By codybrom
Run structured design reviews on code, PRs, or modules to detect complexity, shallow abstractions, design smells, and tactical thinking, and generate independent design alternatives.
Evaluates whether abstractions genuinely provide a fundamentally different way of thinking or are structurally shallow. Use when adjacent layers feel redundant, when decorator/wrapper patterns add boilerplate without depth or when an abstraction feels leaky. Not for measuring a single module's interface-to-implementation ratio (use deep-modules) or checking for information leakage across boundaries (use information-hiding).
Evaluates whether modifications to existing code maintain or degrade design quality. Use when reviewing changes to existing code (diffs, PRs, or recently modified files) to assess whether each change looks designed-in or bolted-on. Not for scanning against a checklist of design smells (use red-flags) or assessing overall design investment (use strategic-mindset).
Reviews comment quality and documentation practices. Use when the user asks to review comments or documentation, when comments just repeat the code, when something is hard to describe in a sentence, or when writing documentation before code to surface design problems. Evaluates the four comment types, comments-first workflow, and comment rot. Not for naming or code obviousness (use naming-obviousness).
Diagnoses what makes code complex and why, using the three-symptom two-root-cause framework. Use when code feels harder to work with than it should but the specific problem is unclear. This skill identifies WHETHER complexity exists and WHERE it comes from. Not for scanning a checklist of known design smells (use red-flags) or evaluating a specific module's depth (use deep-modules).
Measures module depth, whether the interface is simple relative to the implementation behind it. Use when a module's interface has too many parameters or methods, when there are too many small classes each doing too little or when methods just forward calls to other methods. Not for evaluating whether adjacent layers provide different abstractions (use abstraction-quality) or deciding whether to merge/split specific modules (use module-boundaries).
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI agents can write working code, but they don't stop to consider effective design unless asked. Clairvoyance is a set of skills inspired by John Ousterhout's A Philosophy of Software Design. Each skill gives your agent extrasensory perspective around software design, with concrete tests to see ahead of obstacles during implementation and review.
Skills activate automatically and push your agent to ask questions like:
You can also invoke them directly. Use /red-flags to trigger a design smell scan, /deep-modules to check interface depth and /design-it-twice to compare alternatives before committing.
Give your agent Clairvoyance: Claude Code, skills.sh, Codex, Cursor, OpenCode, Gemini CLI, Antigravity, Factory Droid, GitHub Copilot CLI, Kimi Code, Pi.
Note: Installation differs by platform. If you use more than one, install Clairvoyance separately for each.
/plugin marketplace add codybrom/clairvoyance
/plugin install clairvoyance@clairvoyance-plugins
npx skills add codybrom/clairvoyance --skill '*'
Requires Codex CLI ≥ 0.142.0 (codex --version). The Codex App and CLI share the same config, so this also makes Clairvoyance visible in the App's Plugins panel.
codex plugin marketplace add codybrom/clairvoyance
codex plugin add clairvoyance@clairvoyance
Older Codex versions only get the 16 skills, via a manual symlink — see .codex/INSTALL.md for that fallback and full troubleshooting.
Cursor doesn't yet have a one-line "install from a GitHub URL" flow for unlisted plugins, so clone (or symlink) the repo into Cursor's local plugins folder and restart:
git clone https://github.com/codybrom/clairvoyance.git ~/.cursor/plugins/local/clairvoyance
Then check the Customize panel in the sidebar to confirm Clairvoyance and its 16 skills are listed.
Add Clairvoyance to the plugin array in your opencode.json (global or project-level):
{
"plugin": ["clairvoyance@git+https://github.com/codybrom/clairvoyance.git"]
}
Restart OpenCode — no symlinks or manual skill paths needed. See .opencode/INSTALL.md for version pinning, troubleshooting, and migrating off the old symlink-based install.
Requires Gemini CLI ≥ 0.26.0 and an account Gemini CLI currently serves (Code Assist Standard/Enterprise, Google Cloud, or a paid API key — see .gemini/INSTALL.md for details).
gemini extensions install https://github.com/codybrom/clairvoyance.git
Restart Gemini CLI to load the extension.
agy plugin install https://github.com/codybrom/clairvoyance
Droid translates Claude Code plugin format automatically — no Clairvoyance-specific files needed.
droid plugin marketplace add https://github.com/codybrom/clairvoyance
droid plugin install clairvoyance@clairvoyance-plugins
copilot plugin marketplace add codybrom/clairvoyance
copilot plugin install clairvoyance@clairvoyance-plugins
In Kimi Code's plugin manager (/plugins), choose Custom, or run directly:
/plugins install https://github.com/codybrom/clairvoyance
Kimi Code will show a third-party trust prompt since this isn't an officially curated source — confirm to proceed.
pi install git:github.com/codybrom/clairvoyance
Pi auto-discovers the skills/ directory with no extra config.
Machine-readable skill index for LLM agents:
npx claudepluginhub codybrom/clairvoyance --plugin clairvoyanceIterative AI development loop for Claude Code — spins up isolated agents in a loop, each building on the journal notes of the previous one.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.