Skip to main content
[COMMANDS]

Command Reference

Every @xor-hardener command on one page. /review, /describe, /ask, /patch_i, /issue_spec, /issue_implement, and more.

Quick reference

9 commands: /review, /describe, /ask, /ask_line, /issue_spec, /issue_implement, /issue_ask, /test_i, /patch_i. All available via natural language or explicit command syntax.

Automatic triggers

Dependabot PR → automatic triage. XOR-labeled PR → /describe + /review. Push to PR branch → configurable re-checks.

9
Commands available
3
Automatic triggers
NL
Natural language supported

Every command. One page.

Mention @xor-hardener followed by a command or a plain-English prompt. Both work. XOR reads your intent, decides which capability applies, and runs it.

Quick reference

CommandWhereWhat it does
/reviewPR commentSecurity-focused code review with inline suggestions
/describePR commentGenerate a structured PR description
/ask [question]PR commentAsk a question about the PR code
/ask_lineLine commentAsk about specific lines in "Files changed"
/issue_specIssue commentGenerate a specification for an issue
/issue_implementIssue commentImplement a solution and open a PR
/issue_ask [question]Issue commentAsk a question about an issue
/test_iPR or issueExtract or generate test cases
/patch_iPR or issueGenerate patches from an issue spec

Natural language prompts

You don't need to memorize commands. Examples:

@xor-hardener Review this PR for security issues.

@xor-hardener This issue describes a bug in our auth flow. Write a spec for fixing it, then open a PR with the fix.

@xor-hardener Pin all actions in this workflow to SHA. Reduce permissions to least-privilege.

@xor-hardener What does this function do? Is it safe to remove the null check on line 42?

Automatic triggers

Dependabot opens a PR

XOR triages automatically with reachability + EPSS/KEV/CVSS

PR labeled with XOR label

XOR runs /describe + /review

Push to PR branch

XOR re-runs configured checks (configurable)

The two-step issue workflow

For larger work items:

Step 1: /issue_spec

XOR reads the issue, researches the codebase, and posts either questions (if it needs context) or a plan (if it has enough information).

Step 2: /issue_implement

XOR reads the approved plan, generates patches, creates a branch, and opens a PR with the fix and updated tests. You approve the plan before code is written.

[NEXT STEPS]

Start using XOR

FAQ

Do I need to use explicit commands?

No. XOR reads natural language. 'Review this PR for security issues' works the same as /review. Explicit commands are available for precision.

Which commands run automatically?

Dependabot PR triage runs automatically. PRs labeled with an XOR label get /describe + /review. Push-triggered checks are configurable.

What is the two-step issue workflow?

Step 1: /issue_spec — XOR researches the codebase and posts a plan. Step 2: /issue_implement — XOR generates patches and opens a PR. You approve the plan before code is written.

[RELATED TOPICS]

Patch verification

XOR writes a verifier for each vulnerability, then tests agent-generated patches against it. If the fix passes, it ships. If not, the failure feeds back into the agent harness.

Automated vulnerability patching

AI agents generate fixes for known CVEs. XOR verifies each fix and feeds outcomes back into the agent harness so future patches improve.

Benchmark Results

62.7% pass rate. $2.64 per fix. Real data from 1,664 evaluations.

Benchmark Results

62.7% pass rate. $2.64 per fix. Real data from 1,664 evaluations.

Agent Cost Economics

Fix vulnerabilities for $2.64–$52 with agents. 100x cheaper than incident response. Real cost data.

Agent Configurations

13 agent-model configurations evaluated on real CVEs. Compare Claude Code, Codex, Gemini CLI, Cursor, and OpenCode.

Benchmark Methodology

How CVE-Agent-Bench evaluates 13 coding agents on 128 real vulnerabilities. Deterministic, reproducible, open methodology.

Agent Environment Security

AI agents run with real permissions. XOR verifies tool configurations, sandbox boundaries, and credential exposure.

Security Economics for Agentic Patching

Security economics for agentic patching. ROI models backed by verified pass/fail data and business-impact triage.

Validation Process

25 questions we ran against our own data before publishing. Challenges assumptions, explores implications, extends findings.

Cost Analysis

10 findings on what AI patching costs and whether it is worth buying. 1,664 evaluations analyzed.

Bug Complexity

128 vulnerabilities scored by difficulty. Floor = every agent fixes it. Ceiling = no agent can.

Agent Strategies

How different agents approach the same bug. Strategy matters as much as model capability.

Execution Metrics

Per-agent session data: turns, tool calls, tokens, and timing. See what happens inside an agent run.

Pricing Transparency

Every cost number has a source. Published pricing models, measurement methods, and provider rates.

Automated Vulnerability Patching and PR Review

Automated code review, fix generation, GitHub Actions hardening, safety checks, and learning feedback. One-click install on any GitHub repository.

Getting Started with XOR GitHub App

Install in 2 minutes. First result in 15. One-click GitHub App install, first auto-review walkthrough, and engineering KPI triad.

Platform Capabilities

One install. Seven capabilities. Prompt-driven. CVE autopatch, PR review, CI hardening, guardrail review, audit packets, and more.

Dependabot Verification

Dependabot bumps versions. XOR verifies they're safe to merge. Reachability analysis, EPSS/KEV enrichment, and structured verdicts.

Compliance Evidence

Machine-readable evidence for every triaged vulnerability. VEX statements, verification reports, and audit trails produced automatically.

Compatibility and Prerequisites

Languages, build systems, CI platforms, and repository types supported by XOR. What you need to get started.

Continuous Learning from Verified Agent Runs

A signed record of every agent run. See what the agent did, verify it independently, and feed the data back so agents improve.

Signed Compliance Evidence for AI Agents

A tamper-proof record of every AI agent action. Produces evidence for SOC 2, EU AI Act, PCI DSS, and more. Built on open standards so auditors verify independently.

Compliance Evidence and Standards Alignment

How XOR signed audit trails produce evidence for SOC 2, EU AI Act, PCI DSS, NIST, and other compliance frameworks.

Agentic Third-Party Risk

33% of enterprise software will be agentic by 2028. 40% of those projects will be canceled due to governance failures. A risk overview for CTOs.

MCP Server Security

17 attack types across 4 surfaces. 7.2% of 1,899 open-source MCP servers contain vulnerabilities. Technical deep-dive with defense controls.

How Agents Get Attacked

20% jailbreak success rate. 42 seconds average. 90% of successful attacks leak data. Threat landscape grounded in published research.

Governing AI Agents in the Enterprise

92% of AI vendors claim broad data usage rights. 17% commit to regulatory compliance. Governance frameworks from NIST, OWASP, EU CRA, and Stanford CodeX.

OWASP Top 10 for Agentic Applications

The OWASP Agentic Top 10 mapped to real-world attack data and XOR capabilities. A reference page for security teams.

See which agents produce fixes that work

128 CVEs. 13 agents. 1,664 evaluations. Agents learn from every run.