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 kachofugetsu09/akashic-agent --skill opencligit clone --depth 1 https://github.com/kachofugetsu09/akashic-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/kachofugetsu09/akashic-agent/opencli)<a href="https://agentmods.dev/skills/kachofugetsu09/akashic-agent/opencli"><img src="https://agentmods.dev/badge/skills/kachofugetsu09/akashic-agent/opencli/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/kachofugetsu09/akashic-agent/opencli"><img src="https://agentmods.dev/badge/skills/kachofugetsu09/akashic-agent/opencli.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 | $0.00024 | $0.00550 |
| Opus 5.5 | $0.00010 | $0.00220 |
| Sonnet 5.5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
opencli 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 1mo 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCLI
OpenCLI is a command-line program, not the Browser Use tool. Run it with the ordinary shell tool; the Computer plugin connects OpenCLI's standard local port to its persistent browser. For direct page or desktop interaction, load the computer skill and use computer.
Rules
- Run
openclithroughshell; never send OpenCLI arguments to a Browser tool. - Prefer a site adapter. Run
opencli list -f jsonand the leaf command's--help -f jsonbefore guessing commands or flags. - Request
-f jsonfor structured adapter output.PUBLICandLOCALadapters need no browser;COOKIE,INTERCEPT, andUIadapters need the Browser Bridge. - Browser-backed site adapters use
--window background --site-session persistent --keep-tab trueso one logged-in session can be reused. - Before browser-dependent work, run
opencli doctor. Daemon, Extension, and Connectivity must all be ready. - Preserve the exact shell exit code, stdout, stderr, and error. Do not silently fall back to raw HTTP or another browser profile.
- Never start another browser, close the persistent Chromium process, delete its profile, or remove
Singleton*files. The Computer plugin owns that lifecycle.
Discover and diagnose
shell({"command":"opencli list -f json","description":"列出 OpenCLI 能力"})
shell({"command":"opencli bilibili history --help -f json","description":"查看站点命令帮助"})
shell({"command":"opencli doctor","description":"检查 OpenCLI 连接"})
shell({"command":"opencli auth status","description":"检查登录状态"})
Site adapters
Put persistent browser options after the leaf command:
shell({"command":"opencli bilibili history -f json --window background --site-session persistent --keep-tab true","description":"读取哔哩哔哩历史"})
shell({"command":"opencli github whoami -f json --window background --site-session persistent --keep-tab true","description":"读取 GitHub 身份"})
The Computer plugin refreshes known login sessions every 12 hours and retries a failed refresh after 15 minutes. If a site has logged out, ask the user to log in once through the visible Computer panel.
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.
- 1mo ago Changed · -1 lines 73176ed13ca4
- 1mo ago First seen · 47 lines · 24 tokens per session scan A 5cbadeb3fe5e
opencli is a skill published in the GitHub repository kachofugetsu09/akashic-agent (511 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 550 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts with the existing agent-browser CLI, including screenshots and keyboard or interaction checks. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser automation.