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/coralogix/cx-cli/add-skillnpx skills add coralogix/cx-cli --skill add-skillgit clone --depth 1 https://github.com/coralogix/cx-cliWrote 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/coralogix/cx-cli/add-skill)<a href="https://agentmods.dev/skills/coralogix/cx-cli/add-skill"><img src="https://agentmods.dev/badge/skills/coralogix/cx-cli/add-skill.svg" alt="Measured on agentmods" 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 | $0.00141 | $0.01683 |
| Opus 5 | $0.00071 | $0.00842 |
| Sonnet 5 | $0.00028 | $0.00337 |
| Haiku 4.5 | $0.00014 | $0.00168 |
Grade A, and why
add-skill 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a User-Facing Skill
End-to-end workflow for creating a skill in skills/ that teaches AI agents how to use a cx CLI command. This skill is often invoked from add-command Step 6, but can also be used standalone when documenting an existing command.
contributing/adding-a-skill.md has the full reference guide and a copy-pasteable template. Read it alongside this workflow.
Step 0: Understand the Domain
Before writing anything, answer these questions:
- What cx command are you documenting? Identify the command and all its subcommands (e.g.,
cx alerts list,cx alerts get,cx alerts create). - What can the user do with it? List the key operations, flags, and output formats supported.
- Who is the audience? Skills are consumed by AI agents, not humans directly. Write instructions an agent can follow step-by-step to accomplish a user's goal.
- Is there dense reference material? Schemas, enum catalogs, field references, or language syntax exceeding ~100 lines belong in a separate
references/file.
Step 1: Read Existing Skills
Before writing any skill, read existing ones to internalize the project's patterns. Agents that study existing skills first produce consistent, high-quality results rather than inventing new formats.
Always read:
contributing/adding-a-skill.md- full guide with directory structure, frontmatter conventions, reference file rules, and a copy-pasteable templateskills/README.md- the public catalog you'll update in Step 4
Study at least two existing skills:
| Skill | Why study it |
|---|---|
skills/cx-alerts/SKILL.md |
REST-based command with rich examples, JSON payloads, investigation workflow; uses both shared and skill-local reference files |
skills/cx-telemetry-querying/SKILL.md |
Gateway skill that loads shared reference files per pillar — good model for cross-pillar routing and reference-loading patterns |
skills/cx-dashboards/SKILL.md |
Complex multi-step workflow; uses shared references (dataprime, promql, logs, spans) plus skill-local references |
skills/cx-cost-optimization/SKILL.md |
Workflow skill covering 5 commands unified by "reduce costs" intent — good model for multi-command skills |
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 · 108 lines · 141 tokens per session scan A 9895b8e36a8e
add-skill is a skill published in the GitHub repository coralogix/cx-cli (116 stars, last pushed yesterday), licensed Apache-2.0. It adds 141 tokens to every session and 1,683 once invoked, about $0.0007 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
ce-compound
Document a solved problem as a durable repo learning. Use when verified work produced non-obvious reasoning absent from its final code, tests, or existing docs; avoid routine fixes whose artifacts already explain the lesson.
pptx-import
会话里有上传的 .pptx，且用户要把这份幻灯片填进一节已建的课（先 createstage 建课，再 importpptx 把页面追加进这节课堂，保留原版排版；课堂标题以 createstage 为准，PPT 不接管）。随后逐页检查（有 renderscenepreview 就渲染看）并修 bad case，理解整课之后才写旁白/spotlight，最后 TTS。仅在用户要求时插入 quiz 或 interactive。不要重新规划整课。.
learn-everything
Turn an uploaded PDF, paper, book chapter, document, URL, or user-provided topic into a structured, interactive learning course. Use when the user wants to learn, study, understand, master, review, or practice a subject chapter by chapter; asks for a tutorial or curriculum from source material; wants exercises…
office-pptx
Use when the user asks to create, inspect, verify, polish, or deliver PowerPoint .pptx decks, Google Slides-targeted deck artifacts, strategy narratives, operating reviews, pitch decks, teaching decks, section slides, bullet slides, or source-to-PPTX transformations.
readme-critique
High-judgment whole-document review for shape, pedagogy, and design-rationale. Catches the catalog-vs-teaching, composition-vs-enumeration, running-domain-vs-ad-hoc failure modes that readme-verify's gates pass on. Runs between draft and verify.
read-book
When you want to read and extract structured notes from a book — PDF, EPUB, MOBI, markdown, .txt, pasted text, or URL to a public-domain work. Reads in chunks (by chapter when a TOC exists, by 50-page blocks otherwise), extracts per-chapter TL;DR + key concepts + quotes + action items + frameworks, and offers to…