Claude Code training and agent audits, on your repo

Agentic setup audit

€1,500 excl. VAT per day, fixed price, 2 to 4 days

I take your repoThe folder that holds a project’s code and all its change history, managed with git. and look at what actually happens when an agentA tool that reads your code, changes it and runs commands on its own, from a request written in plain English or French. works in it: which CLAUDE.mdThe instruction file that Claude Code reads at startup in a project. The open equivalent is called AGENTS.md. loads, which hookA script that the tool runs automatically before or after an action of the agent, for example to refuse a command or to run the tests. fires, and what a security rule is worth when the agent reaches the same result by a different path than the one it watches. The first move is to remove everything, CLAUDE.md, skillsProcedures written in files, which the agent loads only when the task needs them., hooks, and see where the agent fails on its own before deciding what to put back. That is the principle of hobblingRemoving first the instructions and tools added around a model to see what it can do alone, then putting back only what is still useful.: remove first, modify next, add last, and what protects (read-only access, permissions) stays, only what compensated for the model’s limits goes. Most of the work is async, with 2 or 3 short interviews.

• The CLAUDE.md files, the skills, the hooks, the permissions, and who owns them
• The settings set at team level that do not do what everyone assumes, with nothing to flag the gap
• What gets checked before a mergeBringing a change into the main branch of the code, once it has been reviewed and the tests pass., and reviewA human reading the code before it goes to production. when it comes from an agent, which sometimes gives a verdict on a whole PRPull request: a proposed change to the code, which a teammate reads before it is merged. after checking only part of it
• Cost in tokensThe pieces of text, a few letters each, that a model reads and writes. It is the unit you pay for., where it goes, and the spread between your developers on the same work
• What all of it changes, or does not, in what you ship

At the end you have a written playbook, specific to your repo, with a 90-day plan and a 1-hour walkthrough, built to be run without me.

Workshop in your own repo

€2,500 excl. VAT per day, billed by the day and never per head

1 day on site or remote, on your own code, with your real tickets. No sample project and no sandbox, what we write during the day is committed to your repo that evening. The hour by hour format and the questions I get before a booking are on the Claude Code training page.

• We take 3 or 4 tickets from the current sprint and push them through the agent together
• We write the repo’s CLAUDE.md files during the session, and your developers write them, not me, because a file written by somebody else has nobody to keep it up to date
• We wire up the hooks and skills that are useful at your company and throw out the ones that are not
• We look at what it costs, in tokens and in review time

With 8 developers in the room the day comes to a little over €300 a head.

Office hours

€300 excl. VAT per hour, or €1,000 excl. VAT a month for 4 sessions

1 hour with your leads, screen shared, on whatever is blocking right now: a CLAUDE.md that has doubled in size and nobody rereads, a hook that blocks the whole team, a bill climbing with nobody sure why, a PR written by an agent that nobody quite dares to review.

• Per session when there is a precise question and 1 hour is enough
• On a monthly subscription (retainerA monthly subscription: a number of sessions booked every month for a fixed price.), 4 sessions a month, when there is a piece of work that runs for a while, and a slot held every month costs more than 1 hour picked up at the last minute

The recurring format exists because models change fast. Each wave (Opus 4.5 in November 2025, Opus 5 in July 2026, Opus 5.5 in September 2026) changes what the agent can do on its own, an instruction that helped 6 months ago can hold it back today, and the lag of a team that does not rerun the test grows faster than it used to. It is what I see at my clients.

Building an agent system

€7,500 excl. VAT per week, 2 weeks minimum

For when what you need is not an opinion but shipped code. It is my core trade, ML and then LLMs in production since 2017, and it sells in full weeks rather than in hours taken between meetings.

• An agent wired into your product, an eval harness that tells you whether the answers are any good, a RAGRetrieval-augmented generation: before answering, the model looks up the useful passages in your documents and relies on them. that holds up under load, an inference platformThe service that receives requests from the teams and sends them to the models, handling quotas, errors and costs. that stays up
• I write the code, your developers review it, and all of it lives in your repo from day one
• At the end there is a system that runs, tests, and a handover so the team carries on without me