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/checkmarx/cx-agentic-ai/cx-cli-setupnpx skills add Checkmarx/cx-agentic-ai --skill cx-cli-setupgit clone --depth 1 https://github.com/Checkmarx/cx-agentic-aiWrote 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/checkmarx/cx-agentic-ai/cx-cli-setup)<a href="https://agentmods.dev/skills/checkmarx/cx-agentic-ai/cx-cli-setup"><img src="https://agentmods.dev/badge/skills/checkmarx/cx-agentic-ai/cx-cli-setup.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 | $0.00051 | $0.03248 |
| Opus 5 | $0.00026 | $0.01624 |
| Sonnet 5 | $0.00010 | $0.00650 |
| Haiku 4.5 | $0.00005 | $0.00325 |
Grade B, and why
cx-cli-setup scanned grade B with 1 finding 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
(Windows: `%USERPROFILE%\.checkmarx\checkmarxcli.yaml`) — protect it like an SSH key (`chmod 600`). How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CX CLI Setup
Guides the developer through installing, upgrading, and authenticating the Checkmarx One cx CLI so
the security plugin can operate. The OS is known from the Cursor session — use the matching
path; no detection command is needed. Detailed steps live under references/ (see Additional
Resources); this router is the spine.
When to Use
- The
cxCLI is not installed or not found in PATH - A hook blocked a scannable file write because
cxis missing or below the minimum version - The developer explicitly runs
/cx-cli-setupto reconfigure or reauthenticate - The plugin detected expired credentials and needs a re-auth step
Phase 0 — Assess Current State
Run both checks to decide where to enter. Run them as two separate commands, one at a time —
never chained with ||/&&/;: the security gate only lets a bare, unchained command through
this early (before cx is installed/authenticated), so a chained probe is itself blocked and never
reaches cx at all. The OS is already known from the Cursor session, so run only the matching
Check 1 — do not try both:
# Check 1 — is the CLI present? (bare command, no chaining/redirect)
which cx # bash / sh (macOS, Linux, Git Bash)
where cx # cmd.exe
Get-Command cx # PowerShell
# Check 2 — only if present (identical in every shell)
cx auth validate
Shell syntax matters from here on. Cursor's Shell tool runs the workspace's default shell — PowerShell on Windows, bash/zsh on macOS/Linux,
cmd.exewhere configured — and they disagree about invoking a quoted path, discarding stdout, and referencing environment variables. Every per-shell form used below is spelled out once inreferences/shells.md; read it before writing a command that names an absolute path or a redirect.
| CLI present | Auth result | Action |
|---|---|---|
| No | — | Offer the custom-path option (references/troubleshooting.md), then go to Phase 1 |
| Yes | Success | Tell the developer all looks good; ask if they want to reconfigure/reauth anyway. If no, exit. |
| Yes | Credential failure (invalid/revoked/expired) | CLI is installed but auth failed — skip to Phase 2. |
| Yes | Network failure (DNS/refused/timeout) | CLI is installed but the server is unreachable — do not go to Phase 2; have them check network/proxy, then re-run cx auth validate. |
What ships with it
7 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.
- 3d ago First seen · 230 lines · 51 tokens per session scan B cbb2c5a8aac5
cx-cli-setup is a skill published in the GitHub repository Checkmarx/cx-agentic-ai (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 51 tokens to every session and 3,248 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mcp2cli
Use mcp2cli to connect to, explore, and execute commands against any MCP (Model Context Protocol) server from the terminal. Covers discovery, tool invocation, resource reading, prompt execution, alias creation, config management, background jobs, authentication, and JSON output pipelines.
loot-agent-mcp
You are playing LOOT on Robinhood Chain (4663) through the loot-agent-mcp tools. The game in one line: hold tokens through risk to mint loot boxes, play to earn keys, open boxes with keys, claim your pro rata share of the token's fee pot in ETH. Pots grow when the token trades. Selling burns your game position for the…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
quick-capture
Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.
chainstack
Work with the Chainstack MCP server to manage blockchain nodes and projects. Use when deploying nodes, migrating to Chainstack from another RPC provider such as QuickNode or Alchemy, checking platform status, searching Chainstack docs, contacting the Chainstack team, or interacting with the Chainstack platform API via…
freshness-check
Model-aware staleness check before asserting how a PoE mechanic/item/system works, plus a scope filter so league/event mechanics don't bleed into the wrong character. Routes to freshnessindex.md + mechanicsindex.md.