Borrowing it
Nothing to install: this file belongs to omeryemba/mcp-hayabusa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/omeryemba/mcp-hayabusa/master/.claude/commands/investigate-endpoint.mdgit clone --depth 1 https://github.com/omeryemba/mcp-hayabusaWrote 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/commands/omeryemba/mcp-hayabusa/investigate-endpoint)<a href="https://agentmods.dev/commands/omeryemba/mcp-hayabusa/investigate-endpoint"><img src="https://agentmods.dev/badge/commands/omeryemba/mcp-hayabusa/investigate-endpoint/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/commands/omeryemba/mcp-hayabusa/investigate-endpoint"><img src="https://agentmods.dev/badge/commands/omeryemba/mcp-hayabusa/investigate-endpoint.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 | $0.00028 | $0.00915 |
| Opus 5 | $0.00014 | $0.00458 |
| Sonnet 5 | $0.00006 | $0.00183 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
investigate-endpoint 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 10d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow
You are performing a defensive security investigation of a specific endpoint.
Input
Arguments: $ARGUMENTS
Parse as:
- Hostname (required) — the first argument. If it's missing, stop and ask the user for a hostname before doing anything else.
- Timerange (optional) — e.g.
2026-07-01..2026-07-31,24h,7d. - EVTX path (optional) — a filesystem path to
.evtxevidence for this endpoint.
If only one optional argument is given, check whether it resolves to an existing filesystem path: if so, treat it as the EVTX path; otherwise treat it as the timerange. If two are given, the first is the timerange and the second is the EVTX path.
Example:
/investigate-endpoint WIN-CLIENT01 7d C:\logs\WIN-CLIENT01
Steps
-
Confirm the hostname was supplied; stop and ask if not.
-
If an EVTX path was given, confirm it exists and contains at least one
.evtxfile before running any Hayabusa tool. If it doesn't, tell the user and continue with SIEM-only analysis rather than fabricating evidence. -
Query SIEM data for the hostname (and timerange, if given), if a SIEM MCP tool or resource is configured in this environment. Analyse the results and extract:
- suspicious processes
- users
- IP addresses
- files
- commands
- authentication activity
If no SIEM integration is available, say so explicitly in the output rather than silently skipping this step.
-
If an EVTX path was given, use the Hayabusa MCP tools:
scan_evtx,hayabusa_log_metrics,hayabusa_computer_metricsfor a first-pass overviewhayabusa_search,hayabusa_json_timeline,hayabusa_pivot_keywords_list,hayabusa_logon_summaryto dig into anything suspicious
Look for the same categories as the SIEM step (processes, commands, users, authentication activity, persistence indicators) so the two sources are directly comparable.
-
Correlate SIEM and Hayabusa findings for the same hostname/timerange. The same process, user, or IP appearing in both sources strengthens confidence; a finding present in only one source should be flagged as unconfirmed by the other, not silently merged into one line.
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.
- 10d ago First seen · 112 lines · 28 tokens per session scan A 7a6d86409b3b
investigate-endpoint is a command published in the GitHub repository omeryemba/mcp-hayabusa (0 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 915 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
fortigate
Run cs-security-analyst (AT + CA workflows) against the Fintech FortiGate zero-day scenario and produce a 7-task scorecard.
run
Load a USAP skill SKILL.md and activate it as your operating persona. Argument: skill slug.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.