The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
chore: update AgentShield stats to 35 rules, 14 patterns, 487 tests
Affaan Mustafa8769064a3b0e
diff --git a/README.md b/README.mdindex d72f7058f..eb1010c3d 100644--- a/README.md+++ b/README.md@@ -368,7 +368,7 @@ Both options create:### AgentShield — Security Auditor-> Built at the Claude Code Hackathon (Cerebral Valley x Anthropic, Feb 2026). 387 tests, 98% coverage, 16 static analysis rules.+> Built at the Claude Code Hackathon (Cerebral Valley x Anthropic, Feb 2026). 487 tests, 98% coverage, 35 static analysis rules.Scan your Claude Code configuration for vulnerabilities, misconfigurations, and injection risks.@@ -386,7 +386,7 @@ npx ecc-agentshield scan --opus --streamnpx ecc-agentshield init```-**What it scans:** CLAUDE.md, settings.json, MCP configs, hooks, agent definitions, and skills across 5 categories — secrets detection (11 patterns), permission auditing, hook injection analysis, MCP server risk profiling, and agent config review.+**What it scans:** CLAUDE.md, settings.json, MCP configs, hooks, agent definitions, and skills across 5 categories — secrets detection (14 patterns), permission auditing, hook injection analysis, MCP server risk profiling, and agent config review.**The `--opus` flag** runs three Claude Opus 4.6 agents in a red-team/blue-team/auditor pipeline. The attacker finds exploit chains, the defender evaluates protections, and the auditor synthesizes both into a prioritized risk assessment. Adversarial reasoning, not just pattern matching.