Skip to content

jeremylongshore/tons-of-skills-marketplace / plugins/ai-agency/hyperflow/skills/hyperflow

hyperflow

Flagged

Use when applying Hyperflow's orchestration doctrine in Codex, Antigravity, Grok, or another single-agent surface. Auto-invoke for non-trivial engineering work: build, implement, add, refactor, debug, fix, review, audit, plan, scope, design, brainstorm, ship, or deploy. Trigger with /hyperflow:hyperflow, "use hyperflow", "apply the doctrine", or automatically on any task-shaped message.

FileKindSize
DOCTRINE.mdmarkdown96.9 KB
SKILL.mdskill md9.1 KB
VERSIONother6 B
adaptive-brainstorming.mdmarkdown13.4 KB
artefact-format.mdmarkdown13.7 KB
background-agents.mdmarkdown13.3 KB
brainstorming-advanced.mdmarkdown6.1 KB
consultation.mdmarkdown4.7 KB
design-system.mdmarkdown7.4 KB
doctrine-extensions.mdmarkdown9.2 KB
escalation.mdmarkdown16.8 KB
failure-recovery.mdmarkdown7.6 KB
feature-phases.mdmarkdown7.0 KB
flow-profiles.mdmarkdown20.9 KB
git-workflow.mdmarkdown5.9 KB
latency-patterns.mdmarkdown21.0 KB
memory-system.mdmarkdown15.3 KB
mobile.mdmarkdown4.4 KB
motion.mdmarkdown7.4 KB
output-style.mdmarkdown8.7 KB
personas-A.mdmarkdown36.8 KB
personas-B.mdmarkdown26.0 KB
project-analysis.mdmarkdown8.3 KB
quality-gates.mdmarkdown2.0 KB
review-levels.mdmarkdown4.4 KB
reviewer-prompt-batched.mdmarkdown8.6 KB
reviewer-prompt.mdmarkdown4.4 KB
security.mdmarkdown4.6 KB
session-handoff.mdmarkdown7.4 KB
session-memory.mdmarkdown1.3 KB
task-templates.mdmarkdown2.8 KB
task-tracking.mdmarkdown6.7 KB
task-triage.mdmarkdown17.3 KB
web-research.mdmarkdown4.5 KB
worker-prompt-lean.mdmarkdown5.9 KB
worker-prompt.mdmarkdown17.8 KB

review-levels.md

View on GitHub
# Multi-Level Review System

## Overview

After every worker completes, a Reviewer runs a multi-level review. The number of levels scales with task complexity — the orchestrator classifies complexity first, then dispatches a single Reviewer covering all applicable levels in one pass.

---

## The 5 Levels

| Level | Name | What to check |
|-------|------|---------------|
| 1 | Requirements | Built what was asked? All sub-tasks done? Nothing missing or extra? Matches original spec? |
| 2 | Code Quality | Follows project conventions? Clean patterns? No duplication? Proper naming? Types correct? No `any`? Early returns? SRP? |
| 3 | Integration | Works with existing code? No broken imports? Existing tests still pass? Shared state intact? API contracts preserved? |
| 4 | Performance & Security | No N+1 queries? No unnecessary re-renders? Memoization where needed? No exposed secrets? Input validation at boundaries? No unsafe operations? |
| 5 | UX & Accessibility | Keyboard navigation works? Aria labels present? Responsive layout? Loading/error/empty states handled? RTL support? |

---

## Complexity Classification

**Simple** → levels 1–2 only
- Single file change, rename/move, config change, one-line fix, docs update

**Medium** → levels 1–3
- 2–3 files modified, modifies existing functionality, touches shared code (utils, hooks, services), extends existing components

**Complex** → levels 1–5
- 4+ files created/modified, new feature from scratch, multi-component work, UI with user interactions, database schema changes, API endpoint changes

The orchestrator classifies before dispatching. Classification criteria:
- Number of files in scope
- New functionality vs modifying existing
- UI/UX involved → triggers Level 5
- Data persistence or external APIs involved → triggers Level 4

---

## Review Output Format

```
── Review ──────────────────────────────
L1 Requirements    pass     — [one-line summary]
L2 Code Quality    pass     — [one-line summary]
L3 Integration     pass     — [one-line summary]
L4 Performance     fail     — [specific issue found]
L5 UX/A11y         skipped  — not applicable
────────────────────────────────────────
VERDICT: APPROVED | NEEDS_FIX | SECURITY_VIOLATION
[If NEEDS_FIX: specific issues per level, each on its own line]
[Notes for future tasks if any]
```

Status words: `pass` (level passed) · `fail` (blocks approval) · `skipped` (not applicable). Plain words only — no `✓` / `✗` / `⊘`.

---

## Failure Handling

- Any level fails → `NEEDS_FIX` with specific issues listed per level
- Level 4 security sub-check fails → `SECURITY_VIOLATION` (halts pipeline, surfaces to user immediately)
- Worker receives fix instructions referencing the specific level that failed
- After fix, re-review only the failed levels — not all 5 again
- Max 3 fix attempts per level before escalating to user

---

## Level-Specific Checklists

**L1 — Requirements**
- [ ] All items from the task spec are implemented
- [ ] Nothing extra added beyond the spec
- [ ] Edge cases mentioned in the spec are handled
- [ ] Output makes sense for the original user request

**L2 — Code Quality**
- [ ] Follows naming conventions from project analysis
- [ ] No TypeScript `any` types
- [ ] No unnecessary comments or dead code
- [ ] Functions are focused (SRP)
- [ ] Uses existing utils/hooks instead of reinventing
- [ ] Proper error handling patterns

**L3 — Integration**
- [ ] Imports resolve correctly
- [ ] No circular dependencies introduced
- [ ] Shared state/context not broken
- [ ] API contracts match (types align between caller and callee)
- [ ] Existing tests would still pass

**L4 — Performance & Security**
- [ ] No N+1 database queries
- [ ] Expensive computations memoized
- [ ] No unnecessary re-renders (React.memo, useMemo, useCallback where needed)
- [ ] No hardcoded secrets or API keys
- [ ] Input validation at system boundaries
- [ ] No unsafe innerHTML or SQL injection vectors

**L5 — UX & Accessibility**
- [ ] Interactive elements have aria-labels
- [ ] Keyboard navigation works (tab order, enter/escape handlers)
- [ ] Loading states shown during async operations
- [ ] Error states handled gracefully
- [ ] Empty states have useful messaging
- [ ] Responsive — works on mobile viewport
- [ ] RTL layout considered (logical properties)
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall