Claude Code
4/5 GreatA PM who wants to stop writing tickets for small internal things and just build them — and who can tolerate a terminal.
- Pricing
- No free tier — requires a paid Claude subscription (Pro/Max/Team/Enterprise) or Console API billing. On API billing Anthropic's own cost docs report ~$13 per developer per active day and $150–250 per developer per month across enterprise deployments.
- Last verified
- Jul 28, 2026
What it is
Claude Code is Anthropic’s agentic coding tool: it reads a folder of files, edits them, runs commands, and checks its own work. It runs in a terminal, in VS Code and JetBrains, in a desktop app, and in the browser at claude.ai/code.
The reason it belongs on a PM site has little to do with coding. Three of its features are general-purpose product tooling that happen to ship inside a developer product: CLAUDE.md, a markdown file it reads at the start of every session, so your product context stops being something you re-paste; MCP, which connects it to Jira, Slack, Figma, Google Drive or your database, so it works from your actual systems; and skills, packaged repeatable workflows you can share with a team.
Our verdict
The highest-ceiling tool on this site and the one most likely to change what your job looks like in two years. A PM who can run it can build the internal tool nobody would prioritise, ship a real prototype instead of a Figma of one, and — via MCP — ask questions of Jira and the warehouse in one place. It is also the most honest way to learn what your engineers actually deal with, which quietly improves everything else you do.
Where it falls short: the terminal is a real wall, and the marketing consistently understates it — if you have never used a command line, budget an uncomfortable afternoon, not ten minutes. There is no free tier, so you cannot try it properly without paying. It will confidently do the wrong thing at speed, which is a different failure mode from a tool that just refuses; you need enough judgment to notice, and on a codebase you don’t understand you won’t have it. And it is genuinely dangerous pointed at production systems — the blast radius of an agent with shell access is not theoretical. Keep it on scratch repos and internal tools until you know what you’re doing.
Get value in 10 minutes
Do not start on your company’s main codebase. Start with an empty folder and something small you own.
- Install it:
curl -fsSL https://claude.ai/install.sh | bashon macOS, Linux or WSL. Thenmkdir pm-scratch && cd pm-scratch && claude. - Write a
CLAUDE.mdin that folder with five lines about your product: what it does, who uses it, the two constraints that always apply, the words your company uses for things. Every session now starts from that instead of from nothing. - Ask for something real and small: “Read this CSV of support tickets and build me a single-page HTML dashboard showing volume by category over time. No build step — one file I can open in a browser.”
- Open the file. Ask for the two changes you want. That loop — describe, look, correct — is the whole skill, and it transfers to everything else the tool does.
Pairs with
- ChatGPT ChatGPT in the browser is where you think through the problem; ChatGPT Code is where the result becomes files that persist, get committed, and can be re-run.
- promptfoo ChatGPT Code writes and maintains the promptfoo config for you — it removes the YAML barrier that stops most PMs owning an eval set.
- Replit Agent Replit hosts and runs the thing for people who won't install anything; ChatGPT Code is the better editor once the prototype needs real changes rather than regeneration.
Used in playbooks
“Every AI session starts with the same 400 words about what your product is, who uses it, and what you already decided not to build — and the output is still generic.”
Build the context pack so you stop re-explaining your product every session
“The thing your support team asks for every month is two days of engineering work, and it has been sitting at position fourteen on the roadmap for a year.”
Ship the small internal tool yourself instead of filing a ticket nobody picks up
Go deeper
- Primary sourceClaude Code overview (official docs)What it is, every surface it runs on (terminal, VS Code, JetBrains, desktop, web), and the current install commands. Start here, not with a video.
- Primary sourceHow Claude remembers your project — CLAUDE.md and auto memoryThe most PM-relevant page in the docs. CLAUDE.md is a plain markdown file that loads into every session — this is where your product context lives. Note the 200-line guidance.
- DocsConnect Claude Code to your tools with MCPHow to wire it to Jira, Figma, Slack, Postgres and the rest, so it works from your real systems instead of what you paste in.
- Primary sourceManage costs effectivelyRead before you pitch this to finance. Has the real per-developer numbers and the specific habits that drive spend up (long sessions, Opus left as default).