Commands
Codeep has 115 slash commands. Type /help inside Codeep for the same list — this page is generated from it, so the two cannot disagree.
★
Commands can be chained with
+ — for example /commit+push. Aliases are shown in brackets: /commit (/c).General
| Command | Description |
|---|---|
/help | Show this help |
/status | Current status |
/settings | Open settings |
/version | Show version |
/update | Check for updates |
/cost | Token usage and estimated cost this session, per provider and model, with prompt-cache savings |
/stats | Detailed session view — per-model breakdown, plan-aware totals, prompt-cache reads and writes, and the per-1M pricing table |
/usage [--days N] | What Codeep has used across sessions, from its local usage ledger — today, the last 7 days, all time and tokens by model, with the days listed for --days N. The same figures as codeep usage in the shell, which also prints JSON with --json |
/clear | Clear chat |
/exit | Quit application |
Sessions
| Command | Description |
|---|---|
/sessions | List and load sessions |
/new | Start new session |
/rename <name> | Rename current session |
/search <term> | Search the current session |
/recall <query> | Search across all saved sessions, ranked by relevance and recency |
/recall … --resume | Load the top-matching session directly, skipping the picker |
/recall … --summarize | LLM recap of what you did across matches |
/cloud | List and resume sessions synced from other devices |
/export [md|json|txt] | Export chat |
/compact [keepN] | AI-summarize older messages to free up context, keeping the last N (default 4) |
Checkpoints (2.0)
| Command | Description |
|---|---|
/checkpoint [name] | Snapshot conversation + provider/model + git HEAD |
/checkpoints | List saved checkpoints in this workspace |
/rewind <id> | Restore a checkpoint — conversation and provider/model; files roll back via the git command printed afterwards |
/checkpoint delete <id> | Delete a saved checkpoint |
Before a risky multi-step refactor (or when the agent starts going off the rails), save a named snapshot of the conversation. Restore it later if things go sideways. File rollback is delegated to git — Codeep prints the exact git checkout command after rewind.
/checkpoint before-auth-refactor # save snapshot
/checkpoints # list saved checkpoints
/rewind ck-2026-05-18-a1b2c3d4 # restore conversation + provider/model
/checkpoint delete ck-... # remove a snapshotSnapshots include: full conversation history, current provider + model, the list of files the agent touched in this session, and (if cwd is a git repo) the short SHA of HEAD at checkpoint time. Stored under .codeep/checkpoints/<id>.json in your project.
★
Checkpoints don't snapshot file content — by design. Use
git stash or the suggested git checkout <sha> -- <file> printed after rewind to roll files back.Agent Mode
| Command | Description |
|---|---|
/agent <task> | Run agent with task |
/agent-dry <task> | Dry run (no changes) |
/plan <task> | Generate a plan first — review before /go executes |
/go | Execute the pending plan from /plan |
/stop | Stop running agent |
/undo | Undo last agent action |
/undo-all | Undo all agent actions |
/history | Show agent history |
/changes | Show session changes |
Git & Project
| Command | Description |
|---|---|
/diff | Review git diff with AI |
/diff --staged | Review staged changes |
/commit (/c) | Generate commit message |
/git-commit <msg> | Commit with message |
/push (/p) | Git push |
/pull | Git pull |
/amend | Amend last commit |
/branch | Create/manage branches |
/stash | Stash changes |
/unstash | Apply and drop the most recent stash |
/pr | Create a pull request description |
/changelog | Generate changelog from recent commits |
/init | Initialize project (.codeep/ folder) |
/scan | Scan project structure |
/memory <note> | Add note to project intelligence |
/memory list | Show all memory notes |
/memory remove <n> | Remove note by index |
/memory clear | Clear all memory notes |
/review | AI review of unstaged git changes (not full codebase) |
/review --staged | AI review of staged git changes |
/review --static | Static analysis — changed files, or whole src/ if clean |
/review <file> | Static analysis of specific file(s) |
Project intelligence
Initialize a project, scan it once to give the AI deep context about its structure, frameworks, and conventions. Use /memory to add your own notes — they are included in every AI and agent conversation and synced to the dashboard.
★
Example notes:
/memory Always use pnpm, never npm or /memory Main entry point is src/renderer/main.tsCode Operations
| Command | Description |
|---|---|
/copy [n] | Copy code block to clipboard |
/paste | Paste from clipboard |
/apply | Apply file changes from AI |
/add <path> | Add file to context |
/drop [path] | Remove file (or all) from context |
/multiline | Toggle multi-line input mode |
Skills (Shortcuts)
| Command | Description |
|---|---|
/test (/t) | Generate/run tests |
/test-fix | Fix failing tests |
/coverage | Run/analyze test coverage |
/e2e | Generate end-to-end tests |
/mock | Generate mock data for testing |
/docs (/d) | Open web docs for a command |
/readme | Generate or update README |
/api-docs | Generate API documentation |
/refactor (/r) | Improve code quality |
/fix (/f) | Debug and fix issues |
/explain (/e) | Explain code |
/optimize (/o) | Optimize performance |
/debug (/b) | Debug problems |
/security | Security audit (SQLi, XSS, secrets, auth) |
/types | Add or improve TypeScript types |
/cleanup | Clean up code (remove unused, format) |
/modernize | Update code to use modern syntax |
/migrate | Migrate code to newer version |
/split | Split a large file into smaller modules |
/log | Add logging to code |
/translate | Translate code comments to English |
/skills | List all skills |
/skills <query> | Search skills by keyword |
/skills bundles | List skill bundles (project + global) |
/skills create-bundle <name> | Scaffold a bundle in .codeep/skills/ |
/skills show <name> | Print a bundle's SKILL.md |
/skills browse [query] | Search the marketplace at codeep.dev/skills |
/skills install <owner>/<slug> | Install a marketplace bundle into the project |
/skills publish <name> [--public] | Share a bundle to codeep.dev |
/skills unpublish <owner>/<slug> | Remove a bundle you published |
Code Generation
| Command | Description |
|---|---|
/component <name> | Generate UI component |
/api <name> | Generate API endpoint |
/hook | Generate a React hook |
/service | Generate a service/utility module |
/page | Generate a new page/route |
/form | Generate a form with validation |
/crud | Generate full CRUD for an entity |
/docker | Generate Dockerfile + compose |
/ci | Generate CI/CD configuration |
/env | Setup environment configuration |
/k8s | Generate Kubernetes manifests |
/terraform | Generate Terraform configuration |
/nginx | Generate Nginx configuration |
/monitor | Add monitoring and observability |
/build | Build the project |
/deploy | Build and deploy |
/release | Create a new release |
/publish | Publish package to npm |
Settings
| Command | Description |
|---|---|
/provider | Change AI provider |
/model | Change model |
/model <name> | Load saved profile (e.g. /model fast) |
/protocol | Switch API protocol |
/lang | Set response language |
/grant | Grant write permission |
/login | Login with API key |
/logout | Logout from provider |
/profile save <name> | Save current provider+model as profile |
/profile load <name> | Load a saved profile |
/profile list | List saved profiles |
/profile delete <name> | Delete a saved profile |
/openrouter | OpenRouter routing preferences: show, prefer or ignore upstream providers, fallbacks on/off, privacy strict/allow, clear |
/personality | List personalities and custom bots with model, tools, and scope |
/personality <name> | Activate a personality or custom bot. /personality off to clear. |
/me | Your user profile — reply language, style, stack — injected into every run on every surface |
/me init [project] | Scaffold a profile template (global, or for this project). /me off to disable |
/me learn [on|off] | Learn durable prefs from this session now; on/off toggles auto-learn. /me forget clears it |
/me sync | Push your profile to the codeep.dev dashboard (and pull on a fresh machine) |
/agents | List the sub-agents the agent can delegate to — planner, researcher, reviewer, tester, or your own in .codeep/agents/ |
/insights [--days N] | Activity summary — runs, files, tools, projects over the last N days (default 7) |
/telegram | Set up answering confirmations on your phone |
/telegram on|off | Turn Telegram approvals on or off |
/audit | What agents did here — runs, tools, and what the boundary refused |
/audit on|off | Turn the project audit record on or off |
Thinking
| Command | Description |
|---|---|
/thinking (/effort) | Show the thinking tier and what this model supports |
/thinking <auto|low|medium|high|max> | Set the reasoning-effort tier. Auto uses each model's own default; other tiers are clamped to the levels the current provider and model actually distinguish, so an unsupported value is never sent. Models with no graded control ignore it. |
Extensions & MCP (2.0)
| Command | Description |
|---|---|
/mcp | List connected MCP servers + their tools |
/mcp browse [id] | Browse the MCP marketplace, or show one server |
/mcp install <id> [args] | Install a marketplace server into this project |
/mcp add <name> <cmd> | Add a custom MCP server (npx, binary, etc.) |
/mcp remove <name> | Remove a project-scoped MCP server |
/mcp reload | Re-read .codeep/mcp_servers.json (after manual edit) |
/mcp resources | List resources exposed by connected servers |
/mcp read <uri> | Read one MCP resource |
/mcp prompts | List prompt templates exposed by servers |
/mcp prompt <server> <name> | Materialize a prompt with arguments (key=value) |
/hooks | List installed lifecycle hooks (.codeep/hooks/<event>.sh) |
/commands | List custom slash commands (.codeep/commands/*.md) |
/web-cache | Show @web fetch cache stats |
/web-cache clear | Clear the @web fetch cache |
Cloud & Account
| Command | Description |
|---|---|
/account | Show whether this machine is linked to codeep.dev. Linking runs in your shell as codeep account, and the approval link it prints can be opened on any device where you are already signed in |
/tasks | List codeep.dev tasks |
/tasks add <title> [--bug|--feature] [--desc <text>] | Create a task on the dashboard |
/tasks done <n> | Mark task #n as done |
/tasks delete <n> | Delete task #n |
/sync | Sync learning preferences and profiles to codeep.dev |
/sync learning | Sync only learning preferences |
/sync profiles | Sync only saved profiles |
/telemetry [on|off] | Show or toggle automatic cloud telemetry |
/keysync [on|off] | Show or toggle syncing API keys to codeep.dev. Off by default — keys stay in your OS keychain unless you opt in |
Context
| Command | Description |
|---|---|
/context-save | Save conversation |
/context-load | Load conversation |
/context-clear | Clear saved context |
/learn | Learn code preferences |
/learn status | Show learned prefs |
/learn rule <text> | Add custom rule |
Ollama (Local AI)
| Command | Description |
|---|---|
/provider | Select "ollama" for local models |
/settings > Ollama URL | Set URL (default: http://localhost:11434) |
/model | Pick installed Ollama model dynamically |
/model pull <model> | Pull an Ollama model (local Ollama only) |
/model browse | Browse recommended local coding models and pull one |
/model rm <model> | Remove a locally-installed Ollama model (local only) |
OLLAMA_HOST=0.0.0.0 | Required env var for remote Ollama access |
Lifecycle Hooks
Drop executable shell scripts in .codeep/hooks/<event>.sh and Codeep runs them at the relevant moment during a session. Use them to enforce policy (block writes to certain paths), auto-format edits, run lint gates before commit, or log every tool call to your own pipeline.
| Event | When | Blocking? |
|---|---|---|
pre_tool_call | Before every agent tool call (built-in or MCP) | Yes — non-zero exit blocks the call |
post_edit | After write_file / edit_file succeeds (built-in only) | No (advisory) |
on_error | When any tool call fails (built-in or MCP) | No (logging) |
pre_commit | Before /commit stages anything | Yes — non-zero exit blocks the commit |
Each hook receives these environment variables:
CODEEP_HOOK_EVENT # event name
CODEEP_WORKSPACE # workspace root absolute path
CODEEP_SESSION_ID # current session id
CODEEP_HOOK_TOOL # tool name (pre_tool_call, on_error, post_edit)
CODEEP_HOOK_PARAMS # JSON-encoded tool parameters (pre_tool_call, on_error)
CODEEP_HOOK_FILE # absolute file path (post_edit only)Example — auto-format on every edit:
#!/bin/bash
# .codeep/hooks/post_edit.sh
prettier --write "$CODEEP_HOOK_FILE" 2>/dev/null⚠
Hooks are arbitrary shell that runs whenever an agent tool fires. Codeep shows a warning banner on session start if hooks are installed — for the same reason we don't read hooks from a global
~/.codeep/hooks/ directory (only project-scoped, so cloning a hostile repo at least flashes the warning before scripts can run).Custom Slash Commands
Drop a Markdown file in .codeep/commands/<name>.md (project-scoped) or ~/.codeep/commands/<name>.md (global, all projects) and Codeep exposes it as /<name> — in the TUI, the VS Code extension, and any other ACP client (Zed). The file's body becomes the user prompt; the agent handles it normally.
Example: a security review template
Save the following as .codeep/commands/sec-review.md:
---
description: Security review of a file
aliases: [sec, secrev]
---
Please perform a thorough security review of {{args}}. Look for:
- AuthN/AuthZ bypasses, SQL/NoSQL injection, XSS, CSRF
- Path traversal, insecure deserialization
- Hardcoded secrets, race conditions
Report findings ordered by severity.Then call it as /sec-review src/api/login.ts (or /sec via the alias).
Placeholders
| Placeholder | Resolves to |
|---|---|
{{args}} | Full argument string |
$ARGUMENTS | Full argument string (Claude Code compatibility) |
{{arg1}}, {{arg2}}, … | Positional arguments (1-indexed) |
★
Project files shadow global files with the same name, so a per-repo
.codeep/commands/deploy.md can override a global one. Run /commands to list everything available in the current workspace.Image Paste
Press Ctrl+V to paste an image directly from the clipboard into the conversation. Codeep will automatically detect the image and send it to a vision model for analysis.
★
Requires a Z.AI or MiniMax API key. On macOS, copy a screenshot with
Cmd+Shift+4 then press Ctrl+V in Codeep.