amq-cli
Agent Message Queue - file-based inter-agent messaging with co-op mode, cross-project federation, and orchestrator integrations
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/avivsinai--agent-message-queue)HTML
<a href="/listings/avivsinai--agent-message-queue"><img src="/api/listings/avivsinai--agent-message-queue/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
This walkthrough connects **Claude Code** and **Codex CLI** on one machine. Install both agent CLIs and put `claude` and `codex` on `PATH` first. Use macOS, Linux, or WSL; native Windows supports a subset (see the [platform matrix](INSTALL.md#platform-capability-matrix)).
1. Install the binary
On macOS:
brew install avivsinai/tap/amq
On Linux, or without Homebrew, use the installer script or a release download from [Installation](INSTALL.md#binary-installation). Confirm the install with `amq --version`.
2. Install Skill
Install the agent instructions so each agent knows how to use AMQ:
npx skills add avivsinai/agent-message-queue -g -y
Restart the agents after installing. [Other skill installation methods](INSTALL.md) are available if you do not use npm. agy (Antigravity CLI) reads skills from `~/.gemini/config/skills`, so copy the skill there as INSTALL.md shows.
3. Set up the project
In the repository where the agents will work:
amq setup
Select the agents and launcher, then confirm the preview. Setup writes the project configuration and creates the default session and its mailboxes. An agent's handle is its harness name (`claude`, `codex`) unless you enter `handle=harness`, for example `reviewer=claude`. Only the handle goes into the roster and the mailboxes.
4. Start both agents
amq launch
The first launch asks you to trust the launch plan. With `tmux`, `cmux`, or `ghostty`, AMQ starts the agents in that terminal app. With the `commands` backend, it prints one command per agent and exits with code `6` (action required). Paste each complete command into a separate terminal; do not shorten or rebuild it.
By default the wake rings a plain doorbell (text and Enter) on every harness, so it always rings; a doorbell that lands on an open dialog can answer it. Optional, for Claude Code: `amq wake install-dialog-hook` keeps the wake from typing into an open AskUserQuestion, plan, or permission dialog. Add `--harness codex` (then trust the entries in Codex `/hooks`) or `--harness cursor` (or `--harness all`) for their approval prompts. `amq coop exec` prints `dialog guard: plain` or `dialog guard: proper (<harness>)` to show which one a seat gets.
If you use only the Claude Code or Codex desktop app, `amq launch` has no terminal to start. Skip this step and follow [Claude Code desktop app](COOP.md#claude-code-desktop-app) or [Codex desktop app](COOP.md#codex-desktop-app).
Start both agents before sending the first message. Messages that arrive before a recipient's wake starts remain unread but do not trigger that new wake. The recipient can still get them with `amq drain --include-body`.
<a id="messaging"></a>
5. Exchange a message
Ask Claude to run this command through its shell tool:
amq send --to codex --subject "Hello" --body "Can you see this?"
Ask Codex to check its inbox if it has not already responded to the notification:
amq list --new amq drain --include-body
`list` previews new messages. `drain` reads them, moves them out of the new inbox, and writes receipts. The output includes the sender and message body. To reply in the same thread, use the ID from that output:
amq reply --id "<message-id>" --body "Yes, I can see it."
The launched agents already have their identity and session set. You do not need to repeat `--me` or `--root` inside those sessions.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/plugin.json · Manifest · 23 lines
- {
- "name": "amq-cli",
- "version": "0.153.2",
- "description": "Agent Message Queue - file-based inter-agent messaging with co-op mode, cross-project federation, and orchestrator integrations",
- "author": {
- "name": "Aviv Sinai",
- "url": "https://github.com/avivsinai"
- },
- "repository": "https://github.com/avivsinai/agent-message-queue",
- "license": "MIT",
- "skills": "./skills/",
- "keywords": [
- "messaging",
- "agents",
- "maildir",
- "queue",
- "inter-agent",
- "coop",
- "federation",
- "integration",
- "spec"
- ]
- }
README.md · README · 205 lines
- # Agent Message Queue (AMQ)
- **Messaging between coding agents.**
- [](https://github.com/avivsinai/agent-message-queue/actions/workflows/ci.yml)
- [](https://github.com/avivsinai/agent-message-queue/releases/latest)
- [](LICENSE)
- AMQ lets two coding agents exchange messages through a shared directory.
- One agent asks for a review; the other reads the message and replies in the
- same thread. Messages are plain files, so the local queue needs no messaging
- server or database—and you do not have to relay each request yourself.
- Try the queue in a fresh shell on macOS. This example uses two mailbox names;
- it does not start agents. [Other installation methods →](INSTALL.md)
- ```bash
- brew install avivsinai/tap/amq
- amq init --root .agent-mail/demo --agents alice,bob # Create two mailboxes for demo.
- amq send --root .agent-mail/demo --me alice --to bob --body "Please review the parser."
- amq drain --root .agent-mail/demo --me bob --include-body
- ```
- 
- - **Keep the conversation together.** Reply in threads, attach context, and
- route messages between sessions or projects.
- - **Know what happened to a message.** Receipts distinguish a queued message
- from one the recipient drained.
- - **Bring your own agents.** Use the CLI from agent tools or scripts;
- optional wake notifications prompt running agents to check their inboxes.
- - **Keep control of the workflow.** AMQ handles messages. You and your
- orchestration tools own tasks, worktrees, permissions, and merges.
- <a id="quick-start"></a>
- ## Getting started
- This walkthrough connects **Claude Code** and **Codex CLI** on one machine.
- Install both agent CLIs and put `claude` and `codex` on `PATH` first.
- Use macOS, Linux, or WSL; native Windows supports a subset (see the
- [platform matrix](INSTALL.md#platform-capability-matrix)).
- ### 1. Install the binary
- On macOS:
- ```bash
- brew install avivsinai/tap/amq
- ```
- On Linux, or without Homebrew, use the installer script or a release
- download from [Installation](INSTALL.md#binary-installation). Confirm the
- install with `amq --version`.
- ### 2. Install Skill
- Install the agent instructions so each agent knows how to use AMQ:
- ```bash
- npx skills add avivsinai/agent-message-queue -g -y
- ```
- Restart the agents after installing. [Other skill installation methods](INSTALL.md)
- are available if you do not use npm. agy (Antigravity CLI) reads skills from
- `~/.gemini/config/skills`, so copy the skill there as INSTALL.md shows.
- ### 3. Set up the project
- In the repository where the agents will work:
- ```bash
- amq setup
- ```
- Select the agents and launcher, then confirm the preview. Setup writes the
- project configuration and creates the default session and its mailboxes.
- An agent's handle is its harness name (`claude`, `codex`) unless you enter
- `handle=harness`, for example `reviewer=claude`. Only the handle goes into the
- roster and the mailboxes.
- ### 4. Start both agents
- ```bash
- amq launch
- ```
- The first launch asks you to trust the launch plan. With `tmux`, `cmux`, or
- `ghostty`, AMQ starts the agents in that terminal app. With the `commands`
- backend, it prints one command per agent and exits with code `6` (action
- required). Paste each complete command into a separate terminal; do not
- shorten or rebuild it.
- By default the wake rings a plain doorbell (text and Enter) on every harness,
- so it always rings; a doorbell that lands on an open dialog can answer it.
- Optional, for Claude Code: `amq wake install-dialog-hook` keeps the wake from
- typing into an open AskUserQuestion, plan, or permission dialog. Add
- `--harness codex` (then trust the entries in Codex `/hooks`) or
- `--harness cursor` (or `--harness all`) for their approval prompts.
- `amq coop exec` prints `dialog guard: plain` or
- `dialog guard: proper (<harness>)` to show which one a seat gets.
- If you use only the Claude Code or Codex desktop app, `amq launch` has no
- terminal to start. Skip this step and follow
- [Claude Code desktop app](COOP.md#claude-code-desktop-app) or
- [Codex desktop app](COOP.md#codex-desktop-app).
- Start both agents before sending the first message. Messages that arrive
- before a recipient's wake starts remain unread but do not trigger that new
- wake. The recipient can still get them with `amq drain --include-body`.
- <a id="messaging"></a>
- ### 5. Exchange a message
- Ask Claude to run this command through its shell tool:
- ```bash
- amq send --to codex --subject "Hello" --body "Can you see this?"
- ```
- Ask Codex to check its inbox if it has not already responded to the notification:
- ```bash
- amq list --new
- amq drain --include-body
- ```
- `list` previews new messages. `drain` reads them, moves them out of the new
- inbox, and writes receipts. The output includes the sender and message body.
- To reply in the same thread, use the ID from that output:
- ```bash
- amq reply --id "<message-id>" --body "Yes, I can see it."
- ```
- The launched agents already have their identity and session set. You do not
- need to repeat `--me` or `--root` inside those sessions.
- ## How it works
- Each agent has an inbox and an outbox under a local queue root. A message
- contains a JSON header and a Markdown body. AMQ writes and syncs a temporary
- file, then publishes it with a rename: a reader sees a complete message or
- no message, not a partly written body.
- A session is a separate queue. Routing checks help prevent a shell pinned
- to one session from changing another by mistake. A wake notification asks an
- agent to check its inbox; it is not evidence that the agent read or completed
- the request. See [routing](docs/session-routing.md) and
- [message tracing](docs/trace.md) for those contracts.
- Optional [priority holds](docs/wake-operations.md#hold-by-priority) can delay
- the first notification for routine mail while urgent mail skips the hold. Wake
- [live settings](docs/wake-operations.md#live-settings) have a machine default
- for this user (`amq wake config --machine --hold-normal 5m`) and per-agent
- overrides; use `amq wake config --me <handle> --hold-normal 5m` to change a
- running wake.
- AMQ is for local agent coordination, not a distributed broker. The optional
- [bridge companion](cmd/amq-bridge/README.md) exchanges messages between hosts;
- each host keeps control of its own queue.
- ## Remote control
- The optional [remote companion](cmd/amq-remote/README.md) gives a running
- Claude Code or Codex session its own private Buzz channel, so you can write to
- that session from the Buzz app. One machine agent per machine runs inside
- `amq-remote serve`; set it up once with the owner's signed grant.
- No Buzz desktop app is needed. Inside the session, type `/amq-remote`
- (in Codex, `$amq-remote`); `/amq-remote off` disconnects it. Setup, commands,
- and the trust model are in that README.
- ## Documentation
- | I want to… | Read |
- | --- | --- |
- | Install, update, or use another platform | [Installation](INSTALL.md) |
- | Run agent pairs, isolate sessions, or supervise notifications | [Co-op operations](COOP.md) |
- | Batch routine wake notifications by priority | [Wake operations](docs/wake-operations.md#hold-by-priority) |
- | Look up a command or flag | [CLI reference](docs/cli.md) |
- | Diagnose delivery or wake problems | [Wake operations](docs/wake-operations.md) · [Trace](docs/trace.md) |
- | Attach to a running harness session | [amq-remote](cmd/amq-remote/README.md) |
- | Build an integration or understand the design | [Documentation index](docs/README.md) |
- | Understand the trust model | [Security](SECURITY.md) |
- <a id="extension-metadata"></a>
- Building on AMQ? Use the [adapter contract](docs/adapter-contract.md),
- [launch API](docs/launch-api.md), and [extension metadata](docs/adr-layer-extensions.md).
- [amq-squad](https://github.com/omriariav/amq-squad) is a role-aware team launcher
- built on these primitives.
- ## Contributing
- See the [contribution guide](CONTRIBUTING.md) for development and review.
- Contributor clones should install the git hooks
- (`./scripts/install-hooks.sh`) so pushes run the static checks locally.
- Use [GitHub issues](https://github.com/avivsinai/agent-message-queue/issues)
- for questions and bug reports. Follow the [code of conduct](CODE_OF_CONDUCT.md)
- and report security issues through the [security policy](SECURITY.md).
- ## License
- [MIT](LICENSE).
scripts/install.sh · Bundled script · 362 lines · 1 finding marked
- #!/bin/bash
- # AMQ Binary Installer
- # Usage: curl -fsSL https://raw.githubusercontent.com/avivsinai/agent-message-queue/main/scripts/install.sh | bash
- Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
- Line 3 on GitHub
- #
- # Installs to user-local directory (no sudo required):
- # - $GOBIN if set
- # - ~/.local/bin if exists
- # - ~/go/bin if exists
- # - ~/.local/bin (created if needed)
- #
- # Options:
- # curl ... | bash -s -- --skill # Also install Claude Code/Codex skill
- # curl ... | VERSION=v0.7.3 bash # Specific version
- # curl ... | INSTALL_DIR=~/bin bash # Custom install dir
- set -e
- REPO="avivsinai/agent-message-queue"
- VERSION="${VERSION:-latest}"
- INSTALL_SKILL=false
- CALLER_PWD=$PWD
- # Parse arguments
- while [[ $# -gt 0 ]]; do
- case $1 in
- --skill)
- INSTALL_SKILL=true
- shift
- ;;
- *)
- shift
- ;;
- esac
- done
- # Determine install directory (user-local, no sudo needed)
- # Priority: explicit INSTALL_DIR > GOBIN > ~/.local/bin > ~/go/bin
- determine_install_dir() {
- if [ -n "$INSTALL_DIR" ]; then
- echo "$INSTALL_DIR"
- elif [ -n "$GOBIN" ]; then
- echo "$GOBIN"
- elif [ -d "$HOME/.local/bin" ]; then
- echo "$HOME/.local/bin"
- elif [ -d "$HOME/go/bin" ]; then
- echo "$HOME/go/bin"
- else
- # Default to ~/.local/bin (XDG standard)
- echo "$HOME/.local/bin"
- fi
- }
- INSTALL_DIR=$(determine_install_dir)
- case "$INSTALL_DIR" in
- /*) ;;
- *) INSTALL_DIR="$CALLER_PWD/$INSTALL_DIR" ;;
- esac
- GREEN='\033[0;32m'
- RED='\033[0;31m'
- BLUE='\033[0;34m'
- YELLOW='\033[1;33m'
- NC='\033[0m'
- echo -e "${BLUE}=== AMQ Binary Installer ===${NC}"
- echo ""
- # Detect platform
- OS=$(uname -s | tr '[:upper:]' '[:lower:]')
- ARCH=$(uname -m)
- case "$ARCH" in
- x86_64|amd64) ARCH="amd64" ;;
- arm64|aarch64) ARCH="arm64" ;;
- *)
- echo -e "${RED}Error: Unsupported architecture: $ARCH${NC}"
- exit 1
- ;;
- esac
- case "$OS" in
- darwin|linux) ;;
- mingw*|msys*|cygwin*)
- echo -e "${RED}Error: The installer script does not support native Windows.${NC}"
- echo "For the complete coop/wake workflow, use WSL with the Linux installer."
- echo "For native core queue commands, download the Windows ZIP manually:"
- echo " https://github.com/$REPO/releases"
- exit 1
- ;;
- *)
- echo -e "${RED}Error: Unsupported OS: $OS${NC}"
- exit 1
- ;;
- esac
- echo "Platform: ${OS}_${ARCH}"
- # Get version
- if [ "$VERSION" = "latest" ]; then
- echo "Fetching latest version..."
- VERSION=$(curl -fsSL "https://api.github.com/repos/$REPO/releases/latest" | grep '"tag_name"' | cut -d'"' -f4)
- if [ -z "$VERSION" ]; then
- echo -e "${RED}Error: Could not determine latest version${NC}"
- echo "The GitHub API may be unavailable, rate-limited, or blocked by a proxy."
- echo "Try one of:"
- echo " Homebrew: brew install avivsinai/tap/amq"
- echo " Manual download: https://github.com/$REPO/releases"
- echo " Pinned rerun: curl -fsSL https://raw.githubusercontent.com/$REPO/main/scripts/install.sh | VERSION=vX.Y.Z bash"
- exit 1
- fi
- fi
- echo "Version: $VERSION"
- # Build asset name (format: amq_0.7.3_darwin_arm64.tar.gz)
- VERSION_NUM="${VERSION#v}" # Remove 'v' prefix
- ASSET="amq_${VERSION_NUM}_${OS}_${ARCH}.tar.gz"
- URL="https://github.com/$REPO/releases/download/$VERSION/$ASSET"
- CHECKSUMS_URL="https://github.com/$REPO/releases/download/$VERSION/checksums.txt"
- echo "Downloading: $ASSET"
- # Create temp directory
- TMP_DIR=""
- STAGE_DIR=""
- STAGED_BINARY=""
- cleanup() {
- if [ -n "$STAGE_DIR" ]; then
- rm -rf "$STAGE_DIR" || true
- fi
- if [ -n "$TMP_DIR" ]; then
- rm -rf "$TMP_DIR" || true
- fi
- }
- trap cleanup EXIT
- trap 'exit 130' INT
- trap 'exit 143' TERM
- TMP_DIR=$(mktemp -d)
- # Download (curl -f fails on HTTP errors like 404)
- if ! curl -fsSL "$URL" -o "$TMP_DIR/$ASSET"; then
- echo -e "${RED}Error: Download failed (asset not found or network error)${NC}"
- echo "URL: $URL"
- echo "Check available releases: https://github.com/$REPO/releases"
- exit 1
- fi
- # Verify the selected release asset before extracting or installing it.
- CHECKSUMS_FILE="$TMP_DIR/checksums.txt"
- if ! curl -fsSL "$CHECKSUMS_URL" -o "$CHECKSUMS_FILE"; then
- echo -e "${RED}Error: failed to download checksums${NC}"
- exit 1
- fi
- if [ ! -r "$CHECKSUMS_FILE" ]; then
- echo -e "${RED}Error: checksums.txt is missing or unreadable${NC}"
- exit 1
- fi
- if ! CHECKSUM_RESULT=$(awk -v asset="$ASSET" '
- {
- sub(/\r$/, "")
- field = $2
- candidate = field
- sub(/^\*/, "", candidate)
- last = $NF
- sub(/^\*/, "", last)
- if (candidate == asset) {
- count++
- if (NF != 2 ||
- length($1) != 64 ||
- $1 !~ /^[0-9A-Fa-f]+$/ ||
- (field != asset && field != "*" asset)) {
- malformed = 1
- }
- hash = $1
- } else if (last == asset) {
- count++
- malformed = 1
- }
- }
- END {
- if (count == 0) {
- print "missing"
- } else if (count > 1) {
- print "duplicate"
- } else if (malformed) {
- print "malformed"
- } else {
- print "ok:" hash
- }
- }
- ' "$CHECKSUMS_FILE"); then
- echo -e "${RED}Error: checksums.txt is unreadable${NC}"
- exit 1
- fi
- case "$CHECKSUM_RESULT" in
- missing)
- echo -e "${RED}Error: checksum entry not found for $ASSET${NC}"
- exit 1
- ;;
- duplicate)
- echo -e "${RED}Error: duplicate checksum entries found for $ASSET${NC}"
- exit 1
- ;;
- malformed)
- echo -e "${RED}Error: malformed checksum entry for $ASSET${NC}"
- exit 1
- ;;
- ok:*)
- EXPECTED="${CHECKSUM_RESULT#ok:}"
- ;;
- *)
- echo -e "${RED}Error: could not parse checksum entry for $ASSET${NC}"
- exit 1
- ;;
- esac
- if command -v sha256sum &> /dev/null; then
- (cd "$TMP_DIR" && printf '%s %s\n' "$EXPECTED" "$ASSET" | sha256sum -c -) || {
- echo -e "${RED}Error: checksum verification failed${NC}"
- exit 1
- }
- elif command -v shasum &> /dev/null; then
- if ! ACTUAL_LINE=$(shasum -a 256 "$TMP_DIR/$ASSET"); then
- echo -e "${RED}Error: checksum verification failed${NC}"
- exit 1
- fi
- ACTUAL="${ACTUAL_LINE%%[[:space:]]*}"
- EXPECTED_NORMALIZED=$(printf '%s' "$EXPECTED" | tr '[:upper:]' '[:lower:]')
- ACTUAL_NORMALIZED=$(printf '%s' "$ACTUAL" | tr '[:upper:]' '[:lower:]')
- if [ "$EXPECTED_NORMALIZED" != "$ACTUAL_NORMALIZED" ]; then
- echo -e "${RED}Error: checksum verification failed${NC}"
- exit 1
- fi
- else
- echo -e "${RED}Error: sha256sum or shasum is required to verify the download${NC}"
- exit 1
- fi
- if ! tar xzf "$TMP_DIR/$ASSET" -C "$TMP_DIR" 2>/dev/null; then
- echo -e "${RED}Error: Failed to extract archive (corrupted download?)${NC}"
- exit 1
- fi
- if [ -L "$TMP_DIR/amq" ] ||
- [ ! -f "$TMP_DIR/amq" ] ||
- [ ! -s "$TMP_DIR/amq" ] ||
- [ ! -x "$TMP_DIR/amq" ]; then
- echo -e "${RED}Error: archive did not contain a regular executable amq binary${NC}"
- exit 1
- fi
- # Install to user-local directory (no sudo needed)
- echo "Installing to: $INSTALL_DIR/amq"
- # Ensure install directory exists
- mkdir -p "$INSTALL_DIR"
- # Build the replacement beside the target, then atomically publish it.
- if ! STAGE_DIR=$(mktemp -d "$INSTALL_DIR/.amq.install.XXXXXX"); then
- echo -e "${RED}Error: could not create staged install directory${NC}"
- exit 1
- fi
- STAGED_BINARY="$STAGE_DIR/amq"
- if ! install -m 0755 "$TMP_DIR/amq" "$STAGED_BINARY"; then
- echo -e "${RED}Error: failed to stage binary${NC}"
- exit 1
- fi
- if ! chmod 0755 "$STAGED_BINARY" ||
- [ ! -f "$STAGED_BINARY" ] ||
- [ ! -s "$STAGED_BINARY" ] ||
- [ ! -x "$STAGED_BINARY" ]; then
- echo -e "${RED}Error: staged binary validation failed${NC}"
- exit 1
- fi
- if ! "$STAGED_BINARY" --version >/dev/null; then
- echo -e "${RED}Error: staged binary failed its version check${NC}"
- exit 1
- fi
- if ! mv -f "$STAGED_BINARY" "$INSTALL_DIR/"; then
- echo -e "${RED}Error: failed to publish binary${NC}"
- exit 1
- fi
- if [ -e "$STAGED_BINARY" ] ||
- [ -L "$STAGED_BINARY" ] ||
- [ -L "$INSTALL_DIR/amq" ] ||
- [ ! -f "$INSTALL_DIR/amq" ] ||
- [ ! -s "$INSTALL_DIR/amq" ] ||
- [ ! -x "$INSTALL_DIR/amq" ] ||
- ! cmp -s "$TMP_DIR/amq" "$INSTALL_DIR/amq"; then
- echo -e "${RED}Error: published binary validation failed${NC}"
- exit 1
- fi
- rmdir "$STAGE_DIR" 2>/dev/null || true
- STAGE_DIR=""
- STAGED_BINARY=""
- # Verify the exact installed binary, never an older PATH entry.
- INSTALLED_BINARY="$INSTALL_DIR/amq"
- if INSTALLED_VERSION=$("$INSTALLED_BINARY" --version); then
- echo "Installed: $INSTALLED_VERSION"
- else
- echo -e "${RED}Error: installed binary failed its version check${NC}"
- exit 1
- fi
- echo ""
- echo -e "${GREEN}Installation complete!${NC}"
- echo ""
- if ! PATH_AMQ=$(command -v amq 2>/dev/null); then
- echo -e "${YELLOW}Warning: $INSTALL_DIR is not in your PATH${NC}"
- echo ""
- echo "Add it to your shell config:"
- if [ -n "$ZSH_VERSION" ] || [ -f "$HOME/.zshrc" ]; then
- echo " echo 'export PATH=\"\$PATH:$INSTALL_DIR\"' >> ~/.zshrc && source ~/.zshrc"
- else
- echo " echo 'export PATH=\"\$PATH:$INSTALL_DIR\"' >> ~/.bashrc && source ~/.bashrc"
- fi
- else
- case "$PATH_AMQ" in
- /*) ;;
- */*) PATH_AMQ="$CALLER_PWD/$PATH_AMQ" ;;
- esac
- if [[ ! "$PATH_AMQ" -ef "$INSTALLED_BINARY" ]]; then
- echo -e "${YELLOW}Warning: PATH resolves amq to a different executable${NC}"
- echo " PATH-selected: $PATH_AMQ"
- echo " Verified install: $INSTALLED_BINARY"
- echo ""
- echo "Use the verified binary directly, or select it first in this shell:"
- echo " \"$INSTALLED_BINARY\" --version"
- echo " export PATH=\"$INSTALL_DIR:\$PATH\""
- fi
- fi
- echo ""
- # Install skill if requested
- if [ "$INSTALL_SKILL" = true ]; then
- echo -e "${BLUE}Installing Claude Code / Codex skill...${NC}"
- if command -v npx &> /dev/null; then
- if npx skills add avivsinai/agent-message-queue -g -y; then
- echo -e "${GREEN}Skill installed successfully!${NC}"
- else
- echo -e "${YELLOW}Warning: Skill installation failed. Try manually:${NC}"
- echo " npx skills add avivsinai/agent-message-queue -g -y"
- fi
- else
- echo -e "${YELLOW}Warning: npx not found. Install Node.js, then run:${NC}"
- echo " npx skills add avivsinai/agent-message-queue -g -y"
- fi
- echo ""
- fi
- echo "Next steps:"
- echo " 1. Start agent: \"$INSTALLED_BINARY\" coop exec claude"
- echo " Tip: eval \"\$(\"$INSTALLED_BINARY\" shell-setup)\" adds aliases to this shell only."
- echo " Persist zsh aliases: \"$INSTALLED_BINARY\" shell-setup --shell zsh >> ~/.zshrc"
- echo " Persist bash aliases: \"$INSTALLED_BINARY\" shell-setup --shell bash >> ~/.bashrc"
- echo ""
Version history
v0.153.211/18/2026
v0.152.011/17/2026
v0.150.011/16/2026
v0.146.111/15/2026
v0.143.011/14/2026
v0.142.211/13/2026
v0.141.011/12/2026
v0.140.011/11/2026
v0.137.111/9/2026
v0.135.011/8/2026
v0.132.011/7/2026
v0.126.111/5/2026
v0.123.011/2/2026
v0.120.111/1/2026
v0.120.010/31/2026
v0.119.310/30/2026
v0.116.310/29/2026
v0.116.010/28/2026
v0.115.110/27/2026
v0.113.110/26/2026
v0.108.010/25/2026
v0.107.010/24/2026
v0.106.210/23/2026
v0.102.010/21/2026
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.