By axakon
Consultancy playbook for AI-assisted development. Automates durable-context setup, AGENTS.md authoring, starter-doc scaffolding, spec-driven workflows, architecture decision records, and context distillation.
Record an architecture decision as a lightweight, immutable ADR in the scope's docs folder. Owns the ADR template, numbering, and write. Invokable directly for a direct-path decision, or by spec-workflow at handoff.
Set up or review the project's AGENTS.md through an interactive interview with the developer
Evaluate recent changes and propose updates to the project's permanent context (AGENTS.md or the scope's docs folder) when something durable was learned
Configure the playbook for this scope — choose where durable project context lives, mark the folder, and persist the choice. Recommended as the first playbook command in a fresh repo, before /playbook:agents-md-setup. Safe to re-run to change the location.
Suggest and scaffold starter docs for a project's durable-context folder, tailored to what the repo actually contains. Recommended once on a project that has code but little or no documentation, after /playbook:init and /playbook:agents-md-setup.
Modifies files
Hook triggers on file write and edit operations
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.
A playbook for AI-first software development. Adopt it in your repository to get a documentation structure, an opinionated plugin, and a set of conventions that keep an AI agent productive across a project's lifetime — without the process tax that usually comes with "AI governance."
Adopting TRACE in a fresh repo takes a few minutes and produces:
docs/ tree organized by what each file is: living description of the codebase (system/), prescriptive rules the system MUST follow (architecture/), and historical decisions and rationale (adr/, reference/, working-notes/).AGENTS.md describing your project's conventions (one source of truth, loaded automatically by Claude Code, Cursor, Codex).playbook Claude Code plugin installed, which automates the parts of the workflow most often skipped: writing the initial context file, scaffolding starter docs, planning substantial work with explicit acceptance criteria, recording decisions as ADRs, and distilling durable knowledge as work happens.The fastest way to adopt TRACE is to point Claude Code at this repository from inside your own project and let it walk you through setup. The next section explains how.
You are an AI coding agent running in a user's project directory. The user wants to adopt TRACE in this project. Follow these steps.
Before doing anything, verify that your working directory is not TRACE itself. If the directory contains deliverable/playbook/ at its root, you are inside TRACE's own source tree — stop and tell the user to cd to their target project first.
~/.trace-cache/. Confirm before cloning.git clone https://github.com/axakon/TRACE.git <chosen-path> (replace axakon/TRACE with the actual repo URL if different).<chosen-path>/deliverable/README.md — that file is the adopter walkthrough. Follow it from the user's project directory (your current working directory).Continue to deliverable/README.md in this clone. Follow the walkthrough there, with the user's project directory as your working directory (not the clone).
docs/ folder structure, install the plugin, hand off to plugin skills. Stop after step 3 — don't invent additional steps.If you're contributing to TRACE — adding to the playbook, editing the plugin, or working through the research substrate — start at AGENTS.md. That file is for agents working on this repo, not for agents adopting TRACE elsewhere.
npx claudepluginhub axakon/trace --plugin playbookComprehensive 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.
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.