Scans every file Claude writes for insecure code and hard-coded secrets with the local kestrix-scan scanner and has Claude fix the findings; checks package installs against a local OSV index; secure-review skills and /kestrix:scan, /kestrix:fix and /kestrix:review. Offline; hooks open no network connections.
Plugin kestrix from marketplace kestrix in Ruthvik-Bandari/kestrix-claude-plugin. Commands read from the repo's manifest — 2 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
fixScan a path with Kestrix, fix every finding at medium severity or above, and re-scan until clean or explained.
fixing-security-findingsPer-rule fix playbook for Kestrix security findings, with before and after code for every rule id (py.*, js.*, php.*, go.*, java.*, cs.*, rb.*, c.*, rust.*, swift.*, sql.*, vue.*, svelte.*, html.*, css.*, web.*, next.*, gha.*, docker.*, sh.*, tf.*, k8s.*, config.*, secret.* and dep.*). Use when a Ke
kestrix-securityRuns the local Kestrix command line tool to check things on the user's own machine and explain the result. Use when the user asks whether an email or .eml file is phishing, a scam or spoofed, whether a link or URL is safe to click, what a suspicious file, download or attachment really is, whether a
reviewSecure review of the current git diff with Kestrix, limited to changed lines.
scanRun a Kestrix security scan on a path and summarize the findings.
secure-code-reviewReviews code for security flaws with the local Kestrix scanner, fixes each finding and re-scans. Use when the user asks for a security review or to review this for security, asks "is this code safe" or "is this secure", or wants to find insecure code, check for vulnerabilities, audit or harden code.
statusShow what the Kestrix hooks did in this session: files scanned, findings reported, and files that were not security-checked, with the reason.
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/kestrix_hook.py" session-start
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/kestrix_hook.py" pre-tool-use
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/kestrix_hook.py" install-guard
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/kestrix_hook.py" post-tool-use
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/kestrix_hook.py" bash-post
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/kestrix_hook.py" stop
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/kestrix_hook.py" bash-post
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
hooks
Cross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails
3 skills · 1 command · 1 agent
Install the "AAS Security Engineer" editorial skill bundle for Claude Code.
12 skills
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
12 skills · 1 MCP server · hooks
Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture
24 skills · 2 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.