Axguard Evidence — Security skill for Claude Code
Evidence & Confidence diagnostic (not a vuln report).
How to install Axguard Evidence
Installs to ~/.claude/skills/awarexone-axguard-axguard-evidence/SKILL.md
mkdir -p ~/.claude/skills/awarexone-axguard-axguard-evidence && curl -fsSL https://raw.githubusercontent.com/Awarexone/AXguard/HEAD/commands/axguard-evidence.md -o ~/.claude/skills/awarexone-axguard-axguard-evidence/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Axguard Evidence does
description: Evidence & Confidence diagnostic (not a vuln report). Usage: /axguard-evidence [path]
/axguard-evidence
**Specialist:** Evidence & Confidence engine
Usage
/axguard-evidence
/axguard-evidence ./app
Focus
Deterministic Phase 5 pass after the False Positive Adversary:
- Collects supporting and counter evidence per finding (source, flow, sink, controls, framework, config, reachability, trust boundary, …)
- Deduplicates evidence into a shared stor
Alternatives in Security
- Memory Self Review — Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMOR 297 ★
- CodexQB — CodexQB is a Codex plugin for evidence-backed repo comprehension, planning, QA audit, and gated implementation 186 ★
- Gdpr Review — Audit the codebase (or a given path/feature) for GDPR compliance and produce a prioritized findings report 172 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Axguard Adversary
False Positive Adversary diagnostic (not a vuln report). Usage: /axguard-adversary [path]
Axguard Report
Regenerate or polish Markdown/HTML audit reports. Usage: /axguard-report [path]
Hunt
Start hunting on a target — loads scope, reads disclosed reports, picks best attack surface based on tech stac
Vuln Report Skill
Claude Code skill: turn confirmed vulnerabilities into submission-ready DOCX reports 漏洞报告成稿 skill(SRC/0day 提交稿
Design Audit Squad
Orchestration complète Lyse Design Squad: 12 agents UI/DS/agent-surface, Lyse statique optionnel, taste, a11y,
Audit Ur Harness
An Agent Skill that audits a project's AI harness — guardrails, memory, verification, observability, tool desi
Related Agents
Finding Reporter
Phase 14 per-finding report authoring agent. Reads a single finding directory (draft.md, debate.md, adversaria
Stamity Reviewer
Reviews a change set across ten quality lenses and returns a verdict with confidence and graded findings, each
Vuln Confidence Scorer
Second-opinion confidence scorer for one vuln-scan finding. Spawn with a finding block and target dir — not fo