Agent rules and reusable skills from my daily setup
This repository also configures its own agents. See what agentsmith tells them →
Skill Claude CodeCodex
Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them. Triggers when the user asks to check drift, audit the spec, verify invariants, or ask whether code still matches the spec.…
Skill Claude CodeCodex
Control Collaborator's spatial canvas from the terminal using the collab-canvas CLI. Use when placing, moving, or resizing tiles (terminals, files, images, graphs) on the pannable canvas surface.
Skill Codex
Search and analyze 5,400+ Solana hackathon projects using Colosseum Copilot. Find similar projects, discover winner patterns, identify gaps, and explore ML clusters. Use when a user says "colosseum copilot", "hackathon projects", "winner patterns", "gap analysis hackathon", "similar Solana projects", or "colosseum…
Skill Codex
Map the competitive landscape for a crypto product idea. Use when a user says "who are my competitors", "map the competitive landscape", "what exists in this space", "show me similar projects", or "competitive analysis". Leverages solana-new's catalogs of 106 repos, 77 skills, and 36 MCPs.
Skill Codex
Create a structured pitch deck for a crypto project. Use when a user says "create a pitch deck", "help me pitch", "I need slides", "prepare for demo day", "investor presentation", or "grant application". Reads idea-context.md and build-context.md from prior phases if available.
Skill Claude CodeCodex
Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and…
Skill Codex
Help a developer debug a failing Solana program or transaction. Use when a user says "debug my program", "program error", "transaction failed", "stuck", "help me fix", "why is this failing", "error code", or "instruction failed". Reads build-context.md if available.
Skill Codex
Research DeFi protocols and market opportunities using DefiLlama data. Use when a user says "show me TVL data", "which protocols are growing", "DeFi market research", "what should I build in DeFi", "find DeFi opportunities", "analyze protocol TVL", or "which chains are trending". Uses TVL as a trust metric to suggest…
Skill Codex
Guide a Solana project from devnet to mainnet production deployment. Use when a user says "deploy to mainnet", "go to production", "deployment checklist", "prepare for launch", "mainnet deployment", or "ship it". Reads build-context.md from a prior build phase if available.
Skill Claude CodeCodex
Modern Developer Relations strategy for 2025-2026. Use when designing DevRel programs, DX strategy, documentation, SDK onboarding, community programs, hackathons, grants, ambassador programs, technical content, developer education, AI/Web3/platform ecosystem growth, metrics dashboards, or when translating developer…
Skill Claude CodeCodex
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Skill Claude CodeCodex
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
Skill Claude CodeCodex
Use when a request involves Ethereum, the EVM, or blockchain systems. Applies to building, auditing, deploying, or interacting with smart contracts, dApps, wallets, or DeFi protocols. Covers Solidity development, contract addresses, token standards (ERC-20, ERC-721, ERC-4626, etc.), Layer 2 networks (Base, Arbitrum…
Skill Claude CodeCodex
Expert EVM full-stack development for Solidity contracts, Foundry tests, audits, gas optimization, L2 deployments, account abstraction, EIP-7702/4337 flows, viem/wagmi frontends, transaction UX, and production dApps. Use when building, reviewing, debugging, testing, deploying, or securing smart contracts and…
Skill Claude CodeCodex
Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service -- even for well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. Your…
Skill Codex
Interview users sharply to discover, rank, or validate what they should build in crypto. Use when a user asks what to build in crypto, wants startup ideas in a crypto niche such as DeFi or AI x crypto, wants blunt feedback on an existing crypto idea, or wants a concrete artifact comparing the best next ideas. Treat…
Skill Claude CodeCodex
Expert frontend architecture and UI engineering for React, Next.js/App Router, TypeScript, Tailwind, shadcn/ui, accessibility, performance, design systems, Web3 transaction UX, and production-quality interfaces. Use when building components/pages, reviewing frontend code, implementing mockups, improving UX polish…
Skill Claude CodeCodex
Apply high-quality web interface design rules when building, reviewing, or styling frontend code. Use when the user says "build a frontend", "create a component", "style this", "review my UI", "build a landing page", "design this page", "make this look good", "add animation", "build a form", "improve the UI", "polish…
Skill Claude CodeCodex
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Skill Claude CodeCodex
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Skill Claude Code
Compact the current conversation into a handoff document for another agent to pick up.
Skill Claude CodeCodex
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
Skill Claude CodeCodex
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: