igmrrf/agentic
Multi-language engineering standards, agent rules, and agent skills, set up in any project with one command.
Optional terse conversational voice, activated explicitly with /caveman or a request for caveman mode. Persists until disabled; preserves technical facts and full artifacts.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Deliver software tasks from acceptance criteria through implementation, independent review, automated tests, live product verification, and production readiness, with at most two fix cycles.
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
Ground repository documentation in real code with bounded workers.
Explore architectural alternatives and record a concepts brief.
Draft a self-contained architecture specification from requirements.
Compare architectural documentation with implementation without modifying source.
Evaluate architectural review findings and apply authorized document repairs.
Review a design through five independent Goldfish stages.
Run a bounded antagonistic document review and resolution loop.
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/comprehensive/end-to-end reviews, or requested report artifacts.
Apply the Agentic engineering standards to the current project — agent rules (CLAUDE.md and others), linter/formatter configs, and CI workflows for Rust, Go, TypeScript, Python, Lua, Swift, or Kotlin. Use when the user invokes /setup or /agentic:setup, or asks to adopt or bootstrap these coding standards in a repository.
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.