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 mxyhi/ok-skills --skill opencli-usagegit clone --depth 1 https://github.com/mxyhi/ok-skillsWrote 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/mxyhi/ok-skills/opencli-usage)<a href="https://agentmods.dev/skills/mxyhi/ok-skills/opencli-usage"><img src="https://agentmods.dev/badge/skills/mxyhi/ok-skills/opencli-usage/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/mxyhi/ok-skills/opencli-usage"><img src="https://agentmods.dev/badge/skills/mxyhi/ok-skills/opencli-usage.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 | $0.00031 | $0.00575 |
| Opus 5.5 | $0.00012 | $0.00230 |
| Sonnet 5.5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
opencli-usage 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 6d 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.
This is a copy
100% identical to opencli-usage — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCLI
OpenCLI exposes reusable website adapters and direct Chrome tools to agents.
opencli list search
opencli list --site github --limit 20
opencli github search --help -f json
list [query] searches command names and descriptions across built-ins and adapters.
Results are compact and paginated: {ok:true,data:{commands,total,nextOffset?}}.
Pass --offset <nextOffset> to continue. Inspect exact inputs using command help.
Do not hard-code the adapter catalog or dump all commands into context.
Results
Commands default to JSON: {ok:true,data:...}. Failures produce a nonzero exit
code and {ok:false,error:{code,message,hint?,...}} on stdout. Logs use stderr.
Explicit -f table|yaml|csv|md|plain exports are available where command help lists
them. Help, version, completion and explicit plain exports retain their own formats.
Browser follow modes stream one JSON envelope per line.
Use error codes and supplied candidates/keys to recover. Unknown write outcomes require inspecting state before repeating an action. An empty successful result is distinct from an execution failure.
Browser
opencli browser open https://example.com --session research
opencli browser state --session research
opencli browser close --session research
opencli browser chrome describe
Page commands use --session; native Chrome methods need no session. --profile
selects a connected Chrome profile. profile list discovers profiles and
profile use <name> selects the default. Use doctor for connection diagnosis.
See opencli-browser for interaction, API evidence and tab/group management.
Adapters and installation
opencli adapter init example/search
opencli adapter check example/search
opencli adapter test example/search --args '{"query":"hello"}'
opencli adapter status
See opencli-adapter-author for implementation. adapter eject makes an official
site editable locally; adapter reset removes that local override. Adapter tests
execute real commands and can perform writes.
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.
- 6d ago Changed · -84 lines · -43 tokens per session cb7d9baabcc8
- 24d ago Changed · -20 lines 22761f2fcb5c
- 1mo ago First seen · 171 lines · 74 tokens per session scan A c15f0840b208
opencli-usage is a skill published in the GitHub repository mxyhi/ok-skills (505 stars, last pushed 7d ago), licensed Apache-2.0. It adds 31 tokens to every session and 575 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to opencli-usage, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
skill-trigger-auditor
Audit whether skills, agents and slash commands route correctly and safely, and whether a trigger regression test is needed. Use before changing routing metadata or widening a description.
subagent-driven-development
A development workflow in which a fresh coding agent implements each independent task, another review checks that task, and a final review examines the complete set of changes.
performance-optimization
Measure first, optimize second. Data-driven performance improvements with before/after benchmarks and production validation.