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 nongjun/awesome-harness-engineering --skill aigit clone --depth 1 https://github.com/nongjun/awesome-harness-engineeringWrote 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/nongjun/awesome-harness-engineering/ai)<a href="https://agentmods.dev/skills/nongjun/awesome-harness-engineering/ai"><img src="https://agentmods.dev/badge/skills/nongjun/awesome-harness-engineering/ai.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00352 |
| Opus 5 | $0.00025 | $0.00176 |
| Sonnet 5 | $0.00010 | $0.00070 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
AI响应解析 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 6d 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.
This is a copy
91% identical to llm-json-parser — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
LLM JSON 解析
当前实现
位于 AIService 内部，使用正则表达式提取（非 json-repair 库）。
关键函数
| 函数 | 用途 |
|---|---|
| parse_ai_json_response(content) | 提取并解析 JSON，返回 (dict, thinking_text) |
| safe_parse_ai_json(content, default) | 带默认值的安全解析 |
处理流程
- 提取并移除 thinking 标签内容
- 识别 Markdown 代码块（json 或无标记）
- 从混合文本中用正则提取 JSON 对象
- 标准 json.loads() 解析
适用场景
- AI 回复包裹在 thinking 标签中
- AI 回复被 Markdown 代码块包裹
- AI 回复中混有自然语言和 JSON
重点关注
- 当前实现不使用 json-repair 库，仅做正则提取
- 对于中文标点、未闭合引号等格式问题暂无自动修复
- 如需更强容错能力，可引入 json-repair 库增强
导入路径
shared_backend.services.ai_service 中导出 parse_ai_json_response 和 safe_parse_ai_json。
参考文件
- 公共模块/shared_backend/services/ai_service.py
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.
- 6d ago First seen · 45 lines · 50 tokens per session scan A 87c056b562d6
AI响应解析 is a skill published in the GitHub repository nongjun/awesome-harness-engineering (2 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 352 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to llm-json-parser, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…