Architecture auditor
Skill rafaelghif/antigravity-agents/.agents/skills/architecture-auditor
Enterprise-Grade Guardrails, Zero-Assumption Execution, and Quality Gates for Autonomous AI Coding Agents.
npx -y skills add rafaelghif/antigravity-agents --skill architecture-auditorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Holistic Impact Analysis, blast radius, extensibility.
SKILL.md
1.7 KB, as published. Nobody here has run it
Architecture Auditor Skill
Objective
Enforce the "World-Class Engineering Mindset" defined in AGENTS.md (Holistic Impact checks).
When to Execute
- BEFORE starting any medium-to-large feature implementation.
- BEFORE refactoring existing core modules.
- Objective Skip Conditions (AND logic):
- Code changes < 10 lines (excluding tests)
- No new dependencies
- No new endpoints/APIs
- No schema changes
- Test coverage remains >= current level
If uncertain, produce a 2-line summary in
.agents/plans/audit-quick-<date>.md.
Execution Steps
- Execute the Holistic Impact checks explicitly listed in AGENTS.md (Blast Radius, Future-Proofing, Reusability, Performance, Security).
- Produce an "Audit Report" artifact inside
.agents/plans/audit-<slug>-<date>.mdbefore writing code. - Use the following explicit template for the report:
- Blast Radius: Modules impacted directly/indirectly.
- Future-Proofing: Number of hardcoded values > 3? Business logic vs. presentation mixed? API response fields not versioned? Constants used in > 5 files?
- Deprecation Debt: Add scoring (1pt per deprecated API version, 3pt per unpatched CVE, 5pt for EOL within 12 months). Score > 10 → mandatory technical debt ticket creation.
- Reusability: Shared utility extraction potential.
- Performance: Algorithmic complexity and bottlenecks.
- Security: Authentication, authorization, and data exposure.
- Mitigations: Planned actions for identified risks.