v2026.2.14 — Forensics & Manageability
Highlights
| What changed | Why you care |
|---|---|
| Forensics-complete DFIR framework | Full digital forensics lifecycle — 13 agents, 9 commands, 10 skills, Sigma hunting, evidence chain-of-custody |
| Codebase manageability tooling | Rules and tools to keep agent-generated code within context window limits |
| 17 specialist agents + 7 team configs | Cloud platform experts (AWS/Azure/GCP), framework specialists, pre-built team compositions |
| UAT-MCP toolkit addon | MCP-powered user acceptance testing with coverage tracking |
| 8 model & prompting guides | Optimization guides for Claude, GPT, local models, and prompting techniques |
Codebase Manageability (#402-#407)
New rules, commands, and skills that prevent agent-generated codebases from growing past context window limits:
agent-friendly-coderule — 300 LOC warning, 500 error thresholds per fileagent-generation-guardrailsrule — runtime checks before writing files/codebase-healthcommand — agent-readiness score with recommendations/complexity-gatecommand — CI pass/fail with baseline mode/decompose-fileskill — guided file splitting with import rewiring/code-chunkerskill — navigable structural maps of large files
Installation
npm install -g aiwg@2026.2.14
aiwg use sdlc # Re-deploy to get new rules, agents, commands, skills
aiwg use forensics # Deploy forensics frameworkFull Changelog
See v2026.2.14 announcement for complete details.