Hope Agent is a cross-device personal AI assistant that remembers context, uses tools, and continues working toward goals through dynamically organized workflows. Individuals use it from desktop, web, server, or messaging environments to manage projects, knowledge, designs, and long-running tasks. The catalogue add-ons extend its agent workflows and capabilities.
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 shiwenwen/hope-agent --skill ha-manualgit clone --depth 1 https://github.com/shiwenwen/hope-agentWrote 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/shiwenwen/hope-agent/ha-manual)<a href="https://agentmods.dev/skills/shiwenwen/hope-agent/ha-manual"><img src="https://agentmods.dev/badge/skills/shiwenwen/hope-agent/ha-manual/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/shiwenwen/hope-agent/ha-manual"><img src="https://agentmods.dev/badge/skills/shiwenwen/hope-agent/ha-manual.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00166 | $0.01308 |
| Opus 5 | $0.00083 | $0.00654 |
| Sonnet 5 | $0.00033 | $0.00262 |
| Haiku 4.5 | $0.00017 | $0.00131 |
Grade A, and why
ha-manual 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 11d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hope Agent User Guide Lookup
You are answering a "how do I use this product" question. The full bilingual user guide ships inside Hope Agent — read it and answer from it. Never invent setting names, panel paths, or slash commands from memory: if the guide names a panel, quote that name; if you cannot find the answer in the guide, say so.
Resolve the manual root first
The guide is mirrored to <data-dir>/manual/ where <data-dir> is
$HA_DATA_DIR when set (Docker: /data), else ~/.hope-agent. Resolve it
dynamically — do NOT hard-code ~/.hope-agent (wrong under Docker/portable):
ls "${HA_DATA_DIR:-$HOME/.hope-agent}/manual/"
Layout: manual/zh/ (简体中文) and manual/en/ (English) — pick the language
the user is speaking. Each contains index.md (overview + navigation) and
01.md … 13.md (chapters). If the directory is missing (mirror not ready:
first boot still warming, or disk issue), tell the user the manual is still
being prepared and to retry in a moment — do not fall back to other paths;
this mirror is the only on-disk copy in packaged installs.
Iron rules
- Read-only: only
read/grep/find/lsthe manual tree. - Answer from the text: cite the chapter number + section heading you used (e.g. "见 05 · 知识空间 §5.2"). Quote exact UI labels from the guide.
- Don't dump chapters: extract the relevant section, answer concisely, and point to the chapter for more.
Chapter routing table
Pick the chapter from the question, read it, grep only when unsure:
| File | Chapter | Covers |
|---|---|---|
01.md |
快速上手 / Getting Started | install per platform, first-launch wizard, run modes (desktop / server+web / ACP), updates, one-click local models, remote access |
02.md |
模型与 Provider / Models & Providers | providers & API keys, Codex sign-in, primary/fallback models, thinking & temperature, failover, STT, media generation (image/audio), web search |
03.md |
对话与会话 / Chat & Sessions | chat UI, attachments & multimodal, session management & search, incognito, working directory, context compaction, all slash commands |
04.md |
记忆系统 / Memory | three memory tiers, auto-memory, recall, Dreaming, user profile, correction loop |
05.md |
知识空间 / Knowledge Space | notes, binding Obsidian, full-text & vector search, backlinks & graph, AI chat panel, access control |
06.md |
设计空间 / Design Space | generating web pages / posters / decks etc., live preview, fine-tuning, versions, export, handoff to code |
07.md |
工具与权限 / Tools & Permissions | built-in tools, permission modes, approval dialog, protected paths & dangerous commands, Docker sandbox, browser control, computer control |
08.md |
自主任务 / Autonomous Tasks | goals, workflows, Loop, Plan Mode, task progress, execution modes |
09.md |
多 Agent 与定时任务 / Multi-Agent & Scheduling | sub-agents, agent teams, natural-language cron jobs, background jobs, self-wakeup |
10.md |
IM 渠道 / IM Channels | Telegram / Discord / Slack / Feishu etc., approvals over IM, streaming mirror, session handover |
11.md |
连接与扩展 / Connect & Extend | MCP client & platform server, hooks, skill system |
12.md |
项目与数据洞察 / Projects & Insights | project containers, agent configuration, dashboard cost & health, Recap reports |
13.md |
设置与安全 / Settings & Security | settings navigation map ("which panel changes X"), changing settings via chat, config backup & rollback, security & reliability |
14.md |
能力评测 / Capability Evaluation | evaluation center: repeatable synthetic tasks against real models, task success / tool calls / latency / token cost metrics, orchestration stability |
index.md |
目录 / Overview | reading guide, core concepts glossary, "I want to…" quick lookup |
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.
- 11d ago First seen · 77 lines · 166 tokens per session scan A af443a5b9c22
ha-manual is a skill published in the GitHub repository shiwenwen/hope-agent (1,589 stars, last pushed 2d ago), licensed MIT. It adds 166 tokens to every session and 1,308 once invoked, about $0.0008 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
memory
Use this skill when Pioneer should proactively use durable memory or recalled context: decide whether memory can improve a turn, answer from remembered user/project facts, request memory tools, search/list/get stored memories, save durable preferences or project decisions, forget memories, audit or clean up memory, or…
subagents
Use this skill when Pioneer should delegate current-turn work to attached task-backed subagents, coordinate parallel child agents, wait for child results, review/revise/accept/cancel/detach attached work, or synthesize accepted child results into the parent answer.
tasks
Use this skill when Pioneer should create, inspect, update, reschedule, pause, resume, troubleshoot, or configure delivery for durable tasks, scheduled tasks, recurring tasks, interval tasks, cron jobs, background work, or existing task state.
browser
Headless web browsing: navigation, page inspection, interaction, data extraction, screenshots, PDFs, and browser session management.
technology-search
Search tech blogs, developer forums, and IT media (TechCrunch, Hacker News, 36氪, etc.) for software and hardware industry updates with heat ranking and EN↔CN translation. Use this skill only when the topic is clearly about programming, software, hardware, AI, or IT infrastructure.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.