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 agentmods add skills/peiiii/nextclaw/predictable-behavior-firstnpx skills add Peiiii/nextclaw --skill predictable-behavior-firstgit clone --depth 1 https://github.com/Peiiii/nextclawWhat 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 | $0.00049 | $0.00786 |
| Opus 5 | $0.00024 | $0.00393 |
| Sonnet 5 | $0.00010 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
predictable-behavior-first 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 3d 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.
What it actually says
可预测行为优先
目标是同一输入与安装状态产生同一行为：不靠隐藏环境状态意外成功，也不把发布、配置或协议缺陷伪装成健康。
默认立场
- fail-fast 优于静默救援，单一事实源优于多级 fallback。
- dev convenience 必须显式开启；发布产物不得借用 cwd、源码 checkout 或本机偶然资源。
- 内部重构迁移所有已知调用方并删除旧入口，不为方便保留 alias、proxy、adapter 或双 manager。
- 未发布中间态不是兼容合同；旧 route/API 只有在承载持久用户数据、已证明外部合同或不可避免的分阶段 rollout 时才保留。
- 无效的 prompt、schema、协议或上游值应修 producer 并显式拒绝，不在下游用别名或归一化悄悄接受。
- read/get/list/status/discover/report 必须纯读、可重复且无副作用；加载、注册、授权、写入和外部调用使用显式 action。
- schema/tool 只表达自身合同，不承载动态 catalog、CLI 教程和 AI 工作流；发现与操作流程归对应 owner。
决策流程
- 写出主合同：发布包、桌面产物、公共 API、配置 schema、持久数据或 transport。
- 区分 shipped runtime 与显式 dev mode。
- 判断 fallback 是否掩盖 packaging/config/release/runtime 缺陷；若是，修源合同并增加相应交付 guard。
- 判断错误是否来自上游意图或协议；若是，修 producer，不在 consumer 宽容化。
- 判断 read-shaped path 是否会被页面加载、路由、轮询、重试、重连或 focus-refetch 自动调用；任何执行副作用都应拆成显式 action。
- 协议模式已知时第一次请求就使用正确 contract，不先发错误模式再按错误文本切换。
- 仍需兼容时，读取例外政策，证明外部必要性，并冻结触发、范围、信号、owner 和退出条件。
禁止的运行时补丁
除非用户明确授权短期事故止血且有删除条件，不得在 shipped runtime 中加入：
- 用
stderr/stdout.includes(...)识别当前坏版本、打包事故或临时上游故障； - “latest release 已坏”等版本/事故签名特判；
- 扫描多个无关目录直到找到可用资源；
- 先发送错误 transport，再根据上游报错文本重试真实模式；
- 自动触发的前端 read path 隐藏 load/register/install/write/external call；
- 没有真实外部合同的旧 API 转发、双实现或永久 mode flag。
输出
说明主合同、观察/执行属性、自动调用副作用、fallback 是否掩盖缺陷、旧路径是否拥有持久数据或外部合同，以及结论属于：删除、fail-fast、显式 dev-only、或有退出条件的临时兼容。
允许兼容必须同时具备具体必要性、窄范围、可观察信号、cleanup owner 和明确退出事件；缺一项就不保留。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 46 lines · 49 tokens per session scan A e9af47930c22
predictable-behavior-first is a skill published in the GitHub repository Peiiii/nextclaw (253 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 786 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
ha-skill-creator
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
ha-mac-control
Hope Agent native macOS desktop control — the standard maccontrol status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using maccontrol, or…
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
ha-logs
Self-service diagnostics — query Hope Agent's local SQLite databases (logs / sessions / background jobs) directly via the exec tool to investigate problems, analyze usage, and locate root causes. Trigger on: user reports something broken / failing / slow / stuck / not responding ('X 不工作', 'X 报错', 'X 卡住', '为什么 X 失败'…
ha-pet-import
Safely import, select, switch, or enable a compatible desktop pet in Hope Agent. Resolve packages from any origin, including local folders, zip archives, pet.json plus a sprite, PNG/WebP atlases, chat attachments, repository or cloud files, direct HTTPS artifact URLs, and download pages. Use whenever a user asks to…
ha-data-analytics
Hope-native local-first data analysis and Artifact reporting. Use for CSV/XLSX analysis, KPI readouts, metric diagnosis, product/business analysis, data-quality review, dashboards, charts, analytical reports, 数据分析, 指标诊断, 数据质量, 分析报告, or when the user wants a shareable offline HTML/ZIP/Markdown/PDF result. Produces the…