Skip to content

v2.8.0 — Tri-Audit Consolidation

Choose a tag to compare

View all tags
@Harery Harery released this 12 Jun 22:24
· 22 commits to main since this release
v2.8.0
53b179b

What is Praetor?

Praetor (Production Readiness, Audit, Evidence, Testing, Operations & Review) is a single-prompt, multi-agent orchestration framework that transforms any codebase into a comprehensive production readiness audit package. Paste one prompt into your LLM — 18 autonomous domain experts overseen by a 4-Judge Quality Council perform multi-disciplinary audits with 100% source-code traceability.

🚀 What's New in v2.8.0

Tri-Audit Consolidation

Three independent BALA7-30 audits ran on v2.7.8 — ~75 distinct valid findings fixed, 10 false positives documented, all declined changes explained with reasons.

Headline Changes

Theme What Changed
🛡️ Verification-layer honesty Checker v2.8: real U4 usage scans, template field checks, file-count assertions, vocabulary-residue sweep
📋 Register schemas Universal entry fields for all 12 registers, PRV expanded to 10 columns, append-only numbering rule
🔄 Run-control determinism Parsing order, multi-line block delimiters, snapshot format upgrade with manifest-hash fingerprint
🔗 Handoff graph completed A08→A17, A10→A02 escalation, A06→A16 for unanchored CRITICALs, deadlock rules
📝 Templates & categories Five mandatory artifact fields, runbook Open Items row, CAT-B format blocks
🌐 Model-agnostic Every "Claude" reference replaced with agent-neutral phrasing (24 sites)
📊 Coherence & counts Persona-count phrasing, QC rework rule, Coverage Ledger vocabulary, Audit Trail canonicalized

New in This Release

  • 🔧 Self-consistency checker — 10-stage automated validation (tools/check_consistency.sh)
  • 🧪 Test fixtures — Flawed app with planted secrets + secret-scan harness
  • 📦 npm package — npx praetor-audit-kit
  • 🤖 Claude Code skill — claude skill install Skill/praetor.skill
  • 📖 Getting Started guide — First-time, step-by-step walkthrough

📦 Installation

# npm (recommended)
npx praetor-audit-kit

# Claude Code
claude skill install Skill/praetor.skill

# Manual — paste prompt into any long-context LLM

📊 By the Numbers

Count
Expert Agent Personas 18
Quality Council Judges 4
Execution Phases 7
Audience Categories 5
Register Types 12
Inter-Agent Protocols 13
Artifact Status Values 7 core + extended
ID Schemes 11

Full Changelog: CHANGELOG.md

One prompt. Eighteen experts. Six disciplines. Full traceability.

Full Changelog: v2.5.1...v2.8.0

Assets 2
Loading