Coding Agents

Build inference shell apps with AI coding assistants like Claude Code, Cursor, or Windsurf.

Setup

1. Install CLI

1curl -fsSL https://cli.inference.sh | sh2infsh login

2. Create App

1# Python app2infsh app init my-app3cd my-app45# Or Node.js app6infsh app init my-app --lang node7cd my-app

This creates your app with all the files needed, including skills that teach your coding agent how to build inference shell apps.

Skills Included

When you run infsh app init, the CLI creates a skills/ directory containing guidance for AI coding assistants:

How It Works

1. You describe what you want — Tell your coding agent what app to build
2. Agent reads skills — The agent uses the skills to understand inference shell patterns
3. Agent writes code — Creates inference.py, updates inf.yml, adds dependencies
4. Test locally — Run infsh app test to verify
5. Deploy — Run infsh app deploy to publish

Example Prompts

1Create an image resizing app that takes an image and dimensions, 2and returns the resized image.

1Build an LLM app that calls OpenAI's API. 2It should track token usage for billing.

1Make a YouTube audio downloader that extracts audio from videos 2and returns MP3 files.

Supported Agents

The skills work with any AI coding assistant that supports project-level context. belt plugin install wires belt into all of them in one step:

• Claude Code and Codex — plugin marketplace (see below)
• Copilot CLI, Cursor, Droid, Gemini CLI, Goose, Grok, Hermes, Kilo, Kimi, Kiro, Oh My Pi, OpenCode, Pi, Qwen Code, Windsurf — hooks, skills, and a belt section in the agent's instruction file

Other agent runtimes (belt plugin install)

1belt login2belt plugin install            # every agent installed on this machine3belt plugin install grok kiro  # or name them

Not every agent lets a hook hand text back to the model on each prompt. Goose hooks are observation-only, Cursor's headless agent -p runs the prompt hook only when Cursor's backend asks for it, Droid runs it only in its TUI and droid exec -o stream-jsonrpc, Grok reads a prompt hook's output only for a block decision, and Windsurf hooks return an exit code only. There, the instruction-file section, the skills, and belt suggest on demand carry belt instead.

Each install writes five core belt skills (suggest, skill, apps, remember, belt) into the agent's skills directory, a hooks config with event names that match that runtime, and a belt section in the agent's instruction file. Skills are downloaded from inference shell when you are logged in; embedded copies are used when you are not logged in, offline, or the download fails. Claude Code and Codex use their plugin marketplaces instead of a direct hooks install; see Claude Code plugin and Codex plugin.

Lifecycle hooks installed by belt plugin install:

SessionStart (plugin installs): Claude Code and Codex (marketplace plugin) call belt plugin hook session-start. When you are logged in, the hook prints your account email. When you are not (including anonymous guest sessions with no API key), it opens a browser for device authorization, prints the approval URL and user code into session context, and polls for up to 45 seconds. A 6-hour cooldown (~/.inferencesh/hook-auth-cooldown) prevents reopening the browser on every session. Cursor (manual install) uses a lighter check: belt me output or a login reminder.

For non-Claude agents, review reads the session transcript from hook stdin. Extraction prefers a local agent CLI on your PATH (codex, gemini, grok, or claude) so it can ride your existing subscription; when none is available, it falls back to the inference shell API (paid). Claude Code uses a richer pipeline (fork-based extraction and optional skill auto-publish) — see Claude Code plugin below.

If a hooks file already exists, manual init skips overwriting it (delete the file to reinstall). After init, follow the CLI message — restart Cursor, OpenCode, Pi, or Windsurf when prompted. OpenCode init runs npm install in the plugin directory and opencode plugin --global when the OpenCode CLI is on your PATH. Pi init runs pi install on the extension when the Pi CLI is on your PATH.

Hook data and privacy

Before installing, belt plugin install prints what belt hooks send upstream:

Never sent: source code, file contents, secrets, or full conversation history.

Traffic is encrypted (TLS 1.2+). See privacy and trust. Run belt plugin info for the per-hook upstream data table (Claude Code plugin) and compliance details.

Disabling hooks

Disable belt hooks for a project tree by adding .beltsh/config.json at the repo root (the CLI walks up from CWD like .git):

1{2  "hooks_disabled": true,3  "suggest_disabled": true,4  "knowledge_disabled": true5}

Quick disable everywhere: BELT_NO_HOOKS=1 (or any truthy value except 0 / false).

→ Using skills with other agents

Codex plugin

When the Codex CLI is on your PATH, belt plugin install codex uses the Codex plugin marketplace (same belt-sh/skills marketplace as Claude Code):

1belt login2belt plugin install codex    # add marketplace + install plugin

init runs:

1codex plugin marketplace add belt-sh/skills2codex plugin add belt@belt-sh-skills

This installs the full belt plugin — hooks, skills, bin scripts, agents, and rules — instead of the simplified manual install.

After install, run /hooks in Codex to review and trust belt hooks.

Duplicate hook cleanup: A successful plugin install removes belt hook entries from ~/.codex/hooks.json if that file already exists (for example after an earlier fallback install when the Codex CLI was missing). The plugin's own hooks.json manages belt hooks, so leaving both would run each hook twice. Non-belt entries in the global file are preserved; if every entry was belt-related, the global file is deleted. The CLI prints which path was updated.

Requires Codex CLI: If the codex command is not on your PATH, belt plugin install codex prints an error with a link to install the Codex CLI. The install then falls back to writing skills and ~/.codex/hooks.json directly.

Claude Code plugin

The belt CLI installs a belt plugin for Claude Code and Cowork (same hooks when CLAUDE_CODE_IS_COWORK is set). Hooks run in the background to suggest skills and apps, capture reusable knowledge, and optionally auto-publish skills from your sessions.

Use the belt plugin command group:

1belt login2belt plugin install claude    # add marketplace + install plugin3belt plugin install claude --inject-rules   # also append belt rules to ~/.claude/CLAUDE.md4belt plugin info           # verify install and hook configuration5belt plugin doctor         # check plugin health (use --fix to auto-repair)

Hook shims: Plugin hook scripts in bin/ are thin shims that delegate to belt plugin hook <event>. The marketplace cache can serve older hook scripts with embedded logic, so belt plugin install claude and belt plugin doctor --fix (when reinstalling) both scan Claude and Codex plugin caches and rewrite any stale hook scripts to shims immediately after install.

Troubleshooting: If hooks stop firing or Claude Code reports a missing plugin directory, run belt plugin doctor. It checks authentication, the plugin cache in Claude's installed_plugins.json, hooks.json inside the install path, that hook scripts in bin/ are thin shims across Claude and Codex caches, and recent activity in ~/.belt/hooks.log. With --fix, it reinstalls the belt plugin when the cache path is stale or missing (claude plugin uninstall belt@belt-sh-skills, then claude plugin install belt, with marketplace add as fallback), removes other stale cache directories, and patches hook scripts that still contain embedded logic. When no fixes are needed, doctor reports All checks passed; when --fix applies repairs, it lists each change (for example fixed: removed stale cache dir abc123 or fixed: patched hook-stop.sh in <hash>) and then prompts a context-aware restart — inside Claude Code, Run /reload-plugins or restart this session to apply changes; from a regular terminal, Restart your agent session to apply changes.

Use --inject-rules when you want belt guidance in your user-level CLAUDE.md (persists across sessions and survives context compaction). If a belt section already exists, init replaces it.

After install, restart Claude Code or run /reload-plugins. Plugin slash commands include /skill, /knowledge, /apps, and /suggest.

Claude Code review also runs fork-based extraction and can auto-publish reusable workflows as skills. Other agents use transcript-based extraction, preferring local CLIs (codex, gemini, grok) when installed — see Other agent runtimes above.

Knowledge import from existing Claude Code projects:

1belt plugin history --dry-run   # preview ~/.claude/projects memory + skill signals2belt plugin history             # import memory files + skill usage (requires belt login)3belt plugin history --extract   # also mine transcripts with Haiku (~$3; requires login)

Tips and notices: Contextual stderr tips after commands can be disabled with INFSH_NO_TIPS=1, or by passing --json / --pjson on the command. Hook tip: lines inside belt suggest --json output are separate (rate-limited in ~/.belt/notices/) and are not suppressed by those flags or INFSH_NO_TIPS.

Bounty and survey notices: The CLI stderr notice block loads active programs from GET /bounties (cached for 6 hours) and shows the highest-priority due notice — for example app-builder incentives or unanswered survey questions. Notice text, cooldowns, and priority come from the API and update without a CLI release. Neither bounty nor survey prompts are injected into belt suggest --json hook context. Claim app bounties with belt app promo submit <namespace/app-name> after deploy; answer surveys with belt feedback <question-id> "answer" or belt feedback "open message". Submissions go to POST /me/bounty and POST /me/survey respectively. See CLI setup — App bounties and CLI setup — Feedback.

→ Using skills with other agents · CLI setup

Next

→ CLI Setup — Manual CLI installation

→ Creating an App — Manual app creation