novahiz 0.1.1 → 0.2.2

package/skills/adversarial-reviewer/SKILL.md

@@ -1,247 +0,0 @@
----
-name: "adversarial-reviewer"
-description: "Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer."
-tier: "STANDARD"
-category: "Engineering / Code Quality"
-dependencies: "None (prompt-only, no external tools required)"
-author: "ekreloff"
-version: "2.9.0"
-license: "MIT"
----
-
-# Adversarial Code Reviewer
-
-## Description
-
-Adversarial code review skill that forces genuine perspective shifts through three hostile reviewer personas (Saboteur, New Hire, Security Auditor). Each persona MUST find at least one issue — no "LGTM" escapes. Findings are severity-classified and cross-promoted when caught by multiple personas.
-
-## Features
-
-- **Three adversarial personas** — Saboteur (production breaks), New Hire (maintainability), Security Auditor (OWASP-informed)
-- **Mandatory findings** — Each persona must surface at least one issue, eliminating rubber-stamp reviews
-- **Severity promotion** — Issues caught by 2+ personas are promoted one severity level
-- **Self-review trap breaker** — Concrete techniques to overcome shared mental model blind spots
-- **Structured verdicts** — BLOCK / CONCERNS / CLEAN with clear merge guidance
-
-## Usage
-
-```
-/adversarial-review              # Review staged/unstaged changes
-/adversarial-review --diff HEAD~3  # Review last 3 commits
-/adversarial-review --file src/auth.ts  # Review a specific file
-```
-
-## Examples
-
-### Example: Reviewing a PR Before Merge
-
-```
-/adversarial-review --diff main...HEAD
-```
-
-Produces a structured report with findings from all three personas, deduplicated and severity-ranked, ending with a BLOCK/CONCERNS/CLEAN verdict.
-
-## Problem This Solves
-
-When Claude reviews code it wrote (or code it just read), it shares the same mental model, assumptions, and blind spots as the author. This produces "Looks good to me" reviews on code that a fresh human reviewer would flag immediately. Users report this as one of the top frustrations with AI-assisted development.
-
-This skill forces a genuine perspective shift by requiring you to adopt adversarial personas — each with different priorities, different fears, and different definitions of "bad code."
-
-## Table of Contents
-
-1. [Quick Start](#quick-start)
-2. [Review Workflow](#review-workflow)
-3. [The Three Personas](#the-three-personas)
-4. [Severity Classification](#severity-classification)
-5. [Output Format](#output-format)
-6. [Anti-Patterns](#anti-patterns)
-7. [When to Use This](#when-to-use-this)
-
-## Quick Start
-
-```
-/adversarial-review              # Review staged/unstaged changes
-/adversarial-review --diff HEAD~3  # Review last 3 commits
-/adversarial-review --file src/auth.ts  # Review a specific file
-```
-
-## Review Workflow
-
-### Step 1: Gather the Changes
-
-Determine what to review based on invocation:
-
-- **No arguments:** Run `git diff` (unstaged) + `git diff --cached` (staged). If both empty, run `git diff HEAD~1` (last commit).
-- **`--diff <ref>`:** Run `git diff <ref>`.
-- **`--file <path>`:** Read the entire file. Focus review on the full file rather than just changes.
-
-If no changes are found, stop and report: "Nothing to review."
-
-### Step 2: Read the Full Context
-
-For every file in the diff:
-1. Read the **full file** (not just the changed lines) — bugs hide in how new code interacts with existing code.
-2. Identify the **purpose** of the change: bug fix, new feature, refactor, config change, test.
-3. Note any **project conventions** from CLAUDE.md, .editorconfig, linting configs, or existing patterns.
-
-### Step 3: Run All Three Personas
-
-Execute each persona sequentially. Each persona MUST produce at least one finding. If a persona finds nothing wrong, it has not looked hard enough — go back and look again.
-
-**IMPORTANT:** Do not soften findings. Do not hedge. Do not say "this might be fine but..." — either it's a problem or it isn't. Be direct.
-
-### Step 4: Deduplicate and Synthesize
-
-After all three personas have reported:
-1. Merge duplicate findings (same issue caught by multiple personas).
-2. Promote findings caught by 2+ personas to the next severity level.
-3. Produce the final structured output.
-
-## The Three Personas
-
-### Persona 1: The Saboteur
-
-**Mindset:** "I am trying to break this code in production."
-
-**Priorities:**
-- Input that was never validated
-- State that can become inconsistent
-- Concurrent access without synchronization
-- Error paths that swallow exceptions or return misleading results
-- Assumptions about data format, size, or availability that could be violated
-- Off-by-one errors, integer overflow, null/undefined dereferences
-- Resource leaks (file handles, connections, subscriptions, listeners)
-
-**Review Process:**
-1. For each function/method changed, ask: "What is the worst input I could send this?"
-2. For each external call, ask: "What if this fails, times out, or returns garbage?"
-3. For each state mutation, ask: "What if this runs twice? Concurrently? Never?"
-4. For each conditional, ask: "What if neither branch is correct?"
-
-**You MUST find at least one issue. If the code is genuinely bulletproof, note the most fragile assumption it relies on.**
-
----
-
-### Persona 2: The New Hire
-
-**Mindset:** "I just joined this team. I need to understand and modify this code in 6 months with zero context from the original author."
-
-**Priorities:**
-- Names that don't communicate intent (what does `data` mean? what does `process()` do?)
-- Logic that requires reading 3+ other files to understand
-- Magic numbers, magic strings, unexplained constants
-- Functions doing more than one thing (the name says X but it also does Y and Z)
-- Missing type information that forces the reader to trace through call chains
-- Inconsistency with surrounding code style or project conventions
-- Tests that test implementation details instead of behavior
-- Comments that describe *what* (redundant) instead of *why* (useful)
-
-**Review Process:**
-1. Read each changed function as if you've never seen the codebase. Can you understand what it does from the name, parameters, and body alone?
-2. Trace one code path end-to-end. How many files do you need to open?
-3. Check: would a new contributor know where to add a similar feature?
-4. Look for "the author knew something the reader won't" — implicit knowledge baked into the code.
-
-**You MUST find at least one issue. If the code is crystal clear, note the most likely point of confusion for a newcomer.**
-
----
-
-### Persona 3: The Security Auditor
-
-**Mindset:** "This code will be attacked. My job is to find the vulnerability before an attacker does."
-
-**OWASP-Informed Checklist:**
-
-| Category | What to Look For |
-|----------|-----------------|
-| **Injection** | SQL, NoSQL, OS command, LDAP — any place user input reaches a query or command without parameterization |
-| **Broken Auth** | Hardcoded credentials, missing auth checks on new endpoints, session tokens in URLs or logs |
-| **Data Exposure** | Sensitive data in error messages, logs, or API responses; missing encryption at rest or in transit |
-| **Insecure Defaults** | Debug mode left on, permissive CORS, wildcard permissions, default passwords |
-| **Missing Access Control** | IDOR (can user A access user B's data?), missing role checks, privilege escalation paths |
-| **Dependency Risk** | New dependencies with known CVEs, pinned to vulnerable versions, unnecessary transitive dependencies |
-| **Secrets** | API keys, tokens, passwords in code, config, or comments — even "temporary" ones |
-
-**Review Process:**
-1. Identify every trust boundary the code crosses (user input, API calls, database, file system, environment variables).
-2. For each boundary: is input validated? Is output sanitized? Is the principle of least privilege followed?
-3. Check: could an authenticated user escalate privileges through this change?
-4. Check: does this change expose any new attack surface?
-
-**You MUST find at least one issue. If the code has no security surface, note the closest thing to a security-relevant assumption.**
-
-## Severity Classification
-
-| Severity | Definition | Action Required |
-|----------|-----------|-----------------|
-| **CRITICAL** | Will cause data loss, security breach, or production outage. Must fix before merge. | Block merge. |
-| **WARNING** | Likely to cause bugs in edge cases, degrade performance, or confuse future maintainers. Should fix before merge. | Fix or explicitly accept risk with justification. |
-| **NOTE** | Style issue, minor improvement opportunity, or documentation gap. Nice to fix. | Author's discretion. |
-
-**Promotion rule:** A finding flagged by 2+ personas is promoted one level (NOTE becomes WARNING, WARNING becomes CRITICAL).
-
-## Output Format
-
-Structure your review as follows:
-
-```markdown
-## Adversarial Review: [brief description of what was reviewed]
-
-**Scope:** [files reviewed, lines changed, type of change]
-**Verdict:** BLOCK / CONCERNS / CLEAN
-
-### Critical Findings
-[If any — these block the merge]
-
-### Warnings
-[Should-fix items]
-
-### Notes
-[Nice-to-fix items]
-
-### Summary
-[2-3 sentences: what's the overall risk profile? What's the single most important thing to fix?]
-```
-
-**Verdict definitions:**
-- **BLOCK** — 1+ CRITICAL findings. Do not merge until resolved.
-- **CONCERNS** — No criticals but 2+ warnings. Merge at your own risk.
-- **CLEAN** — Only notes. Safe to merge.
-
-## Anti-Patterns
-
-### What This Skill is NOT
-
-| Anti-Pattern | Why It's Wrong |
-|-------------|---------------|
-| "LGTM, no issues found" | If you found nothing, you didn't look hard enough. Every change has at least one risk, assumption, or improvement opportunity. |
-| Cosmetic-only findings | Reporting only whitespace/formatting while missing a null dereference is worse than no review at all. Substance first, style second. |
-| Pulling punches | "This might possibly be a minor concern..." — No. Be direct. "This will throw a NullPointerException when `user` is undefined." |
-| Restating the diff | "This function was added to handle authentication" is not a finding. What's WRONG with how it handles authentication? |
-| Ignoring test gaps | New code without tests is a finding. Always. Tests are not optional. |
-| Reviewing only the changed lines | Bugs live in the interaction between new code and existing code. Read the full file. |
-
-### The Self-Review Trap
-
-You are likely reviewing code you just wrote or just read. Your brain (weights) formed the same mental model that produced this code. You will naturally think it looks correct because it matches your expectations.
-
-**To break this pattern:**
-1. Read the code **bottom-up** (start from the last function, work backward).
-2. For each function, state its contract **before** reading the body. Does the body match?
-3. Assume every variable could be null/undefined until proven otherwise.
-4. Assume every external call will fail.
-5. Ask: "If I deleted this change entirely, what would break?" — if the answer is "nothing," the change might be unnecessary.
-
-## When to Use This
-
-- **Before merging any PR** — especially self-authored PRs with no human reviewer
-- **After a long coding session** — fatigue produces blind spots; this skill compensates
-- **When Claude said "looks good"** — if you got an easy approval, run this for a second opinion
-- **On security-sensitive code** — auth, payments, data access, API endpoints
-- **When something "feels off"** — trust that instinct and run an adversarial review
-
-## Cross-References
-
-- Related: `engineering-team/senior-security` — deep security analysis
-- Related: `engineering-team/code-reviewer` — general code quality review
-- Complementary: `ra-qm-team/` — quality management workflows

package/skills/anti-pattern-detector/SKILL.md

@@ -1,185 +0,0 @@
----
-name: anti-pattern-detector
-description: "Detects and prevents common performance, concurrency, caching, monitoring, infrastructure, and build anti-patterns in code. Use when reviewing code for reliability issues, debugging race conditions or deadlocks, optimizing cache strategies, auditing monitoring coverage, validating infrastructure configs, or checking build/deploy safety. Triggers on: anti-pattern, race condition, deadlock, cache stampede, retry storm, circuit breaker, log flooding, SPOF, config drift, dependency hell, docker bloat, migration safety, fire-and-forget, TOCTOU, ABA problem, thundering herd, cold start."
----
-
-# Anti-Pattern Detector
-
-Detects and prevents common reliability anti-patterns across performance, concurrency, caching, monitoring, infrastructure, and build/deploy. Complements `clean-code` (quality), `security-reviewer` (security), and `devops-engineer` (Docker/K8s) by covering operational reliability gaps.
-
-## When to Use
-
-- Code review for reliability issues (auto-triggers with `code-review-excellence`)
-- Debugging race conditions, deadlocks, or performance regressions
-- Auditing cache strategies and invalidation patterns
-- Reviewing monitoring, logging, and alerting coverage
-- Validating infrastructure configs (Terraform, Docker, K8s manifests)
-- Checking build/deploy safety (dependencies, migrations, rollbacks)
-- Pre-deployment reliability checks
-
-## Do not use when
-
-- Task is purely about code style or formatting (use `clean-code`)
-- Task is purely about security vulnerabilities (use `security-reviewer`)
-- Task is purely about Dockerfile optimization (use `docker-expert`)
-- Task is purely about Kubernetes manifests (use `kubernetes-specialist`)
-
-## Core Workflow
-
-### Phase 1 — Scan
-
-Try tool-based detection first, fall back to manual analysis.
-
-**Automated tools (run if available):**
-```bash
-# Concurrency + performance patterns
-semgrep --config=auto --include-pattern='*.py' .
-semgrep --config=auto --include-pattern='*.js' .
-semgrep --config=auto --include-pattern='*.ts' .
-
-# Python-specific
-bandit -r ./src
-flake8 --select=G,C,N .
-
-# JavaScript/TypeScript
-eslint --plugin=sonarjs .
-npx eslint-plugin-n eslint .
-
-# Secrets in git
-gitleaks detect --source=.
-trufflehog git file://./ --only-verified
-
-# Dependency audit
-npm audit --audit-level=moderate
-pip-audit
-cargo audit
-
-# Docker
-hadolint Dockerfile
-trivy fs .
-```
-
-**Manual analysis:** If tools are unavailable or for patterns tools miss, load the relevant `references/` file and scan using the detection patterns.
-
-### Phase 2 — Classify
-
-For each finding, determine:
-
-| Field | Values |
-|-------|--------|
-| **Category** | `concurrency` · `cache` · `async-network` · `monitoring` · `cloud-infra` · `build-deploy` · `language-specific` |
-| **Severity** | `Critical` · `High` · `Medium` · `Low` · `Info` |
-| **Confidence** | `High` (clear pattern match) · `Medium` (likely but needs context) · `Low` (possible, needs verification) |
-| **Location** | `file:line` reference |
-
-**Severity rules:**
-
-| Severity | Criteria |
-|----------|----------|
-| **Critical** | Data loss, security breach, production outage, deadlocking under load |
-| **High** | Memory leak, performance degradation >10x, missing error handling on critical path |
-| **Medium** | Suboptimal pattern, missing best practice, potential issue under specific conditions |
-| **Low** | Code smell, minor inefficiency, style-adjacent reliability issue |
-| **Info** | Informational, no action required, FYI |
-
-### Phase 3 — Report
-
-Use this output template:
-
-```markdown
-## Anti-Pattern Report
-
-### Executive Summary
-- **Critical:** X | **High:** Y | **Medium:** Z | **Low:** W
-- **Categories affected:** concurrency, cache, ...
-- **Files scanned:** N
-
-### Findings
-
-| # | Severity | Category | File:Line | Pattern | Confidence |
-|---|----------|----------|-----------|---------|------------|
-| 1 | Critical | concurrency | src/api.py:42 | Race condition on shared counter | High |
-| 2 | High | cache | src/cache.py:15 | Missing cache invalidation | Medium |
-
-### Detailed Findings
-
-#### FIND-001: Race condition on shared counter
-- **Severity:** Critical (CVSS-like: availability impact)
-- **File:** `src/api.py:42`
-- **Pattern:** Concurrent increment without atomicity
-- **Impact:** Counter corruption under concurrent requests, incorrect data
-- **Remediation:**
-  - Minimal: Add threading.Lock around increment
-  - Better: Use atomic operations (threading.atomic, AtomicInteger)
-  - Complete: Use lock-free data structure or database atomic counter
-- **References:** CWE-362, CWE-662
-```
-
-### Phase 4 — Remediate
-
-For each finding, provide three levels of fix:
-
-1. **Minimal fix** — Quick win, mergeable immediately, addresses the symptom
-2. **Better fix** — Recommended, covers edge cases, addresses the cause
-3. **Complete fix** — Best practice, production-ready, prevents recurrence
-
-## Reference Guide
-
-Load the relevant reference file based on the finding category:
-
-| Category | Reference | Load When |
-|----------|-----------|-----------|
-| Concurrency | `references/concurrency-patterns.md` | Race conditions, deadlocks, TOCTOU, ABA, thundering herd |
-| Cache | `references/cache-patterns.md` | Cache stampede, avalanche, penetration, cold start, TTL issues |
-| Async/Network | `references/async-network-patterns.md` | Fire-and-forget, retry storms, circuit breaker, event listener leaks |
-| Monitoring | `references/monitoring-patterns.md` | Log flooding, missing structured logging, PII in logs, alert fatigue |
-| Cloud/Infra | `references/cloud-infra-patterns.md` | SPOF, auto-scaling, costs, config drift, secrets in git |
-| Build/Deploy | `references/build-deploy-patterns.md` | Dependency hell, docker bloat, migration safety, unpinned deps |
-| Language-specific | `references/language-specific-patterns.md` | JS/Python/Go/Rust/Java specific pitfalls |
-
-## Novahiz Integration
-
-This skill auto-triggers during `code-review-excellence`. The workflow:
-
-1. `novahiz-gate` checks that `anti-pattern-detector` is loaded
-2. During code review, findings are added to the review output
-3. Critical/High findings are flagged in the Todo as blockers
-4. `novahiz-audit` verifies all Critical findings were addressed
-
-## Tool Availability Matrix
-
-| Tool | What it detects | Install |
-|------|-----------------|---------|
-| `semgrep` | Concurrency, performance, security patterns | `pip install semgrep` |
-| `bandit` | Python security + anti-patterns | `pip install bandit` |
-| `eslint-plugin-sonarjs` | JS/TS code smells + anti-patterns | `npm i -D eslint-plugin-sonarjs` |
-| `gitleaks` | Secrets in git history | `brew install gitleaks` |
-| `hadolint` | Dockerfile best practices | `brew install hadolint` |
-| `trivy` | Container + dependency vulnerabilities | `brew install trivy` |
-| `pip-audit` | Python dependency vulnerabilities | `pip install pip-audit` |
-| `cargo audit` | Rust dependency vulnerabilities | `cargo install cargo-audit` |
-
-When tools are not available, proceed with manual analysis using the reference files.
-
-## Constraints
-
-### MUST DO
-- Run automated tools before manual analysis when available
-- Provide specific file/line locations for every finding
-- Include CWE/OWASP references where applicable
-- Offer three levels of remediation (minimal/better/complete)
-- Classify severity consistently using the criteria above
-- Check for secrets in code (gitleaks or manual scan)
-- Flag Critical findings immediately
-
-### MUST NOT DO
-- Skip manual review when tools report zero findings (tools miss context)
-- Report false positives without noting confidence level
-- Suggest fixes that introduce new anti-patterns
-- Mix security findings with reliability findings (use `security-reviewer` for security)
-- Override existing skills' domain (don't rewrite Dockerfiles — use `docker-expert`)
-
-## Limitations
-- Use this skill only when the task clearly matches the scope described above.
-- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
-- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.