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/argos-ci/argos-javascript/argos-uploadnpx skills add argos-ci/argos-javascript --skill argos-uploadgit clone --depth 1 https://github.com/argos-ci/argos-javascriptWhat 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 | $0.00168 | $0.02935 |
| Opus 5 | $0.00084 | $0.01468 |
| Sonnet 5 | $0.00034 | $0.00587 |
| Haiku 4.5 | $0.00017 | $0.00294 |
Grade A, and why
argos-upload 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 2d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Argos media upload
argos media upload <files...> uploads standalone images and videos — not tied
to a build or a test run — and prints a share URL and a Markdown embed for each.
argos media upload checkout-before.png checkout-after.png --branch feat/checkout
Run argos media --help for exact flags. This skill covers the parts --help
cannot: when to upload, how the result reaches a human, and how to read back what
they say about it.
When to upload
Upload when a change is visual and a human has to see it to judge it:
- You changed UI and are working on a branch or a pull request. A before/after pair saves the reviewer from checking out your branch.
- You recorded a Playwright video or a screen recording of a bug reproduction.
- You are reporting a rendering problem that a code snippet cannot convey.
Do not upload when text does the job. A stack trace, a diff, a log excerpt and a list of failing test names are all better as text: searchable, quotable, and readable in a terminal. An unnecessary screenshot is noise in the review.
Do not upload build screenshots that Argos already has. If a visual test run
produced them, they are already in the build and linked from the pull request —
use argos build snapshots instead.
Getting it into a pull request
Name where the media belongs and Argos does the posting. It keeps one comment per pull request listing every media attached to it, edited in place rather than appended to.
argos media upload after.png --pr 1234 # the pull request exists
argos media upload after.png --branch feat/checkout # it does not, yet
--branch is the one to reach for while working. The media is staged: it has
its share URL immediately, and the moment a pull request opens for that branch
Argos attaches it and posts the comment on its own. You do not have to come back
and connect the two. --pr publishes straight away.
Passing neither uploads a loose media: a share URL and nothing else. That is the
right call for a chat message or an issue, where you paste the Markdown yourself.
Neither flag is inferred from the environment, CI included — an upload does not
post to a pull request unless you asked it to. Two consequences worth knowing
before you leave them off: nothing will ever attach that media to a pull request,
and since a loose media's identity is only its name, uploading shot.png from two
different branches makes them versions of one media rather than two.
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.
- 2d ago First seen · 259 lines · 168 tokens per session scan A a8ea9950e843
argos-upload is a skill published in the GitHub repository argos-ci/argos-javascript (18 stars, last pushed 7d ago), licensed MIT. It adds 168 tokens to every session and 2,935 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
write-gitbook
A comprehensive guide for editing GitBook documentation in external environments like Cursor, Claude Code, or other text editors. This skill provides all the formatting syntax, configuration options, and best practices needed to create and maintain GitBook content outside the GitBook web interface.
documentation-writer
Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.
notebooklm
Complete API for Google NotebookLM - full programmatic access including features not in the web UI. Create notebooks, add sources, generate all artifact types, download in multiple formats. Activates on explicit /notebooklm or intent like "create a podcast about X".
keploy-docs
Guide for contributing to the Keploy documentation site at github.com/keploy/docs. Invoke when a change in keploy/keploy introduces, removes, or alters user-visible behavior (new CLI flag, changed default, new command, new configuration field, new on-disk format) and the docs need to catch up — or when the user asks…
wxjava-module-selector
根据微信公众号、小程序、微信支付、企业微信、开放平台、视频号或微信小店、腾讯企点和微信智能对话等业务场景，为用户选择合适的 WxJava Maven 模块、BOM 和示例入口。适用于用户询问“该用哪个模块”、依赖坐标、产品边界或单/多账号 Starter 选择时。.
wxjava-api-contributor
按 WxJava 的 Maven 多模块、Java 8、公共 API 兼容性和 TestNG 约定，为微信官方接口新增或维护 SDK 支持。适用于新增 Service API、请求响应 Bean、序列化、HTTP 实现、Starter 配置或回归测试时。.