brPrompts

Deep engineering system

Reuse written checklists for planning features and reviewing code, so AI-assisted work meets the same bar every time.

brPrompts showing its engineering specification templates and code review checklists

Current status

Version-controlled engineering playbooks, review rubrics, and specification templates used across projects.

Overview

Curated collection of engineering playbooks, security review checklists, and specification templates for keeping AI-assisted software development rigorous.

Why it was built

One-off chat prompts quickly get lost and fail to enforce consistent quality, security, and testing standards across projects.

Why it helps

Gives engineering teams repeatable checklists for planning features, stress-testing assumptions, and reviewing code before it ships.

What you can do

Multi-step code quality, accessibility, and security review checklists
Clear specification and task-breakdown templates
Version-controlled in Git so improvements are shared across all projects

brPrompts • Core Technology & Feature Architecture

Schema-Enforced, Git-Versioned Prompt Engineering Registry & Golden Fixtures

Organizes production system prompts across 13 functional taxonomies with strict YAML frontmatter contracts, explicit negative boundaries (do_not_use_when), and input/output regression pairs.

13 Taxonomies

Structured Agent, Code-Review, Debugging & Planning Catalog

Indexes reusable prompt specifications across agent-system, code-review, debugging, architecture, and data-extraction domains.

Negative Boundaries

Explicit when_to_use & do_not_use_when Guardrail Contracts

Requires every prompt spec to declare both positive trigger conditions and explicit anti-use-cases to prevent prompt misapplication.

Semver Tagging

Immutable Git Tag Versioning (prompt/<slug>/vX.Y.Z)

Pins downstream applications to immutable semantic versions so prompt edits never cause silent production regressions.

Golden I/O Fixtures

Paired examples/<slug>/{input,output}.md Evaluation Suite

Validates prompt revisions against paired golden input and expected output fixtures before promoting quality scores.

Before & After Engineering AuditAI, Compilers & DecisionCode Review Rubrics · Spec Templates

brPrompts — Verified Engineering & Visual Transformation

Comparison focus

Before: Unverified baseline workflow & manual steps

One-off chat prompts quickly get lost and fail to enforce consistent quality, security, and testing standards across projects.

// Baseline manual workflow
// Problem: One-off chat prompts quickly get lost and fail to enforce consistent quality, security, and testing standards across projects.

After: brPrompts deterministic pipeline & verified output

Gives engineering teams repeatable checklists for planning features, stress-testing assumptions, and reviewing code before it ships.

// brPrompts verified pipeline
// Outcome: Reuse written checklists for planning features and reviewing code, so AI-assisted work meets the same bar every time.
// Status: Version-controlled engineering playbooks, review rubrics, and specification templates used across projects.

CV & VLM rubric shift: 0.7725 → 0.9395 (+0.167 · Sharpness +48.4% · PSNR 44.09 dB)

Grounding gate: Negation parity & evidence verified

Interactive walkthrough

Step through how brPrompts works without creating an account or installing local dependencies.

Entry & problem context

Maturity: Deep engineering system

One-off chat prompts quickly get lost and fail to enforce consistent quality, security, and testing standards across projects.

Curated collection of engineering playbooks, security review checklists, and specification templates for keeping AI-assisted software development rigorous.

Shared platform architecture sandbox

Test the live cross-language single source of truth shared across TypeScript, Python, and Rust.

Normalize legacy or rolling model slug

Resolved OpenRouter wire slug: ~anthropic/claude-sonnet-latest

Contextual task intent routerPrefer zero-cost floor (`openrouter/free` cap enforced)

Primary wire model: google/gemini-3.1-flash-image (Gemini 3.1 Flash Image)

Capped fallback chain: google/gemini-3.1-flash-image → google/gemini-nano-banana-2.1 → openrouter/free

Pareto composite score: 0.8499 (effective cost $0.00102/1k)

Universal 9-Surface Visual & Image Capability Router (`resolveVisualRoute`)

Routes character turnaround sheets, 3:4 VN busts, 16:9 scenes, top-down battlemaps, 1:1 tokens, typography plates, semiotic brand favicons, WebGPU background removal, and Tier-2 local ComfyUI models.

Prefer OpenRouter image gateway

Primary model: black-forest-labs/flux-2-pro via fal

Aspect ratio: 16:9 · Max ref images: 2 · Fallback: google/gemini-3-pro-image → google/gemini-3.1-flash-image

Cinematic 16:9 scene backdrop and storyboard synthesis (`fableforge`, `containment`, `ngi.video/console`).

Anchor promotion (`score >= 0.95`): Promoted to canonical anchor (overall 0.958)

Speculative YOLO anatomy pass: Standby · Vector guard: 1024d verified

DeepSeek 18:00 UTC window: Off-peak active (50% V3 / 25% R1 cost)

Model-aware prompt compiler & five-axis vision rubric (30 registered models)

Compiled prompt (natural_language):

Noir detective standing under neon rain in a cyberpunk alley, cinematic volumetric lighting Character anchors: trenchcoat; amber cybernetic eye. Composition & pose guidance: 16:9 widescreen; cinematic keyframes.

Gemini Vision five-axis rubric weighted score: 0.9 (Passes quality gate)

Semiotic Brand Identity & Federated SoC Governance

Peircean Brand Mark, Multi-Size Squint Test & 3-Tier SoC Boundary

SoC tier: internal_commercial16px rubric: 96.7% (PASS)

16px · 32px · 48px squint test

Motif: ast_wave_nexus

Iconic sign: Faceted cache-preserving prompt blocks feeding a structured JSON schema lock

Indexical cue: Prefix-cached system prompt compilation and deterministic output repair

Symbolic archetype: Amber prompt engineering specification catalog

SoC Boundary & Epistemic Retrieval Guardrails

Visibility & ceiling: private_commercial (max tier: internal_commercial)

Boundary policy: Internal structured prompt compilation & refine-then-generate library.

4-gram shingle novelty: 100.0% (non-redundant >15%) · Retired symbol trap: Clear (0 retired symbols)

GitHub Profile & Source Activity

Engineering Velocity & Open-Source Hygiene

Synced from @brbrainerd and @vox-foundation via the GitHub GraphQL API (GET /api/github/stats).

GitHub Profile vox-foundation/vox

Annual GitHub activity

13,842+

3,229 public · 10,136 private revisions

Curated portfolio history

19,523+

Revisions across 32 curated projects

Pull requests & reviews

463 PRs

Merged across 70 first-party codebases

brPrompts historyShell

25 revisions

42 tracked source files · Updated 2026-09-22

Language distribution across curated projectsWeighted by revision history & source volume

TypeScript38.9% (12 projects)

Rust36.9% (1 project)

Python11.3% (8 projects)

JavaScript4.7% (2 projects)

Lua4.1% (1 project)

Public open-source codebases on GitHub

vox-foundation/voxRust · 7,200 rev

Single-file full-stack programming language and Rust compiler that generates database schemas, server routes, and typed clients from one declaration.

#programming-language#rust#compiler#full-stack#lsp

brbrainerd/govSimTypeScript · 435 rev

Interactive political economy simulator with ECS civic rights, institutional modeling, policy levers, and multi-regime scenarios.

#simulation#political-economy#typescript#ecs#strategy-game

brbrainerd/neurogeckoHTML · 6 rev

Interactive 3D macaque brain atlas and stereo surgical view planner rendered in browser WebGL.

#neuroscience#webgl#threejs#brain-atlas#3d-visualization

brbrainerd/brFrameTypeScript · 23 rev

Single-binary Rust and React kiosk shell for Raspberry Pi digital photo frames with remote mobile upload.

#rust#raspberry-pi#kiosk#embedded#react

Browse all projects