ai-adoption

A plugin containing tools for examining Claude Code and Cowork conversation history. It includes reports on token use, profiles of recurring AI-assisted work, and searches across saved sessions.

In plain words
What is it for?
Use it to diagnose session and token patterns, build a task profile with charts and recommendations, or search past transcripts by title, folder, date, or text.
Why use it?
It helps reveal where AI usage spends time or tokens, which tasks recur, where work gets stuck, and how to find an earlier conversation.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add plugins/techwolf-ai/ai-first-toolkit/ai-adoption
Claude Code
/plugin marketplace add techwolf-ai/ai-first-toolkit
Clone the repo
git clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkit

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

ai-adoption scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/ai-adoption/.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "name": "ai-adoption",
  "version": "1.1.0",
  "description": "AI Adoption, three skills for working with your Claude history. token-doctor diagnoses where your Claude Code + Cowork spend goes (length distribution, marathon share, cache rebuilds, per-project health), writes a doctor-style terminal report, and optionally fans out parallel Haiku subagents over your top sessions for habit-level recommendations. task-profile mines those same sessions into a structured task profile: what you do with AI, how often, how successfully, where friction lives; it emits a shareable CSV, an interactive HTML explorer with progressive disclosure and a code-vs-cowork token chart, AI-first coaching cards, and up to five task-centric skill proposals. session-search finds a specific past session by title, working directory, time range, or free-text content across every Claude Code and Cowork transcript on disk.",
  "author": {
    "name": "Jeroen Van Hautte",
    "email": "[email protected]"
  },
  "keywords": ["ai-adoption", "token-doctor", "task-profile", "session-search", "sessions", "analytics", "coaching", "cost", "skills"]
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 11 lines scan A b4a201183406

Subscribe to this mod's changes

ai-adoption is a plugin published in the GitHub repository techwolf-ai/ai-first-toolkit (96 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.