Cindy is an open-source local AI agent that combines coding harnesses, language models, tools, memory, and skills to complete work across files, applications, browsers, computers, and phones. Its desktop and mobile client lets users switch between Claude Code, Codex, other models, and connected services while keeping task context continuous. The catalogue instructions relate to operating or developing this agent.
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 makecindy/cindy --skill nightly-audit-engineer-getting-startedgit clone --depth 1 https://github.com/makecindy/cindyWrote 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/makecindy/cindy/nightly-audit-engineer-getting-started)<a href="https://agentmods.dev/skills/makecindy/cindy/nightly-audit-engineer-getting-started"><img src="https://agentmods.dev/badge/skills/makecindy/cindy/nightly-audit-engineer-getting-started/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/makecindy/cindy/nightly-audit-engineer-getting-started"><img src="https://agentmods.dev/badge/skills/makecindy/cindy/nightly-audit-engineer-getting-started.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 | $0.00046 | $0.00858 |
| Opus 5.5 | $0.00018 | $0.00343 |
| Sonnet 5.5 | $0.00009 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
nightly-audit-engineer-getting-started 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 today.
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.
What it actually says
代码审计伙伴开场设置
只在两种情况下使用：刚被邀请后的第一次对话；或者记忆里还没有下面的偏好。
顺序
宿主已经在对话里放出开场问候和下面的起步选项，用户看到的就是这些；他的第一条回复是选定的方向，或直接给出的任务。
- 先查记忆（只查记忆，不查插件、不读任何来源）；记忆里已有偏好时不再逐项提问。
- 按用户的选择开始；还缺关键信息时，一次只问一件事，可以用宿主的提问卡。
- 这件事需要外部工具时，才按下面“工具”一节找工具，再做只读查看并开始首个成果。
不重复开场问候，不复述本技能，不说“已准备好”就停下；用户一旦给出真实任务，就停止起步提问，直接帮忙。
起步选项（开场时由宿主展示）
- 审计一个模块
- 复查最近合并的改动
- 专门找一类问题
- 了解夜间审计怎么开启
用户选其中一项或用自己的话回答都可以；可按记忆微调措辞。
需要了解的偏好
未知前都视为未设置：
- 要审计的仓库与范围
- 最关注的问题类型（如并发、权限、持久化）
- 这轮只审阅还是也允许准备小范围修复
- 定期审计的时间与时区
用户选定起步方向后，只问这件事用得上的偏好，一次只问一个；能从已连接的数据或用户给的材料看出来的不再问。只把用户明确确认的内容写进记忆，以宿主实际保存结果为准。
工具（用户选定后）
- 首个成果不需要额外工具，用户粘贴材料或说明目标即可开始。
- 之后可能用到：代码托管（例如 GitHub、GitLab）。这只是举例，不限于这些：按能力类别找，先用用户已有的同类工具（含本机已有的 CLI 和现有工具，如 git、gh、glab、浏览器），有什么用什么。同类工具用户通常只用一个，按他实际在用的那个来。
- 发现、安装和连接插件，按宿主伙伴指南（teammate-guide）里的插件规则办；需要新插件或需要连接时，先征得用户同意；当前环境没有合适工具时，用本机已有的工具，或请用户粘贴材料。
- 默认只读，写入（建 issue、发邮件、写表格等）前须用户确认；不索要密码或令牌，不让用户把凭证贴进对话。
只读查看（用户选定后）
用户已有代码托管工具（如 GitHub、GitLab）时，只读查看最近合并的 PR/MR，挑一个改动集中的区域作为第一轮审计建议。只看一次、只读，不写入、不发送、不改状态；没有现成工具就跳过，不为此弹连接卡。
首个成果
对选定范围做一次小范围审计，给出最多三条可复现、带依据的问题。用户选定后立刻开始，不说“稍后处理”后沉默。
例行任务
「夜间代码审计」默认关闭。只说明在用户确认时区、时间和来源后可以开启；本轮不创建、不开启。
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.
- today Changed · +1 lines c66b78834f02
- 4d ago First seen · 57 lines · 46 tokens per session scan A 5bacca5c029e
nightly-audit-engineer-getting-started is a skill published in the GitHub repository makecindy/cindy (3,531 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 858 once invoked, about $0.0002 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 2026-10-20.
Other skills, from other repositories
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
ha-self-diagnosis
Self-understanding and issue reporting for Hope Agent itself. Use when the user asks how Hope Agent works internally, asks about its own source code/docs/runtime behavior, reports a bug/failure/slowness/crash, asks to diagnose logs, or asks to create/submit a GitHub issue for a bug, feature request, or improvement…
safe-refactoring
Execute behavior-preserving or intentionally scoped refactors safely. Use this for multi-file renames, component/service extraction, state-management changes, API migrations, concurrency refactors, or any request where unrelated user work and subtle contracts must be preserved.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
ha-code-review
Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable findings first without speculative noise.
ha-debug
Hope-native debugging for code failures, regressions, crashes, flaky behavior, and bad output: reproduce or characterize, rank falsifiable hypotheses, fix the smallest root cause, and prove the failing path.