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 SummerSec/SumSec-Skills --skill semantic-linter-shotgit clone --depth 1 https://github.com/SummerSec/SumSec-SkillsWrote 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/summersec/sumsec-skills/semantic-linter-shot)<a href="https://agentmods.dev/skills/summersec/sumsec-skills/semantic-linter-shot"><img src="https://agentmods.dev/badge/skills/summersec/sumsec-skills/semantic-linter-shot/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/summersec/sumsec-skills/semantic-linter-shot"><img src="https://agentmods.dev/badge/skills/summersec/sumsec-skills/semantic-linter-shot.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 | $0.00074 | $0.01282 |
| Opus 5.5 | $0.00030 | $0.00513 |
| Sonnet 5.5 | $0.00015 | $0.00256 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
semantic-linter-shot 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 1mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Trap Word Detector (Shot Mode)
A concentrated, single-file reference for detecting semantic trap words in LLM instruction files. No plugin installation required — just read and apply.
Source of truth（与完整插件的关系）
本文件中的表格是便携速查。权威词表、严重等级与失控场景说明以仓库内 references/semantic-trap-lexicon.md 为准；安装完整插件时，运行时数据由 npm run build-lexicon 从该 MD 生成 lib/lexicon-data.js。若速查表与 MD 不一致，以 MD / 生成结果为准。
Gotchas
- 表格用于人工扫读，不保证与当前分支 MD 逐字同步；发版前以 MD 为准核对 ID 与宽/窄词对。
- 替换时保持原意图：目标是收窄语义边界，不是消灭所有抽象词。
- 示例句式若写入你自己的 Skill，可能触发 linter；生产文案请用窄边界改写后的版本。
What Are Semantic Traps?
Semantic trap words are vocabulary with wide semantic boundaries that cause LLMs to produce outputs far beyond intended scope. Empirical note (see linked article in repo README): swapping a narrow defect-focused noun for a broad finance-adjacent noun in an otherwise identical Skill can materially reduce task accuracy.
Core principle: Replace wide-boundary words with narrow-boundary alternatives to constrain LLM output.
Trap Word Reference Table
以下宽词表为速查对照；为免在本仓库触发 linter，表体放在围栏块内（阅读时照常查看即可）。
Chinese (T01-T17)
| ID | Trap Word (Wide) | Replacement (Narrow) | Severity | Why It's Dangerous |
|----|-------------------|----------------------|----------|-------------------|
| T01 | 风险 | 漏洞 | critical | Activates finance/health/legal associations |
| T02 | 审查 | 检查 | high | Triggers subjective evaluation |
| T03 | 描述 | 列出 | high | Triggers explanatory prose |
| T04 | 问题 | 缺陷 | high | Extremely wide scope |
| T05 | 分析 | 总结 | medium-high | Triggers inference and hypothesis |
| T06 | 建议 | 要求 | medium-high | Triggers divergent thinking |
| T07 | 异常 | 错误 | medium | Fuzzy boundary |
| T08 | 改善 | 修复 | high | Triggers optimization suggestions |
| T09 | 参考 | 遵循 | medium-high | Implies flexibility |
| T10 | 评估 | 统计 | high | Triggers subjective judgment |
| T11 | 理解 | 提取 | high | Triggers inference |
| T12 | 关联 | 匹配 | medium | Triggers indirect reasoning |
| T13 | 转化 | 复制 | medium-high | Implies modification allowed |
| T14 | 洞察 | 报告 | high | Triggers creative inference |
| T15 | 评价 | 验证 | medium-high | Triggers subjective scoring |
| T16 | 原则 | 规则 | medium | Implies flexibility |
| T17 | 方法 | 步骤 | medium | Implies choice of paths |
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.
- 1mo ago First seen · 94 lines · 74 tokens per session scan A b6014010c565
semantic-linter-shot is a skill published in the GitHub repository SummerSec/SumSec-Skills (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,282 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
audit-playbook
A code-security audit playbook covering source-code review, runtime checks, software dependencies, deployment settings, and AI-agent security risks.
x64dbg-reversing
Perform dynamic reverse engineering and debugging using X64dbg/X32dbg through natural language commands powered by X64dbg MCP. Use this skill whenever the user wants to: debug executables, analyze program behavior at runtime, set breakpoints, inspect memory and registers, trace execution flow, bypass anti-debug…
novel-reviewer
A review and editing workflow for existing novel chapters. It checks story logic, timelines, character states, unresolved clues, world rules, and writing style.
ida-reversing
Perform reverse engineering and binary analysis in IDA Pro using natural language commands powered by IDA MCP. Use this skill whenever the user wants to: analyze executable files, understand function behavior, decompile code, explore cross-references, search for strings or bytes, patch binary code, document reverse…
video-recap
A workflow that turns a supplied video into a Chinese narrated recap by combining video understanding, story planning, editing, voiceover, and final assembly.
workflow-manager
A writing workflow tracker for chapter-based projects. It records whether each chapter is being assembled, drafted, reviewed, confirmed, polished, or archived.