SummerSec

SummerSec/semantic-linter

Hook

Runs when you submit a prompt, before the agent sees it, executing user-prompt-submit.js via node. From SummerSec/semantic-linter.

SummerSec/semantic-linter

Hook

Runs before the agent uses a tool for Write and Edit tool calls, executing pre-tool-use.js via node. From SummerSec/semantic-linter.

SummerSec/semantic-linter

Hook

Runs after a tool call finishes for Write and Edit tool calls, executing post-tool-use.js via node. From SummerSec/semantic-linter.

SummerSec/semantic-linter

Skill Claude CodeCodex

A vocabulary-management skill for Semantic-Linter, a tool that finds potentially misleading or problematic wording.

SummerSec/semantic-linter

Skill Claude CodeCodex

Install Semantic-Linter project rules into AGENTS.md and or CLAUDE.md so the model can load semantic guidance on demand while editing instruction files.

SummerSec/semantic-linter

Skill Claude CodeCodex

Deep instruction triage beyond the fixed lexicon—score terms, spot wide-boundary wording and stacking risks. Use when the user asks for semantic analysis, deep scan, prompt triage, or hooks pass but phrasing still feels vague.

SummerSec/semantic-linter

Skill Claude CodeCodex

This skill should be used when the user asks to "quick scan", "trap check", "check wording", "词汇检查", "快速检测", "陷阱检查", or when writing/reviewing Skill/Prompt/Agent instructions. Provides a lightweight single-file reference card for identifying wide-boundary vocabulary in LLM instruction files.