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-devassist-ascagit 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-devassist-asca)<a href="https://agentmods.dev/skills/checkmarx/cx-agentic-ai/cx-devassist-asca"><img src="https://agentmods.dev/badge/skills/checkmarx/cx-agentic-ai/cx-devassist-asca/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-devassist-asca"><img src="https://agentmods.dev/badge/skills/checkmarx/cx-agentic-ai/cx-devassist-asca.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 | $0.00188 | $0.05184 |
| Opus 5.5 | $0.00075 | $0.02074 |
| Sonnet 5.5 | $0.00038 | $0.01037 |
| Haiku 4.5 | $0.00019 | $0.00518 |
Grade A, and why
cx-devassist-asca scanned grade A 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 15d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
discovers it and syncs the `Checkmarx` server into `~/.codex/config.toml` (or 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CX Security ASCA
Detects and remediates SAST vulnerabilities in source files using Checkmarx ASCA.
When to Use
This skill has two entry points:
- On-demand scan — User asks to scan a source code file for vulnerabilities (e.g., "scan this
file", "check app.py for security issues"). If the target is a dependency manifest/lockfile
(package.json, requirements.txt, go.mod, …), use
cx-devassist-scainstead. - Remediation — User asks to fix ASCA findings, or Codex needs to fix SAST vulnerabilities detected by ASCA
If ASCA findings are already present in context (e.g., provided by a hook block or a prior scan result), skip Flow 1 entirely and proceed directly to Flow 2 using those findings. Do not run the initial scan; Flow 2's re-scan still applies.
Routing — which Checkmarx capability to use
Pick by the target, and ask if it is ambiguous:
| The user wants to scan… | Use |
|---|---|
A source code file (.py, .js, .java, .go, .ts, …) for code vulnerabilities |
this skill (SAST/ASCA) |
| A dependency manifest / lockfile (package.json, requirements.txt, go.mod, pom.xml, …) | cx-devassist-sca (SCA/OSS) |
| An entire project / repository at cloud scale, or existing platform scan results | the Checkmarx MCP (Cx1 cloud) tools |
A bare "scan this file" refers to whatever file is in context: source code → this skill; a
manifest/lockfile → cx-devassist-sca. If it is unclear which, ask the user.
Prerequisites
- Checkmarx
cxCLI installed. On a first-install sessioncxis in the canonical store but not yet on the agent shell's PATH, so invoke it by its absolute path —"$LOCALAPPDATA/Checkmarx/cx/cx.exe"on Windows,"$HOME/.checkmarx/bin/cx"on Unix (these env vars are available in the agent's shell) — and fall back to a barecxonly when it is already on PATH. - Checkmarx MCP server connected (required for remediation)
Remediation is MCP-only. Every fix MUST come from
mcp__Checkmarx__codeRemediation. If that tool is not available, you MUST NOT remediate by any other means — no manual edits, no generic or LLM-generated fixes, and do not apply theremediationAdvisetext yourself. Stop and recover the MCP first (see Flow 2 → Step 2, "If the tool is not available").
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.
- 15d ago Changed · +85 lines · +79 tokens per session 250e9781121f
- 1mo ago Changed · -60 lines 49e83de32d55
- 1mo ago First seen · 328 lines · 109 tokens per session scan A 8de8c172789d
cx-devassist-asca is a skill published in the GitHub repository Checkmarx/cx-agentic-ai (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 188 tokens to every session and 5,184 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). 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…
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…
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.
quantum-grover
A Qiskit implementation of Grover's algorithm, a quantum search method that increases the chance of finding a marked item. It can explain the method, build an explicit quantum circuit, or run it with chosen inputs.
alicebob-cat-circuits
A local simulator for Alice & Bob cat-qubit circuits, a type of quantum circuit that encodes information in oscillator states. It builds physical or error-corrected logical noise models, compiles the gates, and returns measurement samples and the model parameters used.