><img src="https://agentmods.dev/badge/skills/vigil-soc/vigil/ioc-enrichment/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/ioc-enrichment"><img src="https://agentmods.dev/badge/skills/vigil-soc/vigil/ioc-enrichment.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 | $0.00054 | $0.00943 |
| Opus 5.5 | $0.00022 | $0.00377 |
| Sonnet 5.5 | $0.00011 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
ioc-enrichment 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 25d 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.
IOC enrichment
Use this procedure whenever a finding, alert or question carries indicators that need external context. It applies to any agent: triage, investigation, reporting or threat intelligence.
Procedure
-
Extract indicators. Read the finding (
get_findingif you only hold an id) and list every IP, domain, URL, hash, email and file path fromiocs,raw_dataanddescription. Separate internal addresses (RFC 1918, loopback, your own ranges) from external ones: internal hosts are pivots, not lookups. -
Recall before you look up. Call
recall_entityon each external indicator before spending an external lookup. Memory is read-only; it tells you what Vigil has seen about the entity before and orients the search. It never decides the outcome on its own. -
Enrich in parallel with whatever you hold. Issue independent lookups in the same turn rather than one at a time. Use the tools present in your grant, not a fixed list:
- If you hold
cf_lookup_ip_threatorcf_lookup_domain_threat, use them for IPs and domains respectively. - If you hold
lookup_indicators, query the local threat feed table for the indicator type and values. - If an MCP server exposes intel tools (reputation, passive DNS, WHOIS, sandbox, geolocation), use those too.
- If none of these is callable in this turn, say so once and complete the
report from what the finding and memory already contain, marking each
absent source
not queried. Never end a turn on an announced lookup, and never invent a lookup result.
- If you hold
-
Identify actor and infrastructure context. From the returned data, note TTPs, infrastructure overlap, campaign or malware family associations and first/last-seen dates. Attribution is a hypothesis: give it a confidence and the evidence behind it.
-
State confidence and provenance per source. For every enriched indicator, report each source by name, what that source said, and the confidence it carried (or your own, labelled as such). Where sources disagree, say which you weight more and why. Never merge sources into one unattributed verdict.
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.
- 25d ago First seen · 86 lines · 54 tokens per session scan A 0f21fa037d47
ioc-enrichment is a skill published in the GitHub repository Vigil-SOC/vigil (374 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 943 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 2026-09-22.
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.