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-skill-installergit 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-skill-installer)<a href="https://agentmods.dev/skills/shiwenwen/hope-agent/ha-skill-installer"><img src="https://agentmods.dev/badge/skills/shiwenwen/hope-agent/ha-skill-installer/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-skill-installer"><img src="https://agentmods.dev/badge/skills/shiwenwen/hope-agent/ha-skill-installer.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 | $0.00082 | $0.01643 |
| Opus 5 | $0.00041 | $0.00822 |
| Sonnet 5 | $0.00016 | $0.00329 |
| Haiku 4.5 | $0.00008 | $0.00164 |
Grade A, and why
ha-skill-installer 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 4d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Installer
Install one selected skill with the bundled scripts/install_skill.py. Resolve the script from this activation's <package_directory>; do not guess a repository-relative or cached bundle path. It needs Python 3.9+. For GitHub acquisition the helper calls the owning Hope binary, whose path normal exec supplies in HOPE_AGENT_EXECUTABLE (or hope-agent on PATH outside the app). Check prerequisites and explain a missing runtime without silently installing software.
Select the source and scope
- An exact GitHub repository/subdirectory or local skill directory goes directly to this installer. Use
ha-find-skillsonly if the user still needs a candidate. Do not replace the user's chosen source with a registry recommendation. - Default to the managed directory:
$HA_DATA_DIR/skills/when set, otherwise~/.hope-agent/skills/. When the user requests project-only installation, pass--projectwith the current session's resolved project/workspace directory. Do not infer it from the desktop process's working directory. - Check the visible catalog for an existing name, including shared, extra, and project sources. The helper rejects target-directory collisions and bundled names; it cannot see every configured source. Do not shadow an existing skill as an installation workaround. Use
ha-skill-creatorfor intentional edits. - Public GitHub sources use bounded, unauthenticated metadata and file requests through Hope's native reader. The complete selected file tree is checked for count, size, and unsafe entries before downloading any package files. Requests use the shared SSRF checks, reject redirects, and pin file URLs to the resolved commit; no repository code or credential helpers run. Other Git hosts and private repositories use an already-authorized local checkout with
--local; never put tokens in URLs or script arguments. On an API rate limit or an unavailable reader, report the failure and use an authorized local source if available; do not fall back to an unbounded clone/download.
What ships with it
2 files 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.
- 4d ago First seen · 78 lines · 82 tokens per session scan A 92e4afab3f4e
ha-skill-installer is a skill published in the GitHub repository shiwenwen/hope-agent (1,589 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 1,643 once invoked, about $0.0004 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 2026-09-07.
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.