cx-devassist-asca

cx-devassist-asca is a cursor rule for coding agents from Checkmarx/cx-agentic-ai. It costs 0 tokens per session (737 once invoked), scanned A, original, Apache-2.0.

A rule for finding and fixing security vulnerabilities in source-code files using Checkmarx ASCA, a static analysis scanner. Static analysis checks code without running it.

In plain words
What is it for?
Scanning files such as Python, JavaScript, and Java; reporting each finding; and applying or suppressing fixes after the user decides how to handle them.
Why use it?
It separates source-code security checks from dependency and infrastructure checks, so findings are sent to the appropriate process.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/checkmarx/cx-agentic-ai/cx-devassist-asca
Clone the repo
git clone --depth 1 https://github.com/Checkmarx/cx-agentic-ai

Wrote 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.

agentmods badge for cx-devassist-asca

README.md
[![agentmods](https://agentmods.dev/badge/rules/checkmarx/cx-agentic-ai/cx-devassist-asca.svg)](https://agentmods.dev/rules/checkmarx/cx-agentic-ai/cx-devassist-asca)
Your own site
<a href="https://agentmods.dev/rules/checkmarx/cx-agentic-ai/cx-devassist-asca"><img src="https://agentmods.dev/badge/rules/checkmarx/cx-agentic-ai/cx-devassist-asca.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00737
Opus 5 $0.00000 $0.00368
Sonnet 5 $0.00000 $0.00147
Haiku 4.5 $0.00000 $0.00074

Measured 4d ago against content hash c7694016f928, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cx-devassist-asca 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.

plugins/cursor-devassist/rules/cx-devassist-asca.mdc · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CX DevAssist ASCA (SAST)

Use for source code vulnerability scan/fix. For dependency manifests/lockfiles, use cx-devassist-sca instead.

Routing

Target Use
Source file (.py, .js, .java, …) This rule / /cx-devassist-asca
Manifest/lockfile (package.json, go.mod, …) cx-devassist-sca
Whole repo / cloud scans Checkmarx MCP scan tools

If findings are already in context (hook deny agent_message, CHECKMARX_HOOK_DENY block, prior scan, stop-hook followup_message), skip scan — go straight to remediation. Never retry a blocked Write/StrReplace or paste blocked code in chat.

Scan

# Unix:
"$HOME/.checkmarx/bin/cx" scan asca -s "<file-path>"
# Windows:
"$LOCALAPPDATA/Checkmarx/cx/cx.exe" scan asca -s "<file-path>"

Report findings (rule_name, severity, line, description). Ask the user whether to remediate (fix) or suppress (false positive) each finding before proceeding.

Remediation (MCP-only)

For each finding, call mcp__plugin-cx-devassist-Checkmarx__codeRemediation with type: "sast" and metadata from the scan.

  • MCP available → apply remediation_steps in order; change only code at/near the problematic line
  • MCP unavailableSTOP. No manual fixes. Run /cx-cli-setup if auth fails; ask developer to Developer: Reload Window for MCP

After fixes, re-scan. Remediate only in-scope findings (your changes or the original target); leave pre-existing findings unfixed.

Skill compliance (mandatory)

Invoke and follow skills/cx-devassist-asca/SKILL.md exactly as written — as-is, with no paraphrasing, summarizing, or reimplementing its steps inline in this rule or in chat. Do not skip, abbreviate, substitute your own judgment for, or reorder any step.

The Step 5 Remediation Summary is mandatory output — always produce and show it to the user verbatim, in full, after remediation completes, even for a single finding. Never omit it, shorten it, or fold it into other output:

Read the full file on GitHub · 65 lines

Changes

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.

  1. 4d ago First seen · 65 lines · 0 tokens per session scan A c7694016f928

Subscribe to this mod's changes

cx-devassist-asca is a cursor rule published in the GitHub repository Checkmarx/cx-agentic-ai (0 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 737 tokens. 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 2026-08-31.