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 Checkmarx/cx-agentic-ai --skill cx-install-wiringgit 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-install-wiring)<a href="https://agentmods.dev/skills/checkmarx/cx-agentic-ai/cx-install-wiring"><img src="https://agentmods.dev/badge/skills/checkmarx/cx-agentic-ai/cx-install-wiring/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/checkmarx/cx-agentic-ai/cx-install-wiring"><img src="https://agentmods.dev/badge/skills/checkmarx/cx-agentic-ai/cx-install-wiring.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 | $0.00069 | $0.01280 |
| Opus 5 | $0.00034 | $0.00640 |
| Sonnet 5 | $0.00014 | $0.00256 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade B, and why
cx-install-wiring 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 9d 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.
Tells the agent never to refusemediumAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
description: "On-demand first-time Checkmarx DevAssist setup (intended for Cursor CLI): wires hooks and rules, then continues into cx CLI install and auth. When the developer types /cx-install-wiring, always run the work Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CX Install Wiring (on demand — intended for Cursor CLI)
On-demand only — runs when the developer explicitly types /cx-install-wiring. Do not auto-invoke
this skill from hook denies or missing cx.
If /cx-install-wiring was invoked — always run Phase 1
There is no reliable environment signal to tell Cursor CLI from the IDE Agent panel. When the
developer typed /cx-install-wiring, proceed immediately with Phase 1 (scope → install-hooks.sh).
Forbidden:
- Refusing with "this skill runs only from Cursor CLI" or telling them to open a terminal / run
agent/ type/cx-install-wiringagain — unless they explicitly say they are in the IDE chat panel and cannot use the Shell tool. - Guessing that the session is IDE based on workspace paths, Windows paths, or chat UI alone.
Documentation note (not a gate): This flow is designed for Cursor CLI (terminal agent). IDE
users who need hooks should run install-hooks.sh manually (see README) or use /cx-cli-setup for
cx only — but do not block a slash-command invocation on that assumption.
Never tell the developer to use Developer: Reload Window, the Command Palette, or IDE MCP settings — those apply to the IDE, not Cursor CLI.
Then wire hooks and rules and automatically continue into cx install/auth via
skills/cx-cli-setup/SKILL.md — do not ask the developer to run /cx-cli-setup separately.
Do not run Get-Command cx, cx auth validate, or any other cx command in this phase.
Scope
Question 1 — ask once:
"Install Checkmarx hooks and rules for: (1) User — all projects (
~/.cursor/), or (2) Project — one specific repo (<repo>/.cursor/)?"
- User → run
install-hooks.shwith no extra env vars (see below). - Project → ask Question 2 before running the installer. Do not assume "this repo" without the developer's choice.
Question 2 — only when they chose Project:
"Which repo should get project-scoped hooks and rules? (A) This repo — the directory you're in now (
<show resolved absolute path>) (B) Another path — reply with the absolute path to that repo's root."
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.
- 9d ago First seen · 109 lines · 69 tokens per session scan B 83f5b21e9183
cx-install-wiring is a skill published in the GitHub repository Checkmarx/cx-agentic-ai (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,280 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (tells the agent never to refuse). 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 — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, then fills the gaps with list (filters, sort, a time…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
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.
maintenance
Update mcp-reporter dependencies, adopt SDK changes, reconcile development workflows, and verify the CLI and library.