Borrowing it
Nothing to install: this file belongs to Pirate-Kitty/hayabusa-mcp-security-scanner. 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/Pirate-Kitty/hayabusa-mcp-security-scanner/main/.claude/commands/triage.mdgit clone --depth 1 https://github.com/Pirate-Kitty/hayabusa-mcp-security-scannerWrote 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/pirate-kitty/hayabusa-mcp-security-scanner/triage)<a href="https://agentmods.dev/commands/pirate-kitty/hayabusa-mcp-security-scanner/triage"><img src="https://agentmods.dev/badge/commands/pirate-kitty/hayabusa-mcp-security-scanner/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/commands/pirate-kitty/hayabusa-mcp-security-scanner/triage"><img src="https://agentmods.dev/badge/commands/pirate-kitty/hayabusa-mcp-security-scanner/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 | $0.00052 | $0.03018 |
| Opus 5 | $0.00026 | $0.01509 |
| Sonnet 5 | $0.00010 | $0.00604 |
| Haiku 4.5 | $0.00005 | $0.00302 |
Grade A, and why
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 11d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage the EVTX file at $1 and write an Obsidian-compatible triage note under investigations/triage/, syncing reusable ATT&CK technique notes under techniques/.
1. Parse arguments
evtx_path=$1. If empty, stop immediately and report:Usage: /triage <evtx-path> [severity] [case-id]. Make no tool calls.severity_arg=$2(may be absent).case_id_arg=$3(may be absent).
2. Resolve and validate severity BEFORE scanning
- If
severity_argis present: trim whitespace and lowercase it, then check it is exactly one ofinformational,low,medium,high,critical.- No match → stop immediately, before calling any scan tool, and report:
Invalid severity '<severity_arg>'. Must be exactly one of: informational, low, medium, high, critical. - Match → use the normalized value as
min_severity.
- No match → stop immediately, before calling any scan tool, and report:
- If
severity_argis absent →min_severity = "medium"(the default).
3. Validate case_id BEFORE scanning
- If
case_id_argis absent,case_id = nulland this step is done. - If present: trim whitespace, then check the result matches exactly
^[A-Za-z0-9_-]{1,64}$.- No match (this covers path separators
/\, traversal sequences.., shell metacharacters; | & $" ' * ? ( ) < > ~, whitespace, email addresses, or any other character outside letters/digits/hyphen/underscore) → stop immediately, before calling any scan tool, and report:Invalid case ID '<case_id_arg>'. Use only letters, numbers, hyphens, and underscores (max 64 characters).` Do not attempt to strip or sanitize the value and continue — reject and stop. - Match → use the trimmed value as
case_id.
- No match (this covers path separators
4. Scan
Call mcp__hayabusa-mcp__scan_evtx with evtx_path, the resolved min_severity, and output_format="full".
- If the tool raises a file-not-found or Hayabusa-binary error, surface that error message verbatim, and add a note that
evtx_pathis resolved by the MCP server against its own process working directory (the repo root) — relative paths should be given relative to the repo root, or as absolute paths. - If the scan succeeds with zero findings, this is not a failure: continue through the remaining steps to write a minimal note with
triage_outcome: insufficient evidence, and suggest re-running with a lower severity value.
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.
- 11d ago First seen · 154 lines · 52 tokens per session scan A 036899de06eb
triage is a command published in the GitHub repository Pirate-Kitty/hayabusa-mcp-security-scanner (0 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 3,018 once invoked, about $0.0003 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
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.