[**New**Recall: all-day sessions, no compaction →](https://contextmode.ai/recall) # Spend less on coding agents. *Control what they do.* Context Mode sits between your coding agents and the model. Each request costs less, sessions carry what they learned, and your rules decide what runs. [Get started free](https://console.contextmode.ai/login) [Pricing](https://contextmode.ai/pricing) $ `npx @context-mode/cli` 1,000 requests free, every feature, no card. Works with Claude Code, Codex, OpenCode, Pi and their desktop apps. [Set up your app](#start) [From the team behind the free Context Mode Engine: 34K GitHub stars](#engine-free) Your coding agent Its model Claude Code Claude Codex GPT OpenCode Claude Pi Claude, GPT Also: Claude Desktop, Codex Desktop and T3 Code Context Mode Save Context Saving Protect Remember **Claude Code** `600 tests, 1 to fix` 17.0 KB → 1.2 KB *folded* **Codex** `cat .env` stopped before the shell *blocked* **Claude Code** `2 h later` picked up, full history *recalled* **Codex** `7 MB registry file` 407 B back to the model *in code* **Claude Code** `git push origin main` protected branch *blocked* **Codex** `deploy target?` Render, not Hetzner *remembered* **Claude Code** `turn this plan into tickets` to-tickets loaded *skill* [Gateway A/B, long session, Claude Opus 5.5 **$7.20 → $2.49** *65.5% lower*](https://contextmode.ai/docs/benchmarks) Enterprise · your own cloud ## Run Context Mode in your own cloud. *Cloudflare, AWS or Google Cloud.* The same gateway, in your account. Your code, prompts and memory never leave it. | | Our cloud | Your cloud | | --- | --- | --- | | Where requests go | Your agent, our gateway, the model | Your agent, your gateway, the model | | Code, prompts, memory | In our account | In your account only | | Protect records | In our console | In your own storage | | Network | Public internet | Your region and network rules | | Security review | A new vendor to approve | An account you already approved | | Price | Pro and Team, monthly | From $15,000 a year, 1,000,000 requests a month | 1. **Pick your cloud and region** Cloudflare, AWS or Google Cloud. 2. **We deploy it with you** One call with our team, in your account. 3. **Connect your agents** The same one command, to your own address. [Book a setup call](https://cal.com/mksglu) For teams with 1,000,000 requests a month or more. Yearly contract. How it works ## Spend less. Remember more. *Run only what you allow.* Context Mode acts at three points on each request: before it goes out, before a tool runs, and when a result comes back. Save Remember Protect **Your coding agents** Any machine *17.0 KB 800 orders 330,785 tokens* **Context Mode** - Folds test, build and log output - Runs scripts, returns the answer - Trims tool schemas *1.2 KB 4 orders 75,591 tokens* **Model API** Your Anthropic or OpenAI account **Your archive** Full output, read back by id Try it Test-Driven Debugging Large Tool-Output Handling Long Agentic Coding Session Your agent runs 600 tests. 1 fails. Printed **17.0 KB** Sent to the model **1.2 KB** Sent to the model - The failing test and its error - The summary line - One line for the 599 that passed Kept in your archive - All 600 results, word for word [npm test fix loop · Claude Opus 5.5 **$0.087 → $0.068** *22% lower* 15 of 16 runs](https://contextmode.ai/docs/benchmarks) Your agent reads an API response with 800 orders. Printed **800 orders** Sent to the model **4 orders** Sent to the model - Every field name - The first 3 orders and the last - A line that counts the rest Kept in your archive - The other 796 orders [One large JSON file · Claude Opus 5.5 **$0.086 → $0.068** *21% lower* 12 of 12 runs](https://contextmode.ai/docs/benchmarks) One session, 30 steps. Tokens sent on each call. Direct **330,785** Context Mode **75,591** Sent to the model - Your recent work, unchanged - An index of older work Kept in your archive - Older work, word for word [Long agentic coding session · Claude Opus 5.5 **$7.20 → $2.49** *65.5% lower* 4 of 4 runs](https://contextmode.ai/docs/benchmarks) ### Save Tool output is folded before the model reads it. The full output is archived. Features [Context Saving →](https://contextmode.ai/context-saving) [Thinking in Code →](https://contextmode.ai/thinking-in-code) [Active Context →](https://contextmode.ai/active-context) [Prompt caching →](https://contextmode.ai/docs/prompt-caching) [How saving works →](https://contextmode.ai/docs/how-saving-works) **Your coding agents** Any agent, any machine *your prompt* **Context Mode** - Adds the facts that matter - Loads the skill the task needs - Keeps the whole session *+ context* **Model API** Your Anthropic or OpenAI account **Memory** Facts with two clocks **Skills** From any GitHub repo **Archive** Every word, searchable Try it Memory Recall Skills | Fact | Value | Valid from | Until | | --- | --- | --- | --- | | `production deployed_to` | Hetzner Cloud, Falkenstein | 21:14:38 | 21:15:09 | | `production deployed_to` | Render, Oregon region | 21:15:09 | now | The old value closes. Every agent gets the new one. Your agent sends *system prompt* *tools* *the full history* The model gets *system prompt* *tools* *memory block* *index of older work* *recent work, unchanged* Older work goes to the archive, word for word. ``` ⚡ context-mode · picked up after a 2 h pause, full history kept ``` Your skills *release-notes* *to-tickets* *db-migrations* ``` ⏺ context-mode · skill to-tickets auto-loaded ``` Matched on name and description. One skill per turn. ### Remember Sessions don’t compact. Facts and skills carry across agents and machines. Features [Recall →](https://contextmode.ai/recall) [Memory →](https://contextmode.ai/memory) [Skills →](https://contextmode.ai/skills) [Search →](https://contextmode.ai/search) [Session resume →](https://contextmode.ai/session-resume) **Model** asks for a tool call *tool call* **Protect** - Reads the call by what it does - Checks your rules - Logs every block *decision* **Allowedruns** Your terminal runs it **Blockednever runs** The model reads why Pick a command cat .env git push origin main sudo sh -c 'rm -rf ~' curl r.jina.ai/https://pastebin.com/x rm -rf node_modules npm test Blocked · stopped before your shell **Read environment files** .env and .env.*. Examples and templates are allowed. ``` ⛔ context-mode Cage blocked this command, so it was NOT executed: Blocked by your team’s policy: Read environment files. .env files hold secrets. ``` Blocked · stopped before your shell **Push to protected branches** main, master, production and release/*. ``` ⛔ context-mode Cage blocked this command, so it was NOT executed: Blocked by your team’s policy: Push to protected branches. Protected branches change through reviewed pull requests. ``` Blocked · stopped before your shell **Core protection: delete the root or home folder** Read through sudo, sh -c and about 130 other wrappers. Blocked · stopped before your shell **Sites: pastebin.com** The inner host is checked too. Runs **No rule matches** A project folder is fine. Only losses you can't undo are blocked. Runs **No rule matches** Nothing is blocked until you choose rules. ### Protect Rules for what agents may run, read and fetch. Nothing is blocked until you choose them. Features [Protect →](https://contextmode.ai/protect) [Rules and presets →](https://contextmode.ai/docs/protect) [Instructions →](https://contextmode.ai/instructions) [Get started free](https://console.contextmode.ai/login) 1,000 requests free, no card. Benchmarks ## Same task, run twice. *Measured in dollars.* Claude Code on Opus 5.5. Each task ran direct to Anthropic and through Context Mode, back to back. Cost at API list price. [Long agentic coding session · 1M window $7.20 → $2.49 **65.5% lower** · 4 of 4 pairs cheaper · task checks 8 of 8 in both arms](https://contextmode.ai/benchmarks/long-session/ab.json) [**155 of 168** runs cost less](https://contextmode.ai/docs/benchmarks#pooled) [**168 of 168** tasks succeeded in both arms](https://contextmode.ai/docs/benchmarks#pooled) [**$28.28 → $23.16** all 168 pairs, direct → Context Mode](https://contextmode.ai/docs/benchmarks#pooled) Direct Through Context Mode Cost per task - [Test-Driven Debugging](https://contextmode.ai/docs/benchmarks#test-debugging) - Test fix loop (minitest) $0.157 → **$0.061** 61% lower [8 of 8 runs ↗](https://contextmode.ai/benchmarks/data/final-opus55-tests-W3-minitest-W4.json) - npm test fix loop, short $0.087 → **$0.068** 22% lower [15 of 16 runs ↗](https://contextmode.ai/benchmarks/data/v3-opus55-short.json) - npm test fix loop, long $0.085 → **$0.067** 21% lower [11 of 12 runs ↗](https://contextmode.ai/benchmarks/data/final-opus55-tests-W3-minitest-W4.json) - [Agentic Coding](https://contextmode.ai/docs/benchmarks#agentic-coding) - Code search (grep over 150 files) $0.093 → **$0.066** 29% lower [16 of 16 runs ↗](https://contextmode.ai/benchmarks/data/v3-opus55-short.json) - One-line edit $0.075 → **$0.054** 28% lower [11 of 12 runs ↗](https://contextmode.ai/benchmarks/data/v3-opus55-short.json) - Repo history question (git log, 320 commits) $0.071 → **$0.053** 25% lower [15 of 16 runs ↗](https://contextmode.ai/benchmarks/data/v3-opus55-short.json) - [Large Tool-Output Handling](https://contextmode.ai/docs/benchmarks#tool-output) - One large log $0.091 → **$0.071** 22% lower [15 of 16 runs ↗](https://contextmode.ai/benchmarks/data/v3-opus55-short.json) - One large JSON file $0.086 → **$0.068** 21% lower [12 of 12 runs ↗](https://contextmode.ai/benchmarks/data/v3-opus55-short.json) - [Multi-Agent Orchestration](https://contextmode.ai/docs/benchmarks#multi-agent) - Three parallel subagents, then one more $0.481 → **$0.408** 15% lower [20 of 20 runs ↗](https://contextmode.ai/benchmarks/data/v4-opus55-W1-W2-W3-W4.json) - [Long-Context Data Analysis](https://contextmode.ai/docs/benchmarks#data-analysis) - Large documents processed with a script run 2, later build $0.223 → **$0.201** 10% lower [15 of 20 runs ↗](https://contextmode.ai/benchmarks/data/v4-opus55-W1-W2-W3-W4.json) - Large documents processed with a script run 1, earlier build $0.226 → **$0.205** 9% lower [17 of 20 runs ↗](https://contextmode.ai/benchmarks/data/final-opus55-tests-W3-minitest-W4.json) Every pair counts. No figure for Codex yet. [Method, 95% ranges and Haiku 4.5 →](https://contextmode.ai/docs/benchmarks) [Get started free](https://console.contextmode.ai/login) 1,000 requests free, no card. Headless CI ## Cheaper coding agents in CI. *20% to 23% lower cost per run.* Add two env lines to the job that runs your agent. Same agent, same prompt, same model. Pick a job, set your runs, see the saving. CI job CI failure fix @mention fix Issue triage Model Sonnet 5.5 Opus 5.5 Runs per month **22.8%** lower cost per run A test fails on a pull request. The agent reads the logs, finds the cause and pushes a fix. Direct per month **$50.20** Context Mode per month **$42.00** You save per month **$8.20** Sonnet 5.5 · 16 tasks · 95% range 11.6 to 32.2% · [proof](https://github.com/contextmode/ci-agent-bench/blob/main/confirm-1101/RESULTS-r2.md) Each month is the runs you set times the measured cost per run. Next step ``` npx @context-mode/cli ci init ``` [Try it with your key](https://contextmode.ai/try) [Run it in your own repo](https://github.com/contextmode/ci-agent-bench/generate) [See the proof](https://contextmode.ai/docs/benchmarks#ci-headless) Get started ## Set up in a minute. *Removed with one command.* Works with Claude Code, Claude Desktop, Codex, Codex Desktop, T3 Code, OpenCode and Pi. Install your app the way its makers say. Then one command signs you in, finds it, and shows each change before it writes. Your own model account still pays the model. 1. ### Install your app Use its makers’ own install. Pick your app to see how its makers install it. 2. ### Run the CLI It signs you in, asks which apps to connect, and keeps a backup of each file. $ `npx @context-mode/cli` 3. ### Restart and watch Start a new session. Work as before. The console shows tokens, cost and saving for every request. [Open the console →](https://console.contextmode.ai/app) Your app Claude Code Claude Desktop Codex Codex Desktop T3 Code OpenCode Pi 1 Install Claude Code from its makers: [Claude Code setup →](https://code.claude.com/docs/en/setup) 2 Connect Context Mode `npx @context-mode/cli setup --agent claude` **Writes** `~/.claude/settings.json` **You need** Your Claude login, a subscription or an API key. Restart Claude Code. 1 Install Claude Desktop from its makers: [Download Claude →](https://claude.ai/download) 2 Connect Context Mode `npx @context-mode/cli setup --agent claude-desktop` **Writes** `Developer → Configure Third-Party Inference… (an entry named contextmode)` **You need** Quit the app fully (Cmd+Q) and open it again. The Code and Cowork tabs go through Context Mode. 1 Install Codex from its makers: [Codex CLI →](https://developers.openai.com/codex/cli) 2 Connect Context Mode `npx @context-mode/cli setup --agent codex` **Writes** `~/.codex/config.toml` **You need** Your Codex login: ChatGPT, or an API key stored with codex login --with-api-key. A key that is only exported in your shell is not sent. 1 Install Codex Desktop from its makers: [ChatGPT desktop app for macOS and Linux →](https://developers.openai.com/codex/app) `winget install --id 9PLM9XGG6VKS -s msstore` *Windows* 2 Connect Context Mode `npx @context-mode/cli setup --agent codex-desktop` **Writes** `~/.codex/config.toml (the same file as the Codex CLI)` **You need** Your Codex login. Quit the app fully (Cmd+Q) and open it again. 1 Install T3 Code from its makers: [T3 Code install docs →](https://github.com/pingdotgg/t3code/blob/main/docs/user/install.md) `brew install --cask t3-code` *desktop app, macOS* `curl -fsSL https://t3.codes/install.sh | sh` *CLI, macOS and Linux* `winget install T3Tools.T3Code` *Windows* 2 Connect Context Mode `npx @context-mode/cli setup --agent t3code` **Writes** `~/.claude/settings.json and ~/.codex/config.toml` **You need** T3 Code runs the Claude Code and Codex you have, with their logins. In Settings → Providers, keep CODEX_HOME at ~/.codex and leave Shadow home empty. 1 Install OpenCode from its makers: [OpenCode docs →](https://opencode.ai/docs/) `curl -fsSL https://opencode.ai/install | bash` `npm install -g opencode-ai` `brew install anomalyco/tap/opencode` 2 Store your API key with OpenCode’s own login `opencode auth login` *pick Anthropic, or set ANTHROPIC_API_KEY* 3 Connect Context Mode `npx @context-mode/cli setup --agent opencode` **Writes** `~/.config/opencode/opencode.json` **You need** Your own Anthropic API key. OpenCode has no Claude sign-in, so a Claude subscription does not work here. No key is written to the file. 1 Install Pi from its makers: [Pi on GitHub →](https://github.com/earendil-works/pi) `npm install -g @earendil-works/pi-coding-agent` `curl -fsSL https://pi.dev/install.sh | sh` 2 Store your API key Start `pi`, then type `/login` in Pi, not in your shell. Or set `ANTHROPIC_API_KEY` or `OPENAI_API_KEY`. 3 Connect Context Mode `npx @context-mode/cli setup --agent pi` **Writes** `~/.pi/agent/models.json` **You need** Your own Anthropic or OpenAI API key. A Claude subscription does not go through Pi. If you use one, setup sets only OpenAI. To leave: `npx @context-mode/cli disconnect` [Quick start →](https://contextmode.ai/docs/quick-start) [Get started free](https://console.contextmode.ai/login) 1,000 requests free, no card. Protect ## Your agent asks. *Your rules answer.* Protect checks every command, file read, web fetch and tool-server call from Claude Code and Codex before it runs. The hook stops a blocked call before your shell. In every plan, Free included. [How Protect works →](https://contextmode.ai/protect) 1. 01 **Connect your agents** $ `npx @context-mode/cli` Only the base URL changes. 2. 02 **Pick a preset** Nothing is blocked until you pick one. 3. 03 **Keep working** The agent reads why a call was blocked. You see it in the log. Preset Observe Balanced Locked down See before you rule. **7 run** `git push origin main` Runs `cat .env` Runs `rm -rf ~` Runs `terraform destroy` Runs `aws s3 rm s3://backups --recursive` Runs `WebFetch example.com` Runs `npm test` Runs Nothing is blocked. Activity lists the programs, sites and tool servers your agents used, each with Block and Allow. Where most developers start. **4 blocked · 1 logged · 2 run** `git push origin main` Blocked *Push to protected branches* `cat .env` Blocked *Read environment files* `rm -rf ~` Blocked *Core protections* `terraform destroy` Blocked *Destroy infrastructure* `aws s3 rm s3://backups --recursive` Logged *Change cloud resources* `WebFetch example.com` Runs *Other sites allowed* `npm test` Runs The hook stops a blocked call before your shell: the agent reads the rule and why, and carries on. Logged means it ran, and the log says it would have been blocked. For regulated teams and unattended agents. **6 blocked · 1 run** `git push origin main` Blocked *Push to protected branches* `cat .env` Blocked *Read environment files* `rm -rf ~` Blocked *Core protections* `terraform destroy` Blocked *Destroy infrastructure* `aws s3 rm s3://backups --recursive` Blocked *Change cloud resources* `WebFetch example.com` Blocked *Only sites on your list* `npm test` Runs Only the sites and tool servers on your list are reached. Public package registries stay open. What your agent reads ``` ⛔ context-mode Cage blocked this command, so it was NOT executed: Blocked by your team’s policy: Push to protected branches. Protected branches change through reviewed pull requests. ``` It tells you, doesn’t retry another way, and offers a branch and a pull request. What your log keeps 10:42 *Blocked* **Push to protected branches** *Bash · git* The rule, tool and program. Never the command text, so you can show it to an auditor. Or write your own rules for **sites**, **commands**, **scripts**, **files** and **tool servers**, and test each one before you save it. [Rule types →](https://contextmode.ai/docs/protect#rule-types) For you Free · Pro, from $20 a month - One policy for Claude Code and Codex, on every machine you sign in from - Presets, four packs and your own rules - A log of every decision, export as CSV or JSON Lines - Core protections stay on when your requests run out [Get started free](https://console.contextmode.ai/login) For your team Team · Enterprise - One policy for the whole org. An agent cannot loosen it - An API key can only tighten it. Loosening needs a person and a reason - Every change in History, in a hash chain you can verify - One pool of requests and one bill. Enterprise can run in your own Cloudflare account [Talk to us](mailto:sales@context-mode.com) Tested in real Claude Code sessions with Claude Opus 5.5 (2026-10-02) and Claude Haiku 4.5 (2026-10-04): every run blocked the push to main and the read of .env, and the work still shipped on a branch. [Try it in 5 minutes →](https://contextmode.ai/docs/protect#try-it) Protect reads the call, not the program: a script file or a compiled program gets past it. Keep your agent’s sandbox on. Open source ## Context Mode Engine. *Free, local, private.* Context Mode Engine runs on your machine with eleven coding agents. It keeps raw tool output in a local sandbox and index, so only the answer enters the context. The source is on GitHub, open to read. Free for all time Free to use. Source-available under the [Elastic License 2.0](https://github.com/mksglu/context-mode/blob/main/LICENSE). Local It runs on your machine and keeps its data in `~/.context-mode`. Private Your code and sessions stay on your machine. 98.8% fewer bytes in context Median over tool outputs of 10 KB or more, benchmark of 2026-10-31. [How we measure](https://contextmode.ai/docs/engine/benchmarks) [Install the free plugin](https://contextmode.ai/engine#install) [Source on GitHub](https://github.com/mksglu/context-mode) 34K GitHub stars and 835K npm downloads. [Daily stats](https://contextmode.ai/open-source/stats) · [Method and sources](https://contextmode.ai/benchmarks/data/reach-2026-11-01.json) Pick your agent to see its own install command. ### Claude Code Plugin. Context Mode installs with the agent's own plugin command. Install ``` claude plugin marketplace add mksglu/context-mode claude plugin install context-mode@context-mode ``` Check ``` /ctx-doctor ``` **Update and remove** Update ``` claude plugin update context-mode@context-mode ``` Remove ``` context-mode setup --remove --agents claude-code ``` The hook check passed on 2026-10-26 with Claude Code 2.1.309. [Source: the install guide](https://github.com/mksglu/context-mode/blob/1e5094693e8a2e44e3c18262dda8885a960a0c15/docs/install/README.md) ### Codex Plugin. Context Mode installs with the agent's own plugin command. Install ``` codex plugin marketplace add mksglu/context-mode codex plugin add context-mode@context-mode ``` Next, trust the hooks ``` npm i -g context-mode context-mode setup --agents codex ``` Check ``` /ctx-doctor ``` **Update and remove** Update ``` codex plugin marketplace upgrade context-mode ``` Remove ``` context-mode setup --remove --agents codex ``` The hook check passed on 2026-10-26 with Codex 0.164.0. [Source: the install guide](https://github.com/mksglu/context-mode/blob/1e5094693e8a2e44e3c18262dda8885a960a0c15/docs/install/README.md) ### Gemini CLI Plugin. Context Mode installs with the agent's own plugin command. Install ``` gemini extensions install https://github.com/mksglu/context-mode ``` Check ``` /ctx-doctor ``` **Update and remove** Update ``` gemini extensions update context-mode ``` Remove ``` context-mode setup --remove --agents gemini gemini extensions uninstall context-mode ``` The hook check passed on 2026-10-26 with Gemini CLI 0.65.0. [Source: the install guide](https://github.com/mksglu/context-mode/blob/1e5094693e8a2e44e3c18262dda8885a960a0c15/docs/install/README.md) ### Qwen Code Plugin. Context Mode installs with the agent's own plugin command. Install ``` qwen extensions install https://github.com/mksglu/context-mode:context-mode ``` Check ``` /ctx-doctor ``` **Update and remove** Update ``` qwen extensions update context-mode ``` Remove ``` context-mode setup --remove --agents qwen qwen extensions uninstall context-mode ``` The hook check passed on 2026-10-26 with Qwen Code 0.26.1. [Source: the install guide](https://github.com/mksglu/context-mode/blob/1e5094693e8a2e44e3c18262dda8885a960a0c15/docs/install/README.md) ### Pi Plugin inside the agent. The agent loads Context Mode as a plugin in its own process. Its tools come from that plugin. Install ``` pi install npm:context-mode ``` Check ``` pi list ``` **Update and remove** Update ``` pi update --extensions ``` Remove ``` pi remove npm:context-mode ``` The hook check passed on 2026-10-26 with Pi 0.73.1. [Source: the install guide](https://github.com/mksglu/context-mode/blob/1e5094693e8a2e44e3c18262dda8885a960a0c15/docs/install/README.md) ### OpenCode Plugin inside the agent. The agent loads Context Mode as a plugin in its own process. Its tools come from that plugin. Install ``` opencode plugin add context-mode ``` ``` opencode plugin context-mode --global ``` Check ``` /ctx-doctor ``` **Update and remove** Update ``` opencode plugin update ``` Remove ``` opencode plugin remove context-mode context-mode setup --remove --agents opencode ``` The hook check passed on 2026-10-26. Install and hooks are checked. The plugin's tool name gets its check in a live OpenCode session next. [Source: the install guide](https://github.com/mksglu/context-mode/blob/1e5094693e8a2e44e3c18262dda8885a960a0c15/docs/install/README.md) ### OMP Plugin inside the agent. The agent loads Context Mode as a plugin in its own process. Its tools come from that plugin. Install ``` omp plugin install context-mode ``` Check ``` omp plugin list ``` **Update and remove** Update ``` omp plugin upgrade context-mode ``` Remove ``` omp plugin uninstall context-mode ``` The hook check passed on 2026-11-13 with OMP 18.20.0. [Source: the install guide](https://github.com/mksglu/context-mode/blob/1e5094693e8a2e44e3c18262dda8885a960a0c15/docs/install/README.md) ### Copilot CLI npm and setup. Install Context Mode with npm. Then setup adds its hooks to the agent. Install ``` npm i -g context-mode context-mode setup --agents copilot-cli ``` Check ``` /ctx-doctor ``` **Update and remove** Update ``` context-mode upgrade ``` Remove ``` context-mode setup --remove --agents copilot-cli ``` The hook check passed on 2026-10-26 with Copilot CLI 1.0.103. [Source: the install guide](https://github.com/mksglu/context-mode/blob/1e5094693e8a2e44e3c18262dda8885a960a0c15/docs/install/README.md) ### Kiro npm and setup. Install Context Mode with npm. Then setup adds its hooks to the agent. Install ``` npm i -g context-mode context-mode setup --agents kiro ``` Check ``` /ctx-doctor ``` **Update and remove** Update ``` context-mode upgrade ``` Remove ``` context-mode setup --remove --agents kiro ``` Checked at hook setup on 2026-10-26. A live run in the host app comes next. [Source: the install guide](https://github.com/mksglu/context-mode/blob/1e5094693e8a2e44e3c18262dda8885a960a0c15/docs/install/README.md) ### VS Code npm and setup. Install Context Mode with npm. Then setup adds its hooks to the agent. Install ``` npm i -g context-mode context-mode setup --agents vscode ``` Check ``` /ctx-doctor ``` **Update and remove** Update ``` context-mode upgrade ``` Remove ``` context-mode setup --remove --agents vscode ``` Checked at hook setup on 2026-10-26. A live run in the host app comes next. [Source: the install guide](https://github.com/mksglu/context-mode/blob/1e5094693e8a2e44e3c18262dda8885a960a0c15/docs/install/README.md) ### ZCode npm and setup. Install Context Mode with npm. Then setup adds its hooks to the agent. Install ``` npm i -g context-mode context-mode setup --agents zcode ``` Check ``` /ctx-doctor ``` **Update and remove** Update ``` context-mode upgrade ``` Remove ``` context-mode setup --remove --agents zcode ``` The hook check passed on 2026-10-26. [Source: the install guide](https://github.com/mksglu/context-mode/blob/1e5094693e8a2e44e3c18262dda8885a960a0c15/docs/install/README.md) ## Try it on *your own agents.* Start free: 1,000 requests, every feature, no card. When you run out, nothing breaks. [Get started free](https://console.contextmode.ai/login) [Read the docs](https://contextmode.ai/docs)