Skip to content

armgit / ECC

Public Imported from GitHub
0

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

1.7 KB
Raw Blame
# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
language: "en-US"
early_access: false
tone_instructions: "Be direct, concise, and evidence-led. Prioritize actionable findings over praise."

reviews:
  profile: "assertive"
  request_changes_workflow: false
  high_level_summary: true
  high_level_summary_in_walkthrough: true
  review_status: true
  review_details: true
  commit_status: true
  fail_commit_status: true
  auto_review:
    enabled: true
    drafts: false
  path_instructions:
    - path: ".github/workflows/**"
      instructions: |
        Treat workflow changes as security-sensitive. Flag unpinned third-party actions, broad write permissions, persisted checkout credentials in write-token jobs, pull_request_target misuse, and untrusted GitHub context interpolated into shell commands.
    - path: "{scripts,bin}/**"
      instructions: |
        Focus on command injection, unsafe subprocess usage, path traversal, SSRF, secret exposure, and missing tests for new CLI behavior.
    - path: "skills/**/scripts/**"
      instructions: |
        Review generated or imported scripts as untrusted-input tooling. Flag RCE, path traversal, network fetches without validation, and writes outside the expected workspace.
    - path: "{skills,commands,agents,rules}/**"
      instructions: |
        Focus on prompt-injection resilience, tool-permission scope, destructive action guards, and secret exfiltration risks.
    - path: "{SECURITY.md,docs/security/**}"
      instructions: |
        Check that official distribution surfaces, disclosure guidance, and supply-chain rules stay accurate and do not endorse unofficial packages.

chat:
  auto_reply: true