v2.9.2 — Install-Only Documentation

What Changed

Removed all copy/paste instructions across every doc. Praetor is now install-only — either into your agentic LLM (--install) or standalone via npm.

Changes

• README: Removed Expertise column from all 4 agent tier tables
• README: Rewrote Quick Start to install-only (no copy/paste steps)
• All docs: Replaced copy/paste instructions with install instructions
• VERSION.md, CHEATSHEET, GLOSSARY, RUN_MODES, RESUMABLE_STATE: Updated to remove paste/copy references
• wiki/Home.md, wiki/Quick-Start-Guide.md: Updated for install-only flow
• Version bump 2.9.1 → 2.9.2

Install

npx praetor-audit-kit --install

Full Changelog: v2.9.1...v2.9.2

v2.9.1 — Branding & Assets

v2.9.1 — Branding & Assets

Packaging

• Added assets/ directory to npm package (logo suite + social preview + favicon)
• README badges: fixed stale label, added 13 Agentic Tools and 4-Judge Quality Council badges
• All 6 branding assets attached to release

Wiki

• Home page: logo, slogan, badge row, center-aligned branding
• Quick Start: updated to 13-tool support, --drill command, interactive TUI

Assets included

• logo.svg, logo-horizontal.svg, logo-stacked.svg
• favicon.svg
• social-preview.svg, social-preview.png

Full Changelog: v2.9.0...v2.9.1

v2.9.0 — Interactive TUI Rewrite, 13-Tool Support, Docker Fix

v2.9.0 — Interactive TUI Rewrite

Major Features

• 13 agentic tool support: Expanded from 3 to 13 tools — Claude Code, OpenCode, Cursor, Windsurf, GitHub Copilot, Cline, Amazon Q Developer, Gemini CLI, Aider, Continue.dev, Codex CLI, Roo Code, Sourcegraph Cody
• Interactive TUI: Full arrow-key menu with Install, Pre-flight Check, Scope Selector, Uninstall, Update, Help, Exit
• Sub-scope detail: Drill into any of 52 sub-scopes to see agents (with descriptions), areas covered, AI agent compatibility, LLM disclaimer, and 5-step install guide
• Self-update with progress: 4-step animated progress (local version → npm registry → semver comparison → file verification) with honest output
• Semver comparison: Properly compares local vs npm version — no false downgrades when local is ahead
• LLM disclaimer: Banner clearly states Praetor does NOT provide any LLM API key, subscription, or model access
• AI tool installation disclaimer: Pre-flight check explicitly states Praetor does NOT install AI agentic tools — only installs INTO tools already present
• Docker/PTY fix: Resolved phantom \backslash-r\n key issue causing blank screens in Docker/non-TTY environments

Audit Fixes (2 rounds)

• P0: Fake success on npm install failure — now checks realInstall status
• P0: Version downgrade bug — was using === instead of semver comparison
• P1: Windows safeWhich compatibility (uses where on win32)
• P1: Node.js version check aligned with package.json (>=18)
• P1: runActionThenReturn uses finally for proper cleanup
• P1: installSkill blank screen fix

Stats

• 15 files changed, +1379/-87 lines
• 148 files in npm package
• 230 files in release zip (546KB)
• All 52 tests passing (CLI flags, PTY screens, Docker, edge cases)

Full Changelog: v2.8.6...v2.9.0

v2.8.6 — Doc Sweep + All 10 Production Hardening Fixes

v2.8.6

All 10 production hardening fixes + full doc/wiki/changelog sweep.

CLI Quick Reference

npx praetor-audit-kit                     # banner + quick start
npx praetor-audit-kit --install           # install to Claude Code, OpenCode, Cursor
npx praetor-audit-kit --scope biz         # show Business scope
npx praetor-audit-kit --scope 2-4         # show range of scopes
npx praetor-audit-kit --check             # pre-flight + version check
npx praetor-audit-kit --update            # self-update from npm
npx praetor-audit-kit --uninstall         # remove from all tools

Full Changelog: v2.8.5...v2.8.6

v2.8.5 — Production Hardening + Interactive Scope Selector

What's New in v2.8.5

P0 — Breakage Fixes

• scopes.json manifest: All 52 sub-scopes in a single source of truth
• Agent-safe SKILL.md: Plain-text scope list — no TUI dependency for AI agents
• --scope CLI flag: npx praetor-audit-kit --scope biz for non-interactive selection

P1 — Experience Gaps

• Sub-scope drill-down: Press d in TUI or --drill eng 3 for JSON output
• --uninstall flag: Removes Praetor from all installed agentic tools
• Terminal height detection: Detail pane auto-paginates on small terminals
• Explicit agent mapping: Full scope→agent→category table in SKILL.md

P2 — Scale

• Version check + --update: --check queries npm, --update self-updates
• --no-tui flag: Numbered-list-only mode for Windows/CI
• Scope aliases: --scope security, --scope biz, --scope eng everywhere

Interactive TUI Scope Selector

• 8 main scopes, 52 sub-scopes
• Arrow key navigation with live detail pane
• Number keys (1-8) for instant selection
• Space for multi-select, d for drill-down

CLI Commands

npx praetor-audit-kit --install            # install to Claude Code, OpenCode, Cursor
npx praetor-audit-kit --scope biz          # show Business scope
npx praetor-audit-kit --scope 2-4          # show range
npx praetor-audit-kit --check              # pre-flight + version check
npx praetor-audit-kit --update             # self-update from npm
npx praetor-audit-kit --uninstall          # remove from all tools

Full Changelog: v2.8.4...v2.8.5

v2.8.4 — Packaging & Install Fix

Fixes

• claude skill install replaced with npx praetor-audit-kit --install — the old command did not exist in Claude Code CLI and produced garbage for every user who tried it. The new --install flag copies the full skill tree to ~/.claude/skills/praetor/.
• Removed stale Skill/praetor.skill ZIP from repo and tarball
• Fixed --prompt separator detection (matched inline backtick instead of actual separator)
• Fixed -l short flag (--l double-dash → -l single-dash)
• Added references/ to npm files[] (was referenced but never shipped)
• Fixed banner box alignment (all lines 66 chars)
• Reconciled package name: @harery/praetor-audit-kit → praetor-audit-kit (unscoped)
• Updated all version refs across 12 files (README, CHANGELOG, SKILL.md, VERSION.md, wiki, cheatsheets, protocols)

Install

# Any LLM — paste the prompt
npx praetor-audit-kit --prompt

# Claude Code — install as skill
npx praetor-audit-kit --install

# See all options
npx praetor-audit-kit --help

v2.8.2 — Dual-Audit Consolidation: Handoff Graph Made Canonical + Bidirectionality Resolved

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 is New in v2.8.2

Dual-Audit Consolidation

Two independent BALA7-30 audits of v2.8.1 — "opencode" (38 findings) and "Ro2a" (40 new findings). Every finding adjudicated against source before fixing: ~70 distinct valid findings fixed, 2 false positives confirmed. Both harnesses green.

Headline Changes

Theme	What Changed
🔗 Canonical handoff registry	HANDOFF_PROTOCOL now carries the complete directed-edge graph (~55 edges). Broadcast semantics, circular-pair initiation order, and sink-agent inbound pointers all explicit.
🔄 A00 ↔ A02 protocol coherence	Orchestrator refusal condition exempts A02 uncorrectable distribution. Coverage Ledger write-misattribution fixed.
🎯 Precision & determinism	Priority bands stated as independent windows. BLOCKED replaced with specific BLOCKED_BY_*. Snapshot gains AGENTS_NOT_ACTIVATED. QC failed reasons enumerated as closed set.
📊 Risk-register consolidation	PHASE_6 §13: master view absorbs B.5 + E.4, dedups via RELATED_TO.
📖 Glossary + model tiers	Added HANDOFF, MRR, Sev1/Sev2, SNAPSHOT_TOKEN, SNAPSHOT_DRIFT. Three-tier model-capacity guidance.
📝 Templates & mandates	SLA bound to SLO placeholder. TC-ID label corrected. Burn-rate thresholds marked defaults. License "All rights reserved" removed.
🧪 Harness hardening	Checker scans tests/ + tools/. New stage 11 for CI-pipeline copy parity. Fixture gains FLAW-11/12/13 (AWS key, postgres-creds URL, RSA key).

Also Includes (v2.8.0 + v2.8.1)

• Tri-Audit Consolidation: ~75 findings from three independent audits
• PRV↔E.3 column parity restored (10 columns, 1:1 mapping)
• Self-consistency checker (11 stages)
• Test fixtures with secret-scan harness
• npm package: npx praetor-audit-kit
• Claude Code skill: claude skill install Skill/praetor.skill

---

📦 Installation

# npm (recommended)
npx praetor-audit-kit

# Claude Code
claude skill install Skill/praetor.skill

# Manual — download the zip below, 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: v2.8.0...v2.8.2

v2.8.0 — Tri-Audit Consolidation

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

v2.5 — Autonomous Production Readiness & Audit System

What is Praetor?

Praetor 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 in v2.5

• 🐝 18 Expert Agents — SRE, OWASP Security, WCAG Accessibility, Chaos Engineering, SOC2/GDPR/HIPAA Compliance, and more
• ⚖️ 4-Judge Quality Council — Independent review for Coverage, Citations, Clarity, and Skip-Validity
• 🔄 7-Phase Pipeline — Discovery → MUST CONFIRM → Swarm → QC → Release Gate
• 📦 5 Audience Streams — Engineering, Business, Operations, Support, Compliance
• 🔧 Tooling-Adaptive Output — Auto-detects Datadog, Prometheus, Sentry, etc.
• 🔑 Secret Hygiene — Built-in secret-key scanning with runnable CI stage
• ⏸️ Resumable Sessions — Halt and resume across sessions
• 🚀 Zero Installation — Runs inside any long-context LLM

Downloads

Asset	Description
praetor-prompt-kit-v2.5.zip	Complete prompt kit — copy MASTER_PROMPT.md into your LLM and run
praetor.skill	Claude Code skill package — install directly into Claude Code

Quick Start

1. Download praetor-prompt-kit-v2.5.zip and extract
2. Open prompt/00-orchestrator/MASTER_PROMPT.md and copy from the ═══ line
3. Paste into Claude, GPT-5, or any long-context LLM
4. Append: Source Codebase: https://github.com/your-org/your-repo
5. Reply continue when prompted — Praetor handles the rest

Claude Code Installation

claude skill install praetor.skill

Then run: audit my codebase for production readiness

---

Full changelog: CHANGELOG.md