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 investigate-casegit 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/investigate-case)<a href="https://agentmods.dev/skills/vigil-soc/vigil/investigate-case"><img src="https://agentmods.dev/badge/skills/vigil-soc/vigil/investigate-case/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/investigate-case"><img src="https://agentmods.dev/badge/skills/vigil-soc/vigil/investigate-case.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 | $0.00026 | $0.00463 |
| Opus 5.5 | $0.00010 | $0.00185 |
| Sonnet 5.5 | $0.00005 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
investigate-case 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 2d 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.
What it actually says
Investigating a case
1. Read what the case holds
Start with the case's own records and the findings attached to it. Note every entity they name: hosts, identities, IPs, domains, hashes, processes. Those are your pivots. Note the time window the findings cover.
2. Say what could explain it
Write down two or three explanations before you query: at least one benign and one malicious. Each should predict something you can check. A lockout storm, for example, is a stale credential on a scheduled task (one source host, a regular interval, one account) or password spraying (many accounts, many sources, a short burst).
3. Check the predictions
Query for what would separate the explanations, not for more of what you have.
- Widen the window before you trust an empty search: the activity may sit just outside it.
- Ask the telemetry, not only the findings: detection only scored what it saw.
- Look an observable up in the indicator database before you call it clean.
- Search the findings for the same entity on other hosts or identities: one case is often part of a larger one.
4. Decide what you can support
- malicious: a cited result shows attacker activity.
- suspicious: results point toward it but do not show it.
- benign: a cited result positively shows a legitimate cause.
- false_positive: the detection fired on something that is not what it looks for, and a cited result shows what it actually was.
- inconclusive: the tools could not separate the explanations. Say which query would.
Benign and false_positive are reviewed before they stand. Absence of results does not support either one.
5. Write it so a reader can act
Lead with what happened. Cite the refs you rest on. List every gap with the reason it stayed open. Next steps go most important first, and each names who or what it touches.
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.
- 2d ago First seen · 51 lines · 26 tokens per session scan A 6ec542d95254
investigate-case is a skill published in the GitHub repository Vigil-SOC/vigil (374 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 463 once invoked, about $0.0001 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 2026-10-15.
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.