ladder-adoption

v0.3.0-alpha.2

Find your rung on the Steps of AI Adoption and the next one up. Blank-sheet discovery of this machine and repo, scored against Boris Cherny's adoption ladder, plus a scope interview and phased plan for unattended agents, and an incident-response loop that earns the next rung.

Claude Code3 Skills

By Kamil KuklewskiLicense: MIT0 GitHub starsUpdated 3 days ago

Directory evidence

Runtimes: Claude Code
Parsed components: 3 skill or MCP entries
Source updated: Sep 20, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install ladder-adoption for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install ladder-adoption@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/kkuklewski/ladder-adoption

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

ladder-adoption/

├── .claude-plugin/plugin.json
├── skills/autonomy/SKILL.md
├── skills/incident-response/SKILL.md
└── skills/ladder/SKILL.md

Included Skills3

autonomyskills/autonomy/SKILL.md

2/3 After /ladder: turn a ladder score into an ordered plan for unattended agents on this specific project. `interview` asks the ten things no probe can find — what agents should do overnight, what they must never touch, what a push to the default branch does, which tiers, where tasks live, who merges, the nightly budget, where failures go — and writes .ladder/scope.md. `plan` reads the ladder profile plus that scope and writes .ladder/plan.md: phases in a fixed order, each mapped to the rubric ids it closes, each with an exit proof that can come back negative. Use when asked "how do we get agents running here", "what's the plan to reach step 2/3", "make this repo safe for overnight agents", or after /ladder names a gate. Proposes only; never edits settings, CI, workflows or code.

incident-responseskills/incident-response/SKILL.md

3/3 After /ladder and /autonomy: handle one production incident end-to-end without deploying: read the incident, retrieve project context (repo, CLAUDE.md, docs/knowledge base, state store), diagnose the root cause with a confidence level, optionally prepare a fix in an isolated worktree, run the project's verification contract, and return a fixed-shape report for a human. Two modes: `--init` runs the ladder discovery once and writes `.ladder/incident-profile.md` (the project-specific contract); every later run reads that profile. Use when an incident id / error payload is given, when a trigger (webhook, routine, headless `claude -p`) starts a session with one, or when the user says "init incident response for this repo". This is the plugin's concrete way to earn gate 2→3 groups C and D on the ladder.

ladderskills/ladder/SKILL.md

1/3 Start here: find which rung of the Steps of AI Adoption (Cherny, 2026) this machine and repo stand on, and what the next rung costs. Blank-sheet discovery: runs a read-only probe of the machine (Claude Code version, global settings, skills, MCP servers, plugins, CLIs) and the repo (CLAUDE.md, .claude/, verification scripts, CI, deploy files), scores it against the "how to get from step N to N+1" gates and the guardrails axis, writes .ladder/profile.md, and proposes the single smallest next action. Use when asked "where are we on AI adoption", "what step are we at", "what's blocking step 2/3", "assess this repo for agent readiness", or to refresh the profile. Never applies changes itself.

Plugin manifests1

.claude-plugin/plugin.json

{
  "name": "ladder-adoption",
  "description": "Find your rung on the Steps of AI Adoption and the next one up. Blank-sheet discovery of this machine and repo, scored against Boris Cherny's adoption ladder, plus a scope interview and phased plan for unattended agents, and an incident-response loop that earns the next rung.",
  "version": "0.3.0-alpha.2",
  "author": {
    "name": "Kamil Kuklewski",
    "url": "https://github.com/kkuklewski"
  },
  "homepage": "https://github.com/kkuklewski/ladder-adoption",
  "repository": "https://github.com/kkuklewski/ladder-adoption",
  "license": "MIT",
  "keywords": [
    "claude-code",
    "ai-adoption",
    "maturity",
    "assessment",
    "incident-response",
    "agents",
    "skills"
  ]
}