Arnesto — the agent harness that got out of hand
This repository also configures its own agents. See what arnesto tells them →
Skill Claude CodeCodex
Creates git worktrees for parallel development. Use when creating a git worktree, setting up multiple working directories, or working on features in parallel.
Skill Claude CodeCodex
Use when running git clone, git remote add, git remote set-url, or suggesting GitHub SSH commands to ensure all GitHub access uses the saski SSH host alias.
Skill Claude CodeCodex
Define, compose, and wire Google ADK agents with function tools and multi-agent orchestration. Use when writing agent definitions, adding Python function tools, building pipelines with SequentialAgent/LoopAgent/ParallelAgent, or designing router/delegation patterns. Trigger on: adk agent, LlmAgent, SequentialAgent…
Skill Claude CodeCodex
Bootstrap a Google ADK (Agent Development Kit) project from zero to a running local dev UI. Use when setting up a new ADK agent project, configuring Vertex AI credentials, scaffolding the agent folder, or troubleshooting ADK environment issues. Trigger on: adk setup, adk init, google-adk, vertex ai agent, uv run adk…
Skill Claude CodeCodex
Color-code the Obsidian graph view by rewriting .obsidian/graph.json colorGroups. Use this skill when the user says "color my graph", "color code obsidian", "colorize the graph", "color the graph by tag", "color by category", "highlight visibility in graph", "make the graph colorful", "distinguish tags in graph", or…
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 Code
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 CodeCodex
Use when asked to "growth loops", "build a growth engine", "design a viral loop", "create a content loop", "move beyond paid acquisition", or "why isn't growth compounding". Helps design self-reinforcing growth systems where output becomes input. The Growth Loops framework (from Brian Balfour / Reforge and Elena…
Skill Claude CodeCodex
Applies hexagonal (ports & adapters) architecture. Use when designing application structure, separating domain from infrastructure, creating testable boundaries, or when user mentions ports, adapters, hexagonal, or clean architecture.
Skill Claude CodeCodex
Use when asked to "define our core action", "North Star metric", "accruing benefits", "improve retention mechanics", "hierarchy of engagement", or "Sarah Tavel framework". Helps consumer products identify the actions and benefits that drive long-term retention. The Hierarchy of Engagement framework (created by Sarah…
Skill Claude CodeCodex
Use when asked about "marketplace strategy", "chicken and egg problem", "liquidity", "two-sided market", "tipping a marketplace", "GMV growth", or "Sarah Tavel marketplaces". Helps founders and product leaders build defensible marketplace businesses by sequencing supply and demand. The Hierarchy of Marketplaces…
Skill Claude CodeCodex
Use when asked to "build habit-forming products", "Hooked model", "trigger action reward investment", "create sticky behavior loops", or "design habit loops". Helps design products that form unprompted user habits. The Hooked Model (created by Nir Eyal) explains how products create habits through Trigger, Action…
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.
Skill Claude CodeCodex
Fetch a URL and distill its content into the Obsidian wiki. If invoked from inside a project directory, the page lands directly in that project's folder (creating the project in the vault if needed). Otherwise it goes to misc/ and gains project affinity over time. Use this skill when the user says "/ingest-url ", "add…
Skill Claude CodeCodex
Use when asked to "jobs to be done", "JTBD", "why customers churn", "prep for customer interviews", "hire and fire products", or "find real competitors". Helps discover unmet needs and the context behind purchasing decisions. The Jobs to be Done framework (created by Clayton Christensen and Bob Moesta) explains why…
Skill Claude Code
Launches agent teams with structured roles and task decomposition. Use when asked to create a team, spawn teammates, or coordinate multiple agents in parallel.
Skill Claude CodeCodex
Guide AI adoption decisions in software development using Lean, Extreme Programming, and pragmatic simplicity. Use when evaluating AI tools, agents, workflows, prompts, automations, or rollout guardrails; deciding whether to automate or keep work manual; detecting tool sprawl, prompt graveyards, or low-value AI…
Skill Claude CodeCodex
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this'…
Skill Claude CodeCodex
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources…
Skill Claude Code
Use when the user wants to clean up AI slop, harden a codebase, or run technical due diligence: review code for security flaws and vulnerable or wrongly-licensed dependencies, find and remove dead code, audit dependency health, run and triage linters, type checkers, test suites and formatters, evaluate design…
Skill Claude CodeCodex
Ensures proper Python dependency management, avoiding global pip install and adhering to project-specific tooling. Use this skill if any of the following are true: 1. Attempting to run pip install {packagename}. 2. Python packages or dependencies need to be added or modified. 3. Initiating a new Python project. 4.…
Skill Claude CodeCodex
CRITICAL RULE: You MUST use this skill whenever the task involves any machine learning tasks or data analysis. Use this skill if the user's prompt or requirements mention any of the following: Clustering Classification Regression Time series forecasting Statistical testing Model comparison ML Data analysis…
Skill Claude CodeCodex
Principles for building Unix-composable command-line tools in Go: stdout/stderr discipline, JSON and plain output modes, semantic exit codes, noun-verb commands, structured errors. Use when designing, building, or reviewing CLIs.
Skill Claude CodeCodex
Use when asked about "pricing strategy", "willingness to pay", "value metric", "packaging tiers", "good better best pricing", "subscription vs usage pricing", or "price before product". Helps design products customers will pay for and choose pricing models that capture value. Based on Madhavan Ramanujam's Monetizing…
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: