The README.md was completely rewritten in a single update. Below is a categorized breakdown of all modifications with before/after comparisons based on codebase exploration.
1. Header & Badges
Aspect
Before
After
Banner
Basic project name
Full banner image + tagline "The open-source AI pentesting tool. Autonomous AI hackers..."
### Issue 1
README.md:306
`--scan-mode` accepts only `quick`, `standard`, and `deep`, so copying this example gives an argument error instead of a scan. Use `--scope-mode diff` here, and describe Diff as a scope option rather than a fourth scan mode.
Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!
### Issue 2
README.md:214
The new catalogue overstates the shipped library and includes incorrect examples:
- It claims `100+` skills, but there are 75 skill files, of which 65 are user-selectable.
- `webhooks` does not exist, so the loader skips requests for it.
- `semantic_confusion` belongs under Vulnerabilities, not Custom.
Update the count and examples to match the bundled files.
---
For each issue above, determine whether it is valid and should be fixed. If so, fix it directly.
Summary
Expands README.md with local and cloud workflows, a skills catalogue, scan examples, and documentation links.
The README now walks readers through Strix Cloud scans and source uploads.
The README now shows how to start and manage local scans.
The README now maps Strix security coverage, skills, and scan modes.
Readers can now jump from the README to focused Strix guides.
The README’s existing wording and headings read more cleanly without changing scan behavior.
README.md Modification Review
Overview
The
README.mdwas completely rewritten in a single update. Below is a categorized breakdown of all modifications with before/after comparisons based on codebase exploration.1. Header & Badges
2. Quick Start Section
curl -sSL https://strix.ai/install | bash+ provider configstrix --target ./app-directorywith concrete examplestrix --update+pipx/uv/pipfallbacks3. Run Modes Comparison Table (NEW)
4. Open Source CLI Details (EXPANDED)
strix -n -t ./ --scan-mode quick --max-budget 100= clean,1= fatal,2= vulns foundpenetration_test_report.md,vulnerabilities/*.md,vulnerabilities.json,findings.sarif,run.jsonllm_usage.costvs budget before calling clean5. Strix Cloud CLI (MAJOR EXPANSION - from
cloud/spec.py)strix cloud login --scopes scans:read scans:write uploads:write billing:readstrix cloud domains add --domain example.com --asset-type web_appstrix cloud scans start --engagement-type live_test --domain-ids <uuid> --wait--dry-run --show-files --json→ capture SHA256 →--approve-sha256strix cloud vulns list --severity criticalstrix cloud billing topup --credits 20 --yesstrix cloud workspaces list|create|usestrix cloud session scopes|scopes setstrix cloud org members invitestrix cloud billing subscribe --plan strix_cloud,billing portalstrix cloud integrations install githubstrix cloud domains verify <id>--json; exit codes documented6. Agent Skills Integration (NEW SECTION)
npx skills add usestrix/strixAGENTS.mdpenetration-testing-with-strix,managed-pentesting-with-strix,fix-security-vulnerabilities-with-strix,ci-security-scanning-with-strix,application-security-testing,web-app-penetration-testing,api-security-testing,owasp-top-10-testing,find-security-vulnerabilities-in-codeAGENTS.md,docs.strix.ai/llms.txt,docs.app.strix.ai7. Features Section (REORGANIZED & EXPANDED)
7.1 Agentic Pentesting Tools
7.2 Comprehensive Vulnerability Scanner
7.3 Graph of Agents (Multi-Agent)
7.4 Skills System (100+ Skills) (NEW - from
skills/README.md)sql_injection,xss,idor,race_conditions,rce,ssrfdjango,fastapi,nextjs,nestjssupabase,firebase,auth0,llm_applicationsgraphql,oauth,webhooksnmap,nuclei,httpx,ffuf,subfinder,sqlmapaws,azure,gcp,kubernetesasset_discovery,infrastructure_lifecyclenpx_confusion,dependency_cve_scanning,semantic_confusionquick,standard,deep,diffNotable Advanced Skills (from
skills/README.md):source_aware_whitebox- white-box orchestrationsource_aware_sast- Opengrep/AST/secrets/supply-chainbrowser_security- postMessage, XS-Leaks, service workersagentic_system_security- MCP/tool ecosystemllm_prompt_injection- direct, indirect, multimodal, memory, tool-resultargument_injection- CLI option smuggling7.5 Scan Modes (NEW TABLE)
8. Local Web Viewer (NEW SECTION - from
viewer/cli.py)strix viewstrix view my-run-namestrix view --host 0.0.0.0 --port 8080 --no-openFeatures: Findings dashboard, live agent map, past runs, tokened URLs for authorization.
9. Usage Examples (EXPANDED)
9.1 Basic Usage
9.2 API Testing (NEW)
9.3 Advanced Scenarios (NEW)
10. Headless Mode (EXPANDED)
-n/--non-interactive11. CI/CD GitHub Actions (NEW WORKFLOW)
12. Configuration (EXPANDED)
12.1 Environment Variables
12.2 ChatGPT Subscription Auth (NEW - from
main.py/auth_cli.py)12.3 MCP Server Configuration (NEW - from
main.py/config)Tools namespaced as:
github_list_issues13. Recommended Models (UPDATED with latest models)
vercel_ai_gateway/zai/glm-5.3openrouter/z-ai/glm-5.3openrouter/deepseek/deepseek-v4.1-flash-1017openai/gpt-6.1-solanthropic/claude-opus-5-5vertex_ai/gemini-4-argondeepseek/deepseek-v4-promoonshot/kimi-k3.1-pro14. Documentation Links (COMPREHENSIVE)
15. Legal Disclaimer (ENHANCED)
Summary Statistics
Risk Assessment