Arnesto — the agent harness that got out of hand
This repository also configures its own agents. See what arnesto tells them →
Skill Claude CodeCodex
Use this to fix and re-install agent skills that have failed installation. This skill provides the necessary context and permissions to surgically update the manifest.json after a fix has been applied.
Skill Claude Code
Small Safe Steps (S3): breaks work into 1-3h increments with zero downtime. Use when asking "how do I implement/migrate/refactor", "what steps to do X", "plan safe migration", or handling risky DB/API changes. Applies expand-contract pattern for migrations, refactorings, schema changes.
Skill Claude CodeCodex
Investigate and fix bugs in a company environment using available tickets, internal documentation, private repositories, ownership data, and production evidence. Use for corporate or internal engineering incidents that span systems such as Jira, Confluence, Slack, Drive, GitHub, or enterprise monorepos; use diagnose…
Skill Claude Code
Create compelling progress updates and release notes. Use when shipping a new feature or need to communicate progress to stakeholders.
Skill Claude CodeCodex
Write or rewrite text in ASD-STE100 Simplified Technical English. ONLY use this skill when the user explicitly invokes it by name — i.e. they type "/ste" or literally write "use the ste skill" / "apply ASD-STE100". Do NOT trigger it on paraphrased intent such as "simplify this", "make it clearer", "write technical…
Skill Claude CodeCodex
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Skill Claude CodeCodex
Use when asked to "strategic narrative", "Andy Raskin", "tell our company story", "write a pitch deck", "explain why customers should care", or "movement narrative". Helps craft compelling narratives that define movements rather than just selling products. The Strategic Narrative framework (created by Andy Raskin)…
Skill Claude CodeCodex
Coaches through Rumelt's Strategy Kernel to build sound strategy. Use when defining strategy, diagnosing strategic challenges, or creating strategic plans.
Skill Claude CodeCodex
Enforce consistent tagging across the Obsidian wiki using a controlled vocabulary. Use this skill when the user says "fix my tags", "normalize tags", "clean up tags", "tag audit", "what tags should I use", "tag taxonomy", or whenever you're creating or updating wiki pages and need to choose the right tags. Also…
Skill Claude CodeCodex
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
Skill Claude CodeCodex
Select and implement the right test double with a default preference for fakes, stubs, and spies over mocks. Use when writing or refactoring tests, especially when users mention test doubles, mocking strategy, interaction assertions, or flaky tests caused by over-mocking.
Skill Claude CodeCodex
Encapsulates infrastructure SDKs behind minimal domain-aligned interfaces. Use when accessing any external infrastructure to keep SDK usage contained, testing simple, and changes easy.
Skill Claude CodeCodex
Applies Kent Beck's Thinkies—pattern-based thinking habits that generate ideas. Use when stuck, exploring alternatives, or reframing decisions.
Skill Claude CodeCodex
Use when asked to "thinking in bets", "make decisions under uncertainty", "think probabilistically", "avoid resulting", "separate decision quality from outcomes", or "reduce bias in decisions". Helps make explicit bets and evaluate decisions on process, not results. The Thinking in Bets framework (from Annie Duke)…
Skill Claude CodeCodex
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
Skill Claude CodeCodex
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
Skill Claude Code
Translates technical text between English and Spanish preserving tone and format. Keeps technical terms in English when common in Spanish dev teams (deploy, pull request, pipeline, staging). Use when translating technical documentation, code comments, or team communication.
Skill Claude CodeCodex
Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
Skill Claude CodeCodex
Use when asked to "run an A/B test", "design an experiment", "check statistical significance", "trust our results", "avoid false positives", or "experiment guardrails". Helps design, run, and interpret controlled experiments correctly. Based on Ronny Kohavi's framework from "Trustworthy Online Controlled Experiments".
Skill Claude Code
Analyze collections of user feedback to identify patterns and themes. Use when you have user feedback from multiple sources that needs synthesis.
Skill Claude CodeCodex
Python package and project management with UV. Use when creating Python scripts, initializing projects, or managing dependencies.
Skill Claude CodeCodex
Use when the user wants agent-friendly vault artifacts or source ingest with text-first tools: Mermaid .mmd diagrams rendered with mmdc, Marp Markdown decks compiled to PDF/PPTX, Obsidian Excalidraw Markdown sketches, notebooklm-py summaries, yt-dlp talk metadata/captions, markitdown document conversion, or Makefile…
Skill Claude CodeCodex
A comprehensive verification system for Claude Code sessions.
Skill Claude CodeCodex
Save the current conversation as a permanent, structured wiki note. Use this skill when the user says "save this conversation", "/wiki-capture", "capture this discussion", "file this conversation", "preserve this discussion", or wants to turn what was just discussed into lasting knowledge. The skill classifies the…
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: