What is Claude Code?
Claude Code is Anthropic's terminal coding agent. What it does, where it runs, what a plan costs, and why it is not a chat window or an IDE.
#claude-code
Filtering by topic #claude-code · clear
Self-host agent-console for coding agents
Run the agent-console hub on a VPS so a laptop and every agent box report Claude Code and Codex token use to one place, reached over an SSH tunnel.
What Paperclip's budget caps actually stop
Paperclip stops an agent at its monthly cap, but only for spend it can price. What the budget policy enforces, and what a subscription run reports.
OKF: Google's open format for agent memory
What Google's Open Knowledge Format is, how its provenance and stale_after fields handle stale and poisoned agent memory, and which OKF tool to pick.
Impeccable: a design skill for coding agents
Impeccable gives coding agents 24 design commands and a detector that flags AI design habits with no model. Install it pinned, then audit a page and check it.
A free market data MCP server for Claude
Connect Claude to real US market data in five minutes with a no key MCP server: the four read only tools, and what each client needs to talk to it.
DeepSeek Harness vs Claude Code vs Omnigent
DeepSeek Harness, Claude Code and Omnigent compared on architecture, model coupling, licence and maturity, plus what each one takes to run on a VPS.
Claude Code on Microsoft Foundry: server setup
Run Claude Code on Microsoft Foundry from a VPS or CI runner with no browser: API key or service principal auth, model pinning, and the errors the docs list.
Claude Code spend tracking tools compared
Claude Code spend trackers answer different questions. Compare local log parsers against the built-in usage screens and your own OpenTelemetry stack.
Caveman Skill: Make Coding Agents Say Less
Caveman shortens what a coding agent writes, and its proxy shrinks what the agent reads. Install it pinned to a release, then measure your own sessions.
Agent harness token overhead: where it goes
Two harnesses on one model can bill an order of magnitude apart. The mechanics behind the gap, and how to measure your own agent's token spend.
Superpowers for Claude Code: what it changes
Install the Superpowers plugin for Claude Code, learn the brainstorm-to-merge loop it enforces, and measure what subagent mode costs on your Pro or Max plan.
CLI tools a coding agent needs on a VPS
Install the command line tools a coding agent reaches for on a bare Ubuntu VPS, in three tiers, with the reason each one saves tokens and tool calls.
Upgraded Claude but usage limits did not change
You paid for a higher Claude plan and still hit the same wall. Work through the checks in order: billing timing, account mismatch, org seats, stale CLI login.
Claude API rate limit headers, explained
Every anthropic-ratelimit header the Claude API returns, what retry-after means on a 429, and what the unified 5h and 7d headers Claude Code reads report.
Claude Code vs Cursor, Codex and Copilot
Terminal agent, editor assistant or cloud agent? Compare Claude Code, Cursor, Codex and Copilot by how each one works, what they cost, and where a VPS fits.
Run Claude Code safely on a server
Claude Code can run any command your user can. What the skip permissions flag changes, and how to contain the blast radius, from sandbox to disposable VPS.
What is an agent harness?
An agent harness is the program around the model: the loop, the tools, the permissions and the session state. How it differs from a model and a framework.
Claude Code plugins: what they are and cost
What a Claude Code plugin is, where it lives, how to install one, and what it really costs: nothing for the mechanism, tokens for what it puts in context.
Run MCP servers on a VPS for AI coding agents
Run Model Context Protocol servers on your own VPS so AI agents get real tools: stdio and remote HTTP transports, systemd, TLS, auth, and every failure mode.
Keep secrets out of your AI agents
An agent holding your API keys can leak them in one tool call. Give it scoped short lived tokens behind a credential gateway, never the real keys.
Is Claude Code included with Claude Pro?
Yes, on Pro, Max, Team and Enterprise, and no on the free plan. See what shares your usage window, and when an API key quietly bills you instead.
Claude on Linux: Desktop App and CLI
What runs natively on Linux today: the beta desktop app from apt, the Claude Code CLI, editor plugins, and which paid plan covers each one.
Claude Code sessions that message each other
One Claude Code session can send text to another on the same VPS. What ListAgents and SendMessage do, when a second session helps, and why messages get held.
Claude cloud session credits: how they're used
A cloud session runs Claude Code in the cloud, on Anthropic's machines by default. See which balance it uses, what the credits are, and when they run out.
Recall: give Claude Code a memory on a VPS
Recall is a fully local plugin that logs each Claude Code session and condenses it into a resumable summary. Set it up on a VPS and measure the saving.
What is loop engineering? A definition
Loop engineering means designing the trigger, boundary, verification and budget an AI agent repeats, instead of writing one clever prompt. A plain definition.
Claude Code Projects: threads and your limits
Every thread in a Claude Code project is a full cloud session on your plan limits. See what burns usage fastest and which settings slow it down.
Why coding agents ignore your instructions
Your instruction file says stop and the agent does it anyway. The mechanics behind that, and a diagnosis you can run before you rewrite the rule again.
What are agent skills, really?
An agent skill is a folder with a SKILL.md file whose instructions load only when a task needs them. Why that beats a giant prompt, and how it differs from MCP.
MiMo-Code: Xiaomi's answer to Claude Code
What MiMo-Code actually is: Xiaomi's MIT-licensed terminal coding agent, forked from OpenCode. Read the self-reported benchmark claims before you switch.
Run Claude Code on Bedrock or Vertex AI
Point Claude Code at Amazon Bedrock or Google Vertex AI: the environment variables, where credentials come from, who gets billed, and what you give up.
Use Claude Code from your phone
Claude Code runs in tmux on a VPS and your phone is only the window. SSH keys, mosh for flaky mobile data, tmux attach, and the keyboard fixes that matter.
What Claude Code writes into your commits
Claude Code adds a Co-authored-by trailer to commits, and cloud sessions add a claude.ai link. Read what is there, then control it before you push.
Claude Code auto mode: the new default
Auto mode is now the Claude Code default in terminal and VS Code sessions. What each permission mode does, and which one a server you cannot watch deserves.
Claude Code with an Obsidian vault on a VPS
An Obsidian vault is a folder of markdown, so Claude Code can refile and audit notes. Here is the VPS setup and the permission rules that stop bulk rewrites.
The anti-slop skill for AI coding agents
Anti-slop is a third-party Agent Skill that filters generic AI output from your coding agent. What the three tiers do, and what the core costs per call.
Claude Team Premium vs Max: Which to Buy
Team Premium seats and Claude Max cost the same per person on annual billing. What differs is who controls the seat and which terms cover your data.
Give coding agents a disposable VM
AI coding agents belong on a machine you can destroy. Blast radius, clean state per task, snapshots, and the VPS pattern that keeps it cheap.
The unlazy skill and its Depth Tree method
How the unlazy skill stops an agent declaring done early: the Depth Tree, gates files, the PLAN.md contract, install steps, and what the depth costs you.
Claude Code Hooks Explained
Claude Code hooks run whether the model agrees or not. Where they live, which events fire, what exit code 2 does to a tool call, and the security cost.
Run Claude Code on a remote VPS with tmux
Run Claude Code on an always-on Linux VPS inside tmux so agent sessions survive a dropped SSH connection. Install, harden, and the failure modes to expect.
Matt Pocock's skills: which ones to install
Matt Pocock's skills repo ships 27 agent skills. Here is which ones a solo developer on a VPS should install, and which only pay off on a team.
Claude usage limits: what to do when you hit one
Switching models only fixes a model family limit. How Claude subscription session and weekly limits differ from API 429 rate limits, and what to do next.
Which Claude model should I use? Cost guide
Opus 5.5, Sonnet 5.5 or Haiku 5.5? The October 2026 rates per model, a worked cost comparison on 100,000 jobs, and the settings that move a bill most.
Is Claude Code worth paying for?
A Claude Code plan pays for itself in recovered hours. Here is the arithmetic at your own rate, the cases where it fails, and the VPS cost nobody counts.
Claude Code pricing by country and currency
Claude Code is priced at 20 USD in the US and in local currency where Anthropic supports it. Here is how region, tax and your card change what you pay.
Claude Code: API key instead of a subscription
Yes: Claude Code runs on an Anthropic API key with no Claude subscription; the two bill separately. See which one your session uses, and how to switch.
Is the Claude API cheaper than a subscription?
Metered API billing or a flat plan? Here is the break-even arithmetic on current per-token rates, and what moves it further than the plan fee does.
What are Claude tokens? Claude Code's token math
A Claude token is a few characters. See why a Claude Code turn can bill 80,000 tokens and why five idle minutes on an API key can make the next turn cost 5x.
Claude Max Price: $200 vs $100 per Month
Claude Max costs $100 a month for 5x Pro usage or $200 for 20x. Same models and features at both prices. See what the multiplier means and which tier fits you.
Which Claude plan do you need in 2026?
Free, Pro, Max, Team or Enterprise? Match the 2026 tiers to the way you work: which plans include Claude Code, and when Team beats five Pro accounts.
Claude limit reached: what to do next
Hit a Claude usage limit? Work out which window you are waiting on, then pick a route: smaller model, smaller context, usage credits, or the API.
Does Claude Train on Your Code?
Anthropic trains on your code if a consumer account has model improvement on, or your company opted in. See which terms a session uses and what stays on disk.
Turn a Technical Book Into an Agent Skill
Convert a PDF, EPUB or folder of internal docs into an agent skill your coding agent loads on demand: install, token budget, headless runs, licensing.
Claude Cowork vs Claude Code: how to choose
Cowork runs in an Anthropic sandbox and touches folders you connect. Claude Code runs on your machine or VPS. Where each one fits, checked October 2026.
Ponytail: the lazy senior dev agent skill
Ponytail makes a coding agent take the smallest change that works. What it ships, what its own benchmarks show, and how to copy the rule today.
Claude Code enterprise cost: seats vs API
Claude Code on Team and Enterprise: what each seat includes, the seat prices published in August 2026, and when paying per token costs less.
Claude Code context: stop slow, costly sessions
Every turn re-sends your whole context, so a long session slows down and costs more. Read /context, cut the fixed tax, then clear and compact with intent.
Claude Code resume and session history
Resume a Claude Code session by name or from the picker, and find the plaintext transcripts it leaves behind on the machine where the agent ran.
Share agent skills across repos without drift
Copy a skill into eight repos and the copies drift. Treat skills like dependencies: one shared repo, and a version each project pins and reviews.
Fix Claude Code's invalid API key error
Claude Code says invalid API key while you pay for a subscription? Find the stray ANTHROPIC_API_KEY on your VPS, and learn why /login will not fix it.
Claude Team pricing for a small business
Seat math for a 3 to 15 person team as of October 2026: standard and premium seat prices, when an API key beats a seat, and worked examples at 5 and 12 people.
How much does Claude Code cost?
Claude Code costs $20 a month on Pro, $100 or $200 on Max, or per token with API credits. Prices as of October 2026, with a worked monthly estimate.
Claude Code output styles explained
An output style edits Claude Code's system prompt, so it shapes every reply. What the built-in styles do to your transcript, and how to write your own.
Opus priority access used up: what it means
Your weekly Opus allowance is spent. Sonnet still works. When Opus resets, whether credits or a Max upgrade bring it back early, and what to do in Claude Code.
Claude Code Mod Examples and Writing Your Own
Three real Claude Code mods read hook by hook, then a small TypeScript mod that refuses VPS lockout commands, checked with plugin validate and plugin test.
Claude Opus 5.5: price, plans and fast mode
Opus 5.5 costs $4 per million input tokens and $20 output, 20% below Opus 5. See which Claude plans include it and when fast mode is worth double the rate.
Claude Code mods and what they can reach
A Claude Code mod runs TypeScript inside the agent with your credentials in reach. See what it can touch on a VPS and the checks to run before you install one.
NVIDIA OpenShell: sandbox agents on a VPS
Run Claude Code inside an NVIDIA OpenShell v0.1.2 sandbox on a Docker VPS. Read what the default policy blocks and which attacks it still lets through.
Run Orca's coding agents on a VPS
Run Orca's coding agents on a VPS so they keep working when your laptop sleeps: orca serve on headless Ubuntu, under systemd and firewalled from the internet.
Which models Claude Max gives you
Which Claude models each paid plan includes, and why the most capable one runs out first while the rest of your Claude Max allowance is still there.
Cambium: govern the docs your agents write
Agent-written docs drift into stale claims and contradictory rules. Cambium answers with a governance kernel and append-only receipts. Who needs it.
Claude Code "model overloaded": what to do
Claude Code shows an overloaded message when Anthropic's API returns HTTP 529. Tell that apart from a 429 rate limit and from a plan usage limit.
How to Write Your Own Agent Skill
Write your own agent skill by distilling one real failure: the SKILL.md anatomy, the description line that decides when it fires, and how to test it.
Agent skills vs MCP servers vs rules files
Three ways to give a coding agent context, and one rule for picking. See what a skill, an MCP server and a rules file each cost in tokens and upkeep.
Set up a Claude Code statusline on a VPS
The statusLine setting runs a script and prints its stdout under the prompt. Show hostname, directory, git branch and model, so you edit the right server.
AGENTS.md and HUMAN.md, explained
AGENTS.md is the README your coding agent reads. What belongs in one, what never does, how CLAUDE.md fits, and a starter template to copy.