/sarif-toolkit

Deterministic SARIF reporting and partitioning. Use when inspecting .sarif or .sarif.json static-analysis output, summarizing findings without loading full JSON into chat, or splitting results by rule, path, severity, or balanced chunks.

BOOST

khaneliman@khaneliman

GitHub

From plugin

khanelinix

34750 skills10 agents6 commands

Install

$ npx -y skills add khaneliman/khanelinix --skill sarif-toolkit --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/sarif-toolkit

Context preview

The summary Claude sees to decide when to auto-load this skill.

Deterministic SARIF reporting and partitioning. Use when inspecting .sarif or .sarif.json static-analysis output, summarizing findings without loading full JSON into chat, or splitting results by rule, path, severity, or balanced chunks.

SKILL.md

sarif-toolkit.SKILL.md

name: sarif-toolkit
description: Deterministic SARIF reporting and partitioning. Use when inspecting .sarif or .sarif.json static-analysis output, summarizing findings without loading full JSON into chat, or splitting results by rule, path, severity, or balanced chunks.
metadata:
  disable-model-selection: "true"

SARIF Toolkit

Use bundled script for mechanical inspection. Keep interpretation and fix prioritization with agent.

Report

python3 <skill-dir>/scripts/sarif_report.py <file> --format markdown

Report includes schema/version, runs, tools, result and artifact counts, top rules, severity counts, affected paths, and bounded representative results. Scalar values, tools, severities, and split-file listings are bounded by default with total/omitted metadata. Use `--help` to adjust limits; `0` means unlimited for `--max-*` flags.

Split

Write chunks only when user asks:

python3 <skill-dir>/scripts/sarif_report.py <file> \
  --split rule --output-dir <directory>
python3 <skill-dir>/scripts/sarif_report.py <file> \
  --split balanced --chunks 4 --output-dir <directory>

Strategies: `rule`, `path`, `severity`, `balanced`. Script uses stable filenames and writes `manifest.json` last. Existing non-empty output requires `--force`. Manifest keeps the complete file/run mapping even when stdout lists only a bounded subset.