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 RickyTong1/audit-harness --skill audit-initgit clone --depth 1 https://github.com/RickyTong1/audit-harnessWrote 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/rickytong1/audit-harness/audit-init)<a href="https://agentmods.dev/skills/rickytong1/audit-harness/audit-init"><img src="https://agentmods.dev/badge/skills/rickytong1/audit-harness/audit-init.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 145 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 156 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 157 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 158 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 159 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00045 | $0.02123 |
| Opus 5 | $0.00023 | $0.01061 |
| Sonnet 5 | $0.00009 | $0.00425 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
audit-init 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 9d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit-init — 审计框架安装向导
触发方式
/audit-init
概述
本 Skill 是一个交互式安装向导（wizard），引导用户在当前项目中完成 audit-harness 的全部配置。安装完成后，/start、/end、/recover、/report-daily 四个 Skill 立即可用。
执行步骤
Step 1：环境检测
检查当前项目状态，判断是全新安装还是升级：
checks = {
"audit_context_exists": 项目根目录是否已有 audit_context.py,
"audit_config_exists": 项目根目录是否已有 audit_config.py,
"runs_dir_exists": runs/ 目录是否存在,
"claude_md_exists": CLAUDE.md 是否存在,
"claude_md_has_audit": CLAUDE.md 中是否已有 [AUDIT] 格式规范,
"skills_dir_exists": .claude/skills/ 是否存在,
"is_git_repo": 是否在 git 仓库中,
}
根据检测结果输出状态：
=== audit-harness 安装向导 ===
环境检测：
[✅] Git 仓库: 是
[❌] audit_context.py: 不存在 → 需要安装
[❌] audit_config.py: 不存在 → 需要创建
[❌] runs/ 目录: 不存在 → 需要创建
[✅] CLAUDE.md: 存在
[❌] CLAUDE.md 审计规范: 未配置 → 需要注入
[❌] .claude/skills/: 不存在 → 需要创建
如果检测到已有组件（升级场景），提示用户是否覆盖。
Step 2：收集项目信息
通过 AskUserQuestion 向用户收集项目专属配置。每个问题都附带说明和默认值。
问题 1：关键脚本
你的项目中哪些 Python 脚本是核心脚本？
（这些脚本的哈希会被记录在环境快照中，用于追踪配置变化）
请列出文件名，用逗号分隔，或输入 "scan" 让我自动扫描。
如果用户选择 "scan"：
- 扫描项目根目录下所有 .py 文件
- 按修改时间排序，展示前 20 个
- 让用户选择哪些是核心脚本
问题 2：关键资产文件
你的项目中有哪些关键模型/配置文件？
（如 .pkl、.yaml、.json 等，变更需要被追踪的）
请列出文件名，用逗号分隔，或输入 "none"。
问题 3：Prompt 模板
你的项目是否使用 AI Prompt 模板？
如果是，请提供 glob 模式（如 "prompts/*.txt" 或 "docs/prompt_*.md"）。
如果否，输入 "none"。
问题 4：告警规则
你想设置哪些告警规则？
选项：
1. 使用默认规则（仅数据完整性校验）
2. 稍后手动编辑 audit_config.py
3. 帮我根据项目内容自动生成建议规则
如果用户选择 3：
- 扫描项目中的数据处理脚本
- 分析可能的告警点（错误率、空值率、处理量异常等）
- 生成建议规则，让用户确认
Step 3：安装核心文件
# 3.1 复制 audit_context.py
source = "{audit-harness}/lib/audit_context.py"
target = "{project_root}/audit_context.py"
# 复制文件
# 3.2 生成 audit_config.py（基于 Step 2 收集的信息）
# 写入用户提供的 CORE_SCRIPTS、CORE_ASSETS、PROMPT_TEMPLATE_GLOB、ALERT_RULES
# 3.3 创建 runs/ 目录
mkdir -p runs/daily
# 3.4 创建 .gitignore（runs/ 中的大文件不入库，但保留目录结构）
# runs/下的 .jsonl 文件可能很大，建议 gitignore
输出：
安装核心文件：
[✅] audit_context.py → {project_root}/audit_context.py
[✅] audit_config.py → {project_root}/audit_config.py (已填入你的配置)
[✅] runs/ 目录已创建
[✅] runs/.gitignore 已创建
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.
- 9d ago First seen · 263 lines · 45 tokens per session scan A 2787c57821b8
audit-init is a skill published in the GitHub repository RickyTong1/audit-harness (472 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 2,123 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…